From 7a8047e75e28c2b5546202152beb8589afaf94e9 Mon Sep 17 00:00:00 2001 From: Aditya Kusupati Date: Tue, 5 Nov 2024 13:57:42 -0800 Subject: [PATCH] Update publications.json --- src/components/publications.json | 3079 ------------------------------ 1 file changed, 3079 deletions(-) diff --git a/src/components/publications.json b/src/components/publications.json index 48e2158..7a100c3 100644 --- a/src/components/publications.json +++ b/src/components/publications.json @@ -1,3083 +1,4 @@ [ - { - "title": "Training Language Model Agents without Modifying Language Models", - "authors": [ - "Shaokun Zhang*", - "Jieyu Zhang*", - "Jiale Liu", - "Linxin Song", - "Chi Wang", - "Ranjay Krishna", - "Qingyun Wu" - ], - "year": "2024", - "venue": "ICML 2024", - "links": { - "pdf": "https://arxiv.org/abs/2402.11359" - }, - }, - { - "title": "Iterated Learning Improves Compositionality in Large Vision-Language Models", - "authors": [ - "Chenhao Zheng", - "Jieyu Zhang", - "Aniruddha Kembhavi", - "Ranjay Krishna" - ], - "year": "2024", - "venue": "CVPR 2024", - "links": { - "pdf": "https://arxiv.org/abs/2404.02145" - }, - }, - { - "title": "SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks", - "authors": [ - "Mohammadreza Salehi", - "Sachin Mehta", - "Aditya Kusupati", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2023", - "venue": "EMNLP Findings 2023", - "links": { - "pdf": "https://arxiv.org/abs/2310.12126" - }, - }, - { - "title": "MatFormer: Nested Transformer for Elastic Inference", - "authors": [ - "Ethan Shen", - "Alan Fan", - "Sarah Pratt", - "Jae Sung Park", - "Matthew Wallingford", - "Sham M. Kakade", - "Ari Holtzman", - "Ranjay Krishna", - "Ali Farhadi", - "Aditya Kusupati" - ], - "year": "2024", - "venue": "NeurIPS 2024", - "links": { - "pdf": "https://arxiv.org/abs/2405.18400" - }, - }, - { - "title": "Objaverse-XL: A Universe of 10M+ 3D Objects", - "authors": [ - "Matt Deitke", - "Ruoshi Liu", - "Matthew Wallingford", - "Huong Ngo", - "Oscar Michel", - "Aditya Kusupati", - "Alan Fan", - "Christian Laforte", - "Vikram Voleti", - "Samir Yitzhak Gadre", - "Eli VanderBilt", - "Aniruddha Kembhavi", - "Carl Vondrick", - "Georgia Gkioxari", - "Kiana Ehsani", - "Ludwig Schmidt", - "Ali Farhadi" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2307.05663", - "code": "https://github.com/allenai/objaverse-xl", - "project page": "https://objaverse.allenai.org/" - }, - "thumbnail": "/objaverse-xl.jpg" - }, - { - "title": "SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality", - "authors": [ - "Cheng-Yu Hsieh*", - "Jieyu Zhang*", - "Zixian Ma", - "Aniruddha Kembhavi", - "Ranjay Krishna" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2306.14610", - "code": "https://github.com/RAIVNLab/sugar-crepe" - }, - "thumbnail": "/sugar-crepe.jpg" - }, - { - "title": "DataComp: In search of the next generation of multimodal datasets", - "authors": [ - "Samir Yitzhak Gadre", - "Gabriel Ilharco", - "Alex Fang", - "Jonathan Hayase", - "Georgios Smyrnis", - "Thao Nguyen", - "Ryan Marten", - "Mitchell Wortsman", - "Dhruba Ghosh", - "Jieyu Zhang", - "Eyal Orgad", - "Rahim Entezari", - "Giannis Daras", - "Sarah Pratt", - "Vivek Ramanujan", - "Yonatan Bitton", - "Kalyani Marathe", - "Stephen Mussmann", - "Richard Vencu", - "Mehdi Cherti", - "Ranjay Krishna", - "Pang Wei Koh", - "Olga Saukh", - "Alexander Ratner", - "Shuran Song", - "Hannaneh Hajishirzi", - "Ali Farhadi", - "Romain Beaumont", - "Sewoong Oh", - "Alex Dimakis", - "Jenia Jitsev", - "Yair Carmon", - "Vaishaal Shankar", - "Ludwig Schmidt." - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2304.14108", - "project page": "https://datacomp.ai/" - }, - "thumbnail": "/datacomp.jpg" - }, - { - "title": "On the Connection between Pre-training Data Diversity and Fine-tuning Robustness", - "authors": [ - "Vivek Ramanujan", - "Thao Nguyen", - "Sewoong Oh", - "Ludwig Schmidt", - "Ali Farhadi" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2307.12532" - }, - }, - { - "title": "OBJECT 3DIT: Language-guided 3D-aware Image Editing", - "thumbnail": "/rotate.gif", - "authors": [ - "Oscar Michel", - "Anand Bhattad", - "Eli VanderBilt", - "Ranjay Krishna", - "Aniruddha Kembhavi", - "Tanmay Gupta" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2307.11073", - "project page": "https://prior.allenai.org/projects/object-edit" - }, - "imageWidth": "calc(7/12*100%)" - }, - { - "title": "MADLAD-400: Monolingual And Document-level Large Audited Dataset", - "authors": [ - "Sneha Kudugunta", - "Isaac Rayburn Caswell", - "Biao Zhang", - "Xavier Garcia", - "Derrick Xin", - "Aditya Kusupati", - "Romi Stella", - "Ankur Bapna", - "Orhan Firat" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2309.04662" - } - }, - { - "title": "Neural Priming for Sample-Efficient Adaptation", - "authors": [ - "Matthew Wallingford", - "Vivek Ramanujan", - "Alex Fang", - "Aditya Kusupati", - "Roozbeh Mottaghi", - "Aniruddha Kembhavi", - "Ludwig Schmidt", - "Ali Farhadi" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2306.10191", - "code": "https://github.com/RAIVNLab/neural-priming" - } - }, - { - "title": "Quilt-1M: One Million Image-Text Pairs for Histopathology", - "thumbnail": "/quilt-1m.jpg", - "authors": [ - "Wisdom Oluchi Ikezogwo", - "Mehmet Saygin Seyfioglu", - "Fatemeh Ghezloo", - "Dylan Stefan Chan Geva", - "Fatwir Sheikh Mohammed", - "Pavan Kumar Anand", - "Ranjay Krishna", - "Linda Shapiro" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "http://arxiv.org/abs/2306.11207", - "code": "https://github.com/wisdomikezogwo/quilt1m" - } - }, - { - "title": "EcoAssistant: Using LLM Assistant More Affordably and Accurately", - "authors": [ - "Jieyu Zhang", - "Ranjay Krishna", - "Ahmed H. Awadallah", - "Chi Wang" - ], - "year": "preprint", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2310.03046", - "code": "https://github.com/JieyuZ2/EcoAssistant" - }, - "thumbnail": "/ecoassistant.png" - }, - { - "title": "Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models", - "authors": [ - "Cheng-Yu Hsieh", - "Si-An Chen", - "Chun-Liang Li", - "Yasuhisa Fujii", - "Alexander Ratner", - "Chen-Yu Lee", - "Ranjay Krishna", - "Tomas Pfister" - ], - "year": "preprint", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2308.00675" - } - }, - { - "title": "MIMIC: Masked Image Modeling with Image Correspondences", - "authors": [ - "Kalyani Marathe", - "Mahtab Bigverdi", - "Nishat Khan", - "Tuhin Kundu", - "Aniruddha Kembhavi", - "Linda G. Shapiro", - "Ranjay Krishna" - ], - "year": "preprint", - "venue": null, - "links": { - "pdf": "https://arxiv.org/pdf/2306.15128.pdf", - "code": "https://github.com/RAIVNLab/MIMIC" - } - }, - { - "title": "Cultural and Linguistic Diversity Improves Visual Representations", - "authors": [ - "Andre Ye", - "Sebastin Santy", - "Jena D. Hwang", - "Amy X. Zhang", - "Ranjay Krishna" - ], - "year": "preprint", - "venue": null, - "links": { - "pdf": "https://arxiv.org/pdf/2310.14356.pdf" - } - }, - { - "title": "Improving Multimodal Datasets with Image Captioning", - "authors": [ - "Thao Nguyen", - "Samir Yitzhak Gadre", - "Gabriel Ilharco", - "Sewoong Oh", - "Ludwig Schmidt" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2307.10350" - } - }, - { - "title": "AdANNS: A Framework for Adaptive Semantic Search", - "authors": [ - "Aniket Rege", - "Aditya Kusupati", - "Sharan Ranjit S", - "Alan Fan", - "Qingqing Cao", - "Sham Kakade", - "Prateek Jain", - "Ali Farhadi" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2305.19435", - "code": "https://github.com/RAIVNLab/AdANNS" - } - }, - { - "title": "Stable and low-precision training for large-scale vision-language models", - "authors": [ - "Mitchell Wortsman", - "Tim Dettmers", - "Luke Zettlemoyer", - "Ari Morcos", - "Ali Farhadi", - "Ludwig Schmidt" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2304.13013" - } - }, - { - "title": "Cola: How to adapt vision-language models to Compose Objects Localized with Attributes?", - "authors": [ - "Arijit Ray", - "Filip Radenovic", - "Abhimanyu Dubey", - "Bryan A. Plummer", - "Ranjay Krishna", - "Kate Saenko" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2305.03689", - "project page": "https://cs-people.bu.edu/array/research/cola/" - } - }, - { - "title": "AR2-D2:Training a Robot Without a Robot", - "authors": [ - "Jiafei Duan", - "Yi Ru Wang", - "Mohit Shridhar", - "Dieter Fox", - "Ranjay Krishna" - ], - "year": "2023", - "venue": "CoRL 2023", - "links": { - "pdf": "https://arxiv.org/abs/2306.13818", - "project page": "http://ar2d2.site/" - }, - "thumbnail": "/ar2d2.jpg" - }, - { - "title": "Selective Visual Representations Improve Convergence and Generalization for Embodied-AI", - "thumbnail": "/codebook_teaser.png", - "authors": [ - "Ainaz Eftekhar*", - "Kuo-Hao Zeng*", - "Jiafei Duan", - "Ali Farhadi", - "Ani Kembhavi", - "Ranjay Krishna" - ], - "year": "2024", - "venue": "ICLR 2024", - "links": { - "pdf": "https://arxiv.org/abs/2311.04193" - } - }, - { - "title": "VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building", - "thumbnail": "/vocalexplore.png", - "authors": [ - "Maureen Daum", - "Enhao Zhang", - "Dong He", - "Stephen Mussmann", - "Brandon Haynes", - "Ranjay Krishna", - "Magdalena Balazinska" - ], - "year": "2024", - "venue": "VLDB 2024", - "links": { - "pdf": "https://arxiv.org/pdf/2303.04068" - } - }, - { - "title": "EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions", - "authors": [ - "Enhao Zhang", - "Maureen Daum", - "Dong He", - "Brandon Haynes", - "Ranjay Krishna", - "Magdalena Balazinska" - ], - "year": "2023", - "venue": "VLDB 2023", - "links": { - "pdf": "https://arxiv.org/pdf/2301.00929" - } - }, - { - "title": "Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias", - "authors": [ - "Yue Yu*", - "Yuchen Zhuang*", - "Jieyu Zhang*", - "Yu Meng", - "Alexander Ratner", - "Ranjay Krishna", - "Jiaming Shen", - "Chao Zhang" - ], - "year": "2023", - "venue": "NeurIPS 2023", - "links": { - "pdf": "https://arxiv.org/abs/2306.15895", - "code": "https://github.com/yueyu1030/AttrPrompt" - } - }, - { - "title": "TIFA: Text-to-Image Faithfulness Evaluation with Question Answering", - "authors": [ - "Yushi Hu", - "Benlin Liu", - "Jungo Kasai", - "Yizhong Wang", - "Mari Ostendorf", - "Ranjay Krishna", - "Noah A. Smith" - ], - "year": "2023", - "venue": "ICCV 2023", - "links": { - "pdf": "https://arxiv.org/abs/2303.11897", - "project page": "https://tifa-benchmark.github.io/" - } - }, - { - "title": "What does a platypus look like? Generating customized prompts for zero-shot image classification", - "authors": [ - "Sarah Pratt", - "Ian Covert", - "Rosanne Liu", - "Ali Farhadi" - ], - "year": "2023", - "venue": "ICCV 2023", - "links": { - "pdf": "https://arxiv.org/abs/2209.03320", - "code": "https://github.com/sarahpratt/CuPL" - } - }, - { - "title": "Agile Modeling: From Concept to Classifier in Minutes", - "authors": [ - "Otilia Stretcu", - "Edward Vendrow", - "Kenji Hata", - "Krishnamurthy Viswanathan", - "Vittorio Ferrari", - "Sasan Tavakkol", - "Wenlei Zhou", - "Aditya Avinash", - "Enming Luo", - "Neil Gordon Alldrin", - "MohammadHossein Bateni", - "Gabriel Berger", - "Andrew Bunner", - "Chun-Ta Lu", - "Javier A Rey", - "Giulia DeSalvo", - "Ranjay Krishna", - "Ariel Fuxman" - ], - "year": "2023", - "venue": "ICCV 2023", - "links": { - "pdf": "https://arxiv.org/abs/2302.12948" - } - }, - { - "title": "Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes", - "authors": [ - "Cheng-Yu Hsieh", - "Chun-Liang Li", - "Chih-Kuan Yeh", - "Hootan Nakhost", - "Yasuhisa Fujii", - "Alexander Ratner", - "Ranjay Krishna", - "Chen-Yu Lee", - "Tomas Pfister" - ], - "year": "2023", - "venue": "ACL 2023 (Findings)", - "links": { - "pdf": "https://arxiv.org/pdf/2305.02301" - } - }, - { - "title": "CREPE: Can Vision-Language Foundation Models Reason Compositionally?", - "authors": [ - "Zixian Ma", - "Jerry Hong", - "Mustafa Omer Gul", - "Mona Gandhi", - "Irena Gao", - "Ranjay Krishna" - ], - "year": "2023", - "venue": "CVPR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2212.07796" - }, - "thumbnail": "/crepe.jpg" - }, - { - "title": "Objaverse: A Universe of Annotated 3D Objects", - "thumbnail": "/objaverse-1.png", - "authors": [ - "Matt Deitke", - "Dustin Schwenk", - "Jordi Salvador", - "Luca Weihs", - "Oscar Michel", - "Eli VanderBilt", - "Ludwig Schmidt", - "Kiana Ehsani", - "Aniruddha Kembhavi", - "Ali Farhadi" - ], - "year": "2023", - "venue": "CVPR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2212.08051", - "project page": "https://objaverse.allenai.org/" - } - }, - { - "title": "Phone2Proc: Bringing Robust Robots Into Our Chaotic World", - "thumbnail": "/phone-2-proc.jpg", - "authors": [ - "Matt Deitke", - "Rose Hendrix", - "Luca Weihs", - "Ali Farhadi", - "Kiana Ehsani", - "Aniruddha Kembhavi" - ], - "year": "2023", - "venue": "CVPR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2212.04819", - "project page": "https://allenai.org/project/phone2proc/home" - } - }, - { - "title": "Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics", - "authors": [ - "Kuo-Hao Zeng", - "Luca Weihs", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2023", - "venue": "ICLR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2304.12289", - "project page": "https://prior.allenai.org/projects/action-adaptive-policy" - } - }, - { - "title": "Impossibly Good Experts and How to Follow Them", - "authors": [ - "Aaron Walsman", - "Muru Zhang", - "Sanjiban Choudhury", - "Dieter Fox", - "Ali Farhadi" - ], - "year": "2023", - "venue": "ICLR 2023", - "links": { - "pdf": "https://openreview.net/forum?id=sciA_xgYofB" - } - }, - { - "title": "Neural Radiance Field Codebooks", - "authors": [ - "Matthew Wallingford", - "Aditya Kusupati", - "Alex Fang", - "Vivek Ramanujan", - "Aniruddha Kembhavi", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2023", - "venue": "ICLR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2301.04101" - } - }, - { - "title": "Editing Models with Task Arithmetic", - "thumbnail": "/arithmetic.png", - "authors": [ - "Gabriel Ilharco", - "Marco Tulio Ribeiro", - "Mitchell Wortsman", - "Suchin Gururangan", - "Ludwig Schmidt", - "Hannaneh Hajishirzi", - "Ali Farhadi" - ], - "year": "2023", - "venue": "ICLR 2023", - "links": { - "pdf": "https://arxiv.org/abs/2212.04089", - "code": "https://github.com/mlfoundations/task_vectors" - } - }, - { - "title": "lo-fi: distributed fine-tuning without communication", - "authors": [ - "Mitchell Wortsman", - "Suchin Gururangan", - "Shen Li", - "Ali Farhadi", - "Ludwig Schmidt", - "Michael Rabbat", - "Ari S. Morcos" - ], - "year": "2023", - "venue": "TMLR", - "links": { - "pdf": "https://arxiv.org/abs/2210.11948" - } - }, - { - "title": "​Explanations can Reduce Overreliance on AI Systems during Decision-Making", - "authors": [ - "Helena Vasconcelos", - "Matthew Jorke", - "Madeleine Grunde-McLaughlin", - "Tobias Gerstenberg", - "Michael Bernstein", - "Ranjay Krishna" - ], - "year": "2023", - "venue": "CSCW 2023", - "links": { - "pdf": "https://arxiv.org/abs/2212.06823" - } - }, - { - "title": "ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward", - "authors": [ - "Zixian Ma", - "Rose Wang", - "Li Fei-Fei", - "Michael Bernstein", - "Ranjay Krishna" - ], - "year": "2022", - "venue": "NeurIPS 2022", - "links": { - "pdf": "https://arxiv.org/abs/2210.04365" - } - }, - { - "title": "Patching open-vocabulary models by interpolating weights", - "authors": [ - "Gabriel Ilharco*", - "Mitchell Wortsman*", - "Samir Yitzhak Gadre*", - "Shuran Song", - "Hannaneh Hajishirzi", - "Simon Kornblith", - "Ali Farhadi", - "Ludwig Schmidt" - ], - "year": "2022", - "venue": "NeurIPS 2022", - "links": { - "pdf": "https://arxiv.org/abs/2208.05592", - "code": "https://github.com/mlfoundations/patching" - } - }, - { - "title": "ProcTHOR: Large-Scale Embodied AI Using Procedural Generation", - "thumbnail": "/procthor-3.jpg", - "authors": [ - "Matt Deitke", - "Eli VanderBilt", - "Alvaro Herrasti", - "Luca Weihs", - "Jordi Salvador", - "Kiana Ehsani", - "Winson Han", - "Eric Kolve", - "Ali Farhadi", - "Aniruddha Kembhavi", - "Roozbeh Mottaghi" - ], - "year": "2022", - "venue": "NeurIPS 2022", - "award": "Outstanding Paper Award", - "links": { - "pdf": "https://arxiv.org/abs/2206.06994", - "project page": " https://procthor.allenai.org" - } - }, - { - "title": "Matryoshka Representation Learning", - "authors": [ - "Aditya Kusupati*", - "Gantavya Bhatt*", - "Aniket Rege*", - "Matthew Wallingford", - "Aditya Sinha", - "Vivek Ramanujan", - "William Howard-Snyder", - "Kaifeng Chen", - "Sham Kakade", - "Prateek Jain", - "Ali Farhadi" - ], - "year": "2022", - "venue": "NeurIPS 2022", - "links": { - "pdf": "https://arxiv.org/abs/2205.13147", - "code": "https://github.com/RAIVNLab/MRL" - } - }, - { - "title": "LAION-5B: An open large-scale dataset for training next generation image-text models", - "thumbnail": "/laion-5b-2.jpg", - "authors": [ - "Christoph Schuhmann", - "Romain Beaumont", - "Richard Vencu", - "Cade Gordon", - "Ross Wightman", - "Mehdi Cherti", - "Theo Coombes", - "Aarush Katta", - "Clayton Mullis", - "Mitchell Wortsman", - "Patrick Schramowski", - "Srivatsa Kundurthy", - "Katherine Crowson", - "Ludwig Schmidt", - "Robert Kaczmarczyk", - "Jenia Jitsev" - ], - "year": "2022", - "venue": "NeurIPS 2022 Datasets and Benchmarks track", - "award": "Outstanding Paper Award", - "links": { - "pdf": "https://arxiv.org/abs/2210.08402", - "project page": "https://laion.ai/laion-5b-a-new-era-of-open-large-scale-multi-modal-datasets/" - } - }, - { - "title": "Socially situated artificial intelligence enables learning from human interaction", - "authors": [ - "Ranjay Krishna", - "Donsuk Lee", - "Li Fei-Fei*", - "Michael Bernstein" - ], - "year": "2022", - "venue": "PNAS 2022", - "links": { - "pdf": "https://www.pnas.org/doi/10.1073/pnas.2115730119" - } - }, - { - "title": "Break and Make: Interactive Structural Understanding Using LEGO Bricks", - "authors": [ - "Aaron Walsman", - "Muru Zhang", - "Klemen Kotar", - "Karthik Desingh", - "Ali Farhadi", - "Dieter Fox" - ], - "year": "2022", - "venue": "ECCV 2022", - "links": { - "pdf": "https://arxiv.org/abs/2207.13738", - "code": "https://github.com/aaronwalsman/ltron" - } - }, - { - "title": "Object Manipulation via Visual Target Localization", - "authors": [ - "Kiana Ehsani", - "Ali Farhadi", - "Aniruddha Kembhavi", - "Roozbeh Mottaghi" - ], - "year": "2022", - "venue": "ECCV 2022", - "links": { - "pdf": "https://arxiv.org/abs/2203.08141" - } - }, - { - "title": "Exposing the Limits of Video-Text Models through Contrast Sets", - "authors": [ - "Jae Sung Park", - "Sheng Shen", - "Ali Farhadi", - "Trevor Darrell", - "Yejin Choi", - "Anna Rohrbach" - ], - "year": "2022", - "venue": "NAACL 2022", - "links": { - "pdf": "https://aclanthology.org/2022.naacl-main.261/" - } - }, - { - "title": "Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time", - "authors": [ - "Mitchell Wortsman", - "Gabriel Ilharco", - "Samir Yitzhak Gadre", - "Rebecca Roelofs", - "Raphael Gontijo-Lopes", - "Ari S. Morcos", - "Hongseok Namkoong", - "Ali Farhadi", - "Yair Carmon*", - "Simon Kornblith*", - "Ludwig Schmidt*" - ], - "year": "2022", - "venue": "ICML 2022", - "links": { - "pdf": "https://arxiv.org/abs/2203.05482", - "code": "https://github.com/mlfoundations/model-soups" - } - }, - { - "title": "Robust fine-tuning of zero-shot models", - "authors": [ - "Mitchell Wortsman*", - "Gabriel Ilharco*", - "Jong Wook Kim", - "Mike Li", - "Simon Kornblith", - "Rebecca Roelofs", - "Raphael Gontijo Lopes", - "Hannaneh Hajishirzi", - "Ali Farhadi", - "Hongseok Namkoong", - "Ludwig Schmidt" - ], - "year": "2022", - "venue": "CVPR 2022", - "award": "Best Paper Honorable Mention", - "links": { - "pdf": "https://arxiv.org/abs/2109.01903", - "code": "https://github.com/mlfoundations/wise-ft" - } - }, - { - "title": "MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound", - "thumbnail": "/merlot-reserve.jpg", - "authors": [ - "Rowan Zellers", - "Jiasen Lu", - "Ximing Lu", - "Youngjae Yu", - "Yanpeng Zhao", - "Mohammadreza Salehi", - "Aditya Kusupati", - "Jack Hessel", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2022", - "venue": "CVPR 2022", - "links": { - "pdf": "https://arxiv.org/abs/2201.02639", - "project page": "https://rowanzellers.com/merlotreserve" - } - }, - { - "title": "Forward Compatible Training for Representation Learning", - "authors": [ - "Vivek Ramanujan", - "Pavan Kumar Anasosalu Vasu", - "Ali Farhadi", - "Oncel Tuzel", - "Hadi Pouransari" - ], - "year": "2022", - "venue": "CVPR 2022", - "links": { - "pdf": "https://arxiv.org/abs/2112.02805" - } - }, - { - "title": "Measuring Compositional Consistency for Video Question Answering", - "authors": [ - "Mona Gandhi*", - "Mustafa Omer Gul*", - "Eva Prakash", - "Madeleine Grunde-McLaughlin", - "Ranjay Krishna", - "Maneesh Agrawala" - ], - "year": "2022", - "venue": "CVPR 2022", - "links": { - "pdf": "https://arxiv.org/abs/2204.07190" - } - }, - { - "title": "VOCAL: Video Organization and Interactive AnaLytics", - "authors": [ - "Maureem Daum*", - "Enhao Zhang*", - "Dong He", - "Magdalena Balazinska", - "Brandon Hayes", - "Ranjay Krishna", - "Apryle Craig", - "Aaron Wirsing" - ], - "year": "2022", - "venue": "CIDR 2022", - "links": { - "pdf": "http://cidrdb.org/cidr2022/papers/p41-daum.pdf" - } - }, - { - "title": "Searching for Computer Vision North Stars", - "authors": [ - "Li Fei-Fei", - "Ranjay Krishna" - ], - "year": "2022", - "venue": "Book: Daedalus Special issue on \"AI & Society\" | Daedalus Spring 2022", - "links": { - "pdf": "https://www.amacad.org/sites/default/files/publication/downloads/Daedalus_Sp22_06_Li.pdf", - "project page": "https://www.amacad.org/publication/searching-computer-vision-north-stars" - } - }, - { - "title": "ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users", - "authors": [ - "Dhruv Jain", - "Khoa Huynh Anh Nguyen", - "Steven Goodman", - "Rachel Grossman-Kahn", - "Hung Ngo", - "Aditya Kusupati", - "Ruofei Du", - "Alex Olwal", - "Leah Findlater", - "Jon E. Froehlich" - ], - "year": "2022", - "venue": "CHI 2022", - "links": { - "pdf": "https://arxiv.org/abs/2202.11134" - } - }, - { - "title": "The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents", - "authors": [ - "Sarah Pratt", - "Luca Weihs", - "Ali Farhadi" - ], - "year": "2022", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2201.00411", - "code": "https://github.com/sarahpratt/introspective" - } - }, - { - "title": "LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time", - "authors": [ - "Elvis Nunez*", - "Maxwell Horton*", - "Anish Prabhu", - "Anurag Ranjan", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2022", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2110.04252" - } - }, - { - "title": "FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling", - "authors": [ - "Christopher Xie", - "Keunhong Park", - "Ricardo Martin-Brualla", - "Matthew Brown" - ], - "year": "2021", - "venue": "3DV 2021", - "links": { - "pdf": "https://arxiv.org/abs/2104.08418", - "project page": "https://fig-nerf.github.io/" - } - }, - { - "title": "MERLOT: Multimodal Neural Script Knowledge Models", - "thumbnail": "/merlot.jpg", - "authors": [ - "Rowan Zellers", - "Ximing Lu", - "Jack Hessel", - "Youngjae Yu", - "Jae Sung Park", - "Jize Cao", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2021", - "venue": "NeurIPS 2021", - "links": { - "pdf": "https://arxiv.org/abs/2106.02636", - "project page": "https://rowanzellers.com/merlot/" - } - }, - { - "title": "LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes", - "authors": [ - "Aditya Kusupati", - "Matthew Wallingford", - "Vivek Ramanujan", - "Raghav Somani", - "Jae Sung Park", - "Krishna Pillutla", - "Prateek Jain", - "Sham Kakade", - "Ali Farhadi" - ], - "year": "2021", - "venue": "NeurIPS 2021", - "links": { - "pdf": "https://arxiv.org/abs/2106.01487", - "code": "https://github.com/RAIVNLab/LLC" - } - }, - { - "title": "LanguageRefer: Spatial-Language Model for 3D Visual Grounding", - "authors": [ - "Junha Roh", - "Karthik Desingh", - "Ali Farhadi", - "Dieter Fox" - ], - "year": "2021", - "venue": "CoRL 2021", - "links": { - "pdf": "https://arxiv.org/abs/2107.03438", - "project page": "https://sites.google.com/view/language-refer" - } - }, - { - "title": "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields", - "authors": [ - "Keunhong Park", - "Utkarsh Sinha", - "Peter Hedman", - "Jonathan T. Barron", - "Sofien Bouaziz", - "Dan B Goldman", - "Ricardo Martin-Brualla", - "Steven M. Seitz" - ], - "year": "2021", - "venue": "SIGGRAPH Asia 2021", - "links": { - "pdf": "https://arxiv.org/abs/2106.13228", - "project page": "https://hypernerf.github.io/" - } - }, - { - "title": "Finetuning Pretrained Transformers into RNNs", - "authors": [ - "Jungo Kasai", - "Hao Peng", - "Yizhe Zhang", - "Dani Yogatama", - "Gabriel Ilharco", - "Nikolaos Pappas", - "Yi Mao", - "Weizhu Chen", - "Noah A Smith" - ], - "year": "2021", - "venue": "EMNLP 2021", - "links": { - "pdf": "https://arxiv.org/abs/2103.13076" - } - }, - { - "title": "Parameter Norm Growth During Training of Transformers", - "authors": [ - "William Merrill", - "Vivek Ramanujan", - "Yoav Goldberg", - "Roy Schwartz", - "Noah A. Smith" - ], - "year": "2021", - "venue": "EMNLP 2021", - "links": { - "pdf": "https://arxiv.org/abs/2010.09697" - } - }, - { - "title": "Deformable Neural Radiance Fields", - "authors": [ - "Keunhong Park", - "Utkarsh Sinha", - "Jonathan T. Barron", - "Sofien Bouaziz", - "Dan B Goldman", - "Steven M. Seitz", - "Ricardo Martin-Brualla" - ], - "year": "2021", - "venue": "ICCV 2021", - "links": { - "pdf": "https://arxiv.org/abs/2011.12948", - "project page": "https://nerfies.github.io/" - } - }, - { - "title": "Contrasting Contrastive Self-Supervised Representation Learning Models", - "authors": [ - "Klemen Kotar", - "Gabriel Ilharco", - "Ludwig Schmidt", - "Kiana Ehsani", - "Roozbeh Mottaghi" - ], - "year": "2021", - "venue": "ICCV 2021", - "links": { - "pdf": "https://arxiv.org/abs/2103.14005" - } - }, - { - "title": "PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World", - "authors": [ - "Rowan Zellers", - "Ari Holtzman", - "Matthew Peters", - "Roozbeh Mottaghi", - "Aniruddha Kembhavi", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2021", - "venue": "ACL 2021", - "links": { - "pdf": "https://arxiv.org/abs/2106.00188", - "project page": "https://rowanzellers.com/piglet/" - } - }, - { - "title": "Learning Neural Network Subspaces", - "authors": [ - "Mitchell Wortsman", - "Maxwell Horton", - "Carlos Guestrin", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2021", - "venue": "ICML 2021", - "links": { - "pdf": "https://arxiv.org/abs/2102.10472", - "code": "https://github.com/apple/learning-subspaces" - } - }, - { - "title": "Probing Text Models for Common Ground with Visual Representations", - "authors": [ - "Gabriel Ilharco", - "Rowan Zellers", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2021", - "venue": "NAACL 2021", - "links": { - "pdf": "https://arxiv.org/abs/2005.00619" - } - }, - { - "title": "TuringAdvice: A Generative and Dynamic Evaluation of Language Use", - "authors": [ - "Rowan Zellers", - "Ari Holtzman", - "Elizabeth Clark", - "Lianhui Qin", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2021", - "venue": "NAACL 2021", - "links": { - "pdf": "https://arxiv.org/abs/2004.03607", - "project page": "https://rowanzellers.com/advice/" - } - }, - { - "title": "Pushing it out of the Way: Interactive Visual Navigation", - "authors": [ - "Kuo-Hao Zeng", - "Luca Weihs", - "Ali Farhadi", - "Roozbeh Mottaghi" - ], - "year": "2021", - "venue": "CVPR 2021", - "links": { - "pdf": "https://arxiv.org/abs/2104.14040", - "project page": "https://prior.allenai.org/projects/interactive-visual-navigation", - "code": "https://github.com/KuoHaoZeng/Interactive_Visual_Navigation" - } - }, - { - "title": "ManipulaTHOR: A Framework for Visual Object Manipulation", - "authors": [ - "Kiana Ehsani", - "Winson Han", - "Alvaro Herrasti", - "Eli VanderBilt", - "Eric Kolve", - "Luca Weihs", - "Aniruddha Kembhavi", - "Roozbeh Mottaghi" - ], - "year": "2021", - "venue": "CVPR 2021", - "links": { - "pdf": "https://arxiv.org/abs/2104.11213", - "code": "https://github.com/allenai/manipulathor" - } - }, - { - "title": "What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions", - "authors": [ - "Kiana Ehsani", - "Daniel Gordon", - "Thomas Nguyen", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2021", - "venue": "ICLR 2021", - "links": { - "pdf": "https://arxiv.org/abs/2010.08539", - "code": "https://github.com/ehsanik/muscleTorch" - } - }, - { - "title": "Learning Generalizable Visual Representations via Interactive Gameplay", - "authors": [ - "Luca Weihs", - "Aniruddha Kembhavi", - "Kiana Ehsani", - "Sarah Pratt", - "Winson Han", - "Alvaro Herrasti", - "Eric Kolve", - "Dustin Schwenk", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2021", - "venue": "ICLR 2021", - "links": { - "pdf": "https://openreview.net/forum?id=UuchYL8wSZo" - } - }, - { - "title": "MultiModalQA: complex question answering over text, tables and images", - "authors": [ - "Alon Talmor", - "Ori Yoran", - "Amnon Catav", - "Dan Lahav", - "Yizhong Wang", - "Akari Asai", - "Gabriel Ilharco", - "Hannaneh Hajishirzi", - "Jonathan Berant" - ], - "year": "2021", - "venue": "ICLR 2021", - "links": { - "pdf": "https://openreview.net/forum?id=ee6W5UgQLa" - } - }, - { - "title": "Layer-Wise Data-Free CNN Compression", - "authors": [ - "Maxwell Horton", - "Yanzi Jin", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2021", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2011.09058" - } - }, - { - "title": "AllenAct: A Framework for Embodied AI Research", - "authors": [ - "Luca Weihs", - "Jordi Salvador", - "Klemen Kotar", - "Unnat Jain", - "Kuo-Hao Zeng", - "Roozbeh Mottaghi", - "Aniruddha Kembhavi" - ], - "year": "2021", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2008.12760", - "code": "https://github.com/allenai/allenact", - "project page": "https://allenact.org/" - } - }, - { - "title": "Are We Overfitting to Experimental Setups in Recognition?", - "authors": [ - "Matthew Wallingford", - "Aditya Kusupati*", - "Keivan Alizadeh-Vahid*", - "Aaron Walsman", - "Aniruddha Kembhavi", - "Ali Farhadi" - ], - "year": "2021", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2007.02519", - "code": "https://github.com/RAIVNLab/InTheWild", - "project page": "https://raivn.cs.washington.edu/projects/FLUID" - } - }, - { - "title": "Watching the World Go By: Representation Learning from Unlabeled Videos", - "authors": [ - "Daniel Gordon", - "Kiana Ehsani", - "Dieter Fox", - "Ali Farhadi" - ], - "year": "2021", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2003.07990", - "project page": "https://danielgordon10.github.io/papers/vince.html", - "code": "https://github.com/danielgordon10/vince" - } - }, - { - "title": "Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping", - "authors": [ - "Jesse Dodge", - "Gabriel Ilharco", - "Roy Schwartz", - "Ali Farhadi", - "Hannaneh Hajishirzi", - "Noah A. Smith" - ], - "year": "2021", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/2002.06305" - } - }, - { - "title": "Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs", - "authors": [ - "Ana Marasovic", - "Chandra Bhagavatula", - "Jae Sung Park", - "Ronan Le Bras", - "Noah A. Smith", - "Yejin Choi" - ], - "year": "2020", - "venue": "EMNLP (Findings) 2020", - "links": { - "pdf": "https://arxiv.org/abs/2010.07526" - } - }, - { - "title": "Multiple Topologies Prediction for Navigation at Unsignalized Intersections", - "authors": [ - "Junha Roh*", - "Christoforos Mavrogiannis*", - "Rishabh Madan*", - "Dieter Fox", - "Siddhartha S. Srinivasa" - ], - "year": "2020", - "venue": "CoRL 2020", - "links": { - "pdf": "https://arxiv.org/abs/2011.03894", - "project page": "https://sites.google.com/view/multiple-topologies-prediction", - "code": "https://github.com/rohjunha/multiple-topologies-prediction" - } - }, - { - "title": "Supermasks in Superposition", - "authors": [ - "Mitchell Wortsman*", - "Vivek Ramanujan*", - "Rosanne Liu", - "Aniruddha Kembhavi", - "Mohammad Rastegari", - "Jason Yosinski", - "Ali Farhadi" - ], - "year": "2020", - "venue": "NeurIPS 2020", - "links": { - "pdf": "https://arxiv.org/abs/2006.14769", - "code": "https://github.com/RAIVNLab/supsup" - } - }, - { - "title": "RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference", - "authors": [ - "Oindrila Saha", - "Aditya Kusupati", - "Harsha Vardhan Simhadri", - "Manik Varma", - "Prateek Jain" - ], - "year": "2020", - "venue": "NeurIPS 2020", - "links": { - "pdf": "https://arxiv.org/abs/2002.11921", - "code": "https://github.com/microsoft/EdgeML" - } - }, - { - "title": "A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks", - "authors": [ - "Unnat Jain", - "Luca Weihs", - "Eric Kolve", - "Ali Farhadi", - "Svetlana Lazebnik", - "Aniruddha Kembhavi", - "Alexander Schwing" - ], - "year": "2020", - "venue": "ECCV 2020", - "links": { - "pdf": "https://arxiv.org/abs/2007.04979", - "project page": "https://unnat.github.io/cordial-sync" - } - }, - { - "title": "Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still Image", - "authors": [ - "Jae Sung Park", - "Chandra Bhagavatula", - "Roozbeh Mottaghi", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2020", - "venue": "ECCV 2020", - "links": { - "pdf": "https://arxiv.org/abs/2004.10796", - "project page": "https://visualcomet.xyz" - } - }, - { - "title": "Grounded Situation Recognition", - "authors": [ - "Sarah Pratt", - "Mark Yatskar", - "Luca Weihs", - "Ali Farhadi", - "Aniruddha Kembhavi" - ], - "year": "2020", - "venue": "ECCV 2020", - "links": { - "pdf": "https://arxiv.org/abs/2003.12058", - "project page": "https://prior.allenai.org/projects/gsr" - } - }, - { - "title": "Identity Aware Multi-Sentence Video Description", - "authors": [ - "Jae Sung Park", - "Trevor Darrell", - "Anna Rohrbach" - ], - "year": "2020", - "venue": "ECCV 2020", - "links": { - "pdf": "https://arxiv.org/abs/2008.09791", - "project page": "https://sites.google.com/site/describingmovies/lsmdc-2019" - } - }, - { - "title": "Soft Threshold Weight Reparameterization for Learnable Sparsity", - "authors": [ - "Aditya Kusupati", - "Vivek Ramanujan*", - "Raghav Somani*", - "Mitchell Wortsman*", - "Prateek Jain", - "Sham Kakade", - "Ali Farhadi" - ], - "year": "2020", - "venue": "ICML 2020", - "links": { - "pdf": "https://arxiv.org/abs/2002.03231", - "code": "https://github.com/RAIVNLab/STR", - "project page": "https://homes.cs.washington.edu/~kusupati/#Kusupati20" - } - }, - { - "title": "Adversarial Filters of Dataset Biases", - "authors": [ - "Ronan Le Bras", - "Swabha Swayamdipta", - "Chandra Bhagavatula", - "Rowan Zellers", - "Matthew Peters", - "Ashish Sabharwal", - "Yejin Choi" - ], - "year": "2020", - "venue": "ICML 2020", - "links": { - "pdf": "https://arxiv.org/abs/2002.04108" - } - }, - { - "title": "What\u2019s Hidden in a Randomly Weighted Neural Network?", - "authors": [ - "Vivek Ramanujan*", - "Mitchell Wortsman*", - "Aniruddha Kembhavi", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/1911.13299", - "code": "https://github.com/allenai/hidden-networks" - } - }, - { - "title": "RoboTHOR: An Open Simulation-to-Real Embodied AI Platform", - "thumbnail": "/robothor-small.jpg", - "authors": [ - "Matt Deitke", - "Winson Han", - "Alvaro Herrasti", - "Aniruddha Kembhavi", - "Eric Kolve", - "Roozbeh Mottaghi", - "Jordi Salvador", - "Dustin Schwenk", - "Eli VanderBilt", - "Mathew Walingford", - "Luca Weihs", - "Mark Yatskar", - "Ali Farhadi" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/2004.06799", - "project page": "https://ai2thor.allenai.org/robothor/" - } - }, - { - "title": "Visual Reaction: Learning to Play Catch with Your Drone", - "authors": [ - "Kuo-Hao Zeng", - "Roozbeh Mottaghi", - "Luca Weihs", - "Ali Farhadi" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/1912.02155", - "code": "http://github.com/KuoHaoZeng/Visual_Reaction" - } - }, - { - "title": "Butterfly Transform: An Efficient FFT Based Neural Architecture Design", - "authors": [ - "Keivan Alizadeh-Vahid", - "Anish Prabhu", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/1906.02256", - "code": "https://github.com/keivanalizadeh/ButterflyTransform" - } - }, - { - "title": "Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects", - "authors": [ - "Kiana Ehsani", - "Shubham Tulsiani", - "Saurabh Gupta", - "Ali Farhadi", - "Abhinav Gupta" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/2003.12045", - "project page": "https://ehsanik.github.io/forcecvpr2020/", - "code": "https://github.com/ehsanik/touchTorch" - } - }, - { - "title": "ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks", - "authors": [ - "Mohit Shridhar", - "Jesse Thomason", - "Daniel Gordon", - "Yonatan Bisk", - "Winson Han", - "Roozbeh Mottaghi", - "Luke Zettlemoyer", - "Dieter Fox" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/1912.01734", - "project page": "https://askforalfred.com/", - "code": "https://github.com/askforalfred/alfred" - } - }, - { - "title": "LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation", - "authors": [ - "Keunhong Park", - "Arsalan Mousavian", - "Yu Xiang", - "Dieter Fox" - ], - "year": "2020", - "venue": "CVPR 2020", - "links": { - "pdf": "https://arxiv.org/abs/1912.00416", - "code": "https://github.com/NVlabs/latentfusion" - } - }, - { - "title": "Discovering Neural Wirings", - "authors": [ - "Mitchel Wortsman", - "Ali Farhadi", - "Mohammad Rastegari" - ], - "year": "2019", - "venue": "NeurIPS 2019", - "links": { - "pdf": "https://arxiv.org/abs/1906.00586", - "project page": "https://prior.allenai.org/projects/discovering-neural-wirings", - "code": "https://github.com/allenai/dnw" - } - }, - { - "title": "Defending Against Neural Fake news", - "authors": [ - "Rowan Zellers", - "Ari Holtzman", - "Hannah Rashkin", - "Yonatan Bisk", - "Ali Farhadi", - "Franziska Roesner", - "Yejin Choi" - ], - "year": "2019", - "venue": "NeurIPS 2019", - "links": { - "pdf": "https://arxiv.org/abs/1905.12616", - "project page": "https://rowanzellers.com/grover/", - "code": "http://github.com/rowanz/grover" - } - }, - { - "title": "Conditional Driving from Natural Language Instructions", - "authors": [ - "Junha Roh", - "Chris Paxton", - "Andrezej Pronobis", - "Ali Farhadi", - "Dieter Fox" - ], - "year": "2019", - "venue": "CoRL 2019", - "links": { - "pdf": "https://arxiv.org/abs/1910.07615", - "project page": "https://sites.google.com/view/language-grounded-driving", - "code": "https://github.com/rohjunha/language-grounded-driving" - } - }, - { - "title": "Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index", - "authors": [ - "Minjoon Seo", - "J Lee", - "Tom Kwiatkowski", - "AP Parikh", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2019", - "venue": "ACL 2019", - "links": { - "pdf": "https://arxiv.org/abs/1906.05807", - "code": "https://github.com/uwnlp/denspi" - } - }, - { - "title": "HellaSwag: Can a Machine Really Finish Your Sentence?", - "authors": [ - "Rowan Zellers", - "A Holtzman", - "Yonatan Bisk", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2019", - "venue": "ACL 2019", - "links": { - "pdf": "https://arxiv.org/abs/1905.07830", - "project page": "https://rowanzellers.com/hellaswag/", - "code": "https://github.com/rowanz/hellaswag" - } - }, - { - "title": "Learning to Learn How to Learn:Self-Adaptive Visual Navigation Using Meta-Learning", - "authors": [ - "Mitchell Wortsman", - "Kiana Ehsani", - "Mohammad Rastegari", - "Ali Farhadi", - "Roozbeh Mottaghi" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1812.00971", - "code": "https://github.com/allenai/savn" - } - }, - { - "title": "From Recognition to Cognition: Visual Commonsense Reasoning", - "authors": [ - "Rowan Zellers", - "Yonatan Bisk", - "Ali Farhadi", - "Yejin Choi" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1811.10830", - "project page": "https://visualcommonsense.com/", - "code": "https://github.com/rowanz/r2c/" - } - }, - { - "title": "OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge", - "authors": [ - "Kenneth Marino", - "Mohammad Rastegari", - "Ali Farhadi", - "Roozbeh Mottaghi" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1906.00067" - } - }, - { - "title": "Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph", - "authors": [ - "Yao-Hung Hubert Tsai", - "Santosh Divvala", - "Louis-Philippe Morency", - "Ruslan Salakhutdinov", - "Ali Farhadi" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1903.10547" - } - }, - { - "title": "ELASTIC: Improving CNNs with Instance Specific Scaling Policies", - "authors": [ - "Huiyu Wang", - "Aniruddha Kembhavi", - "Ali Farhadi", - "Alan Yuille", - "Mohammad Rastegari" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1812.05262" - } - }, - { - "title": "Two Body Problem: Collaborative Visual Task Completion", - "authors": [ - "Unnat Jain", - "Luca Weihs", - "Eric Kolve", - "Mohammad Rastegari", - "Svetlana Lazebnik", - "Ali Farhadi", - "Alexander Schwing", - "Aniruddha Kembhavi" - ], - "year": "2019", - "venue": "CVPR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1904.05879" - } - }, - { - "title": "SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation", - "authors": [ - "Daniel Gordon", - "Abhishek Kadian", - "Devi Parikh", - "Judy Hoffman", - "Dhruv Batra" - ], - "year": "2019", - "venue": "ICCV 2019", - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/splitnet.pdf", - "code": "https://github.com/facebookresearch/splitnet" - } - }, - { - "title": "Shifting the Baseline: Single Modality Performance on Visual Navigation & QA", - "authors": [ - "Jesse Thomason", - "Daniel Gordon", - "Yonatan Bisk" - ], - "year": "2019", - "venue": "NAACL 2019 Short Papers", - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/shifting_baseline.pdf" - } - }, - { - "title": "Visual Semantic Navigation using Scene Priors", - "authors": [ - "Wei Yang", - "Xiaolong Wang", - "Ali Farhadi", - "Abhinav Gupta", - "Roozbeh Mottaghi" - ], - "year": "2019", - "venue": "ICLR 2019", - "links": { - "pdf": "https://arxiv.org/abs/1810.06543" - } - }, - { - "title": "What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning", - "authors": [ - "Daniel Gordon", - "Dieter Fox", - "Ali Farhadi" - ], - "year": "2018", - "venue": null, - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/hiprl.pdf", - "project page": "https://danielgordon10.github.io/papers/hiprl.html" - } - }, - { - "title": "Label refinery: Improving imagenet classification through label progression", - "authors": [ - "Hessam Bagherinezhad", - "Maxwell Horton", - "Mohammad Rastegari", - "Ali Farhadi" - ], - "year": "2018", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/1805.02641", - "code": "https://github.com/hessamb/label-refinery" - } - }, - { - "title": "YOLOv3: An Incremental Improvement", - "authors": [ - "Joseph Redmon", - "Ali Farhadi" - ], - "year": "2018", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/1804.02767", - "project page": "https://pjreddie.com/darknet/yolo/" - } - }, - { - "title": "Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension", - "authors": [ - "Minjoon Seo", - "Tom Kwiatkowski", - "Ankur P. Parikh", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2018", - "venue": "EMNLP 2018", - "links": { - "pdf": "https://arxiv.org/abs/1804.07726", - "code": "https://github.com/uwnlp/piqa" - } - }, - { - "title": "PhotoShape: Photorealistic Materials for Large-Scale Shape Collections", - "authors": [ - "Keunhong Park", - "Konstantinos Rematas", - "Ali Farhadi", - "Steve Seitz" - ], - "year": "2018", - "venue": "SIGGRAPH Asia 2018", - "links": { - "pdf": "https://arxiv.org/abs/1809.09761", - "project page": "https://keunhong.com/publications/photoshape/", - "code": "https://github.com/keunhong/photoshape" - } - }, - { - "title": "Imagine This! Scripts to Compositions to Videos", - "authors": [ - "Tanmay Gupta", - "Dustin Schwenk", - "Ali Farhadi", - "Derek Hoiem", - "Aniruddha Kembhavi" - ], - "year": "2018", - "venue": "ECCV 2018", - "links": { - "pdf": "https://arxiv.org/abs/1804.03608" - } - }, - { - "title": "Transferring Common-Sense Knowledge for Object Detection", - "authors": [ - "Krishna Kumar Singh", - "Santosh Kumar Divvala", - "Ali Farhadi", - "Yong Jae Lee" - ], - "year": "2018", - "venue": "ECCV 2019", - "links": { - "pdf": "http://openaccess.thecvf.com/content_ECCV_2018/papers/Krishna_Kumar_Singh_Transferring_Common-Sense_Knowledge_ECCV_2018_paper.pdf" - } - }, - { - "title": "Who Let The Dogs Out? Modeling Dog Behavior From Visual Data", - "authors": [ - "Kiana Ehsani", - "Hessam Bagherinezhad", - "Joseph Redmon", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2018", - "venue": "CVPR 2018", - "links": { - "pdf": "https://arxiv.org/abs/1803.10827", - "code": "https://github.com/ehsanik/dogTorch" - } - }, - { - "title": "Segan: Segmenting and generating the invisible", - "authors": [ - "Kiana Ehsani", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2018", - "venue": "CVPR 2018", - "links": { - "pdf": "https://arxiv.org/abs/1703.10239", - "code": "https://github.com/ehsanik/SeGAN" - } - }, - { - "title": "Actor and Observer: Joint Modeling of First and Third-Person Videos", - "authors": [ - "Gunnar Sigurdsson", - "Abhinav Gupta", - "Cordelia Schmid", - "Ali Farhadi", - "Karteek Alahari" - ], - "year": "2018", - "venue": "CVPR 2018", - "links": { - "pdf": "https://arxiv.org/abs/1804.09627" - } - }, - { - "title": "Structured Set Matching Networks for One-Shot Part Labeling", - "authors": [ - "Jonghyun Choi", - "Jayant Krishnamurthy", - "Aniruddha Kembhavi", - "Ali Farhadi" - ], - "year": "2018", - "venue": "CVPR 2018", - "links": { - "pdf": "https://arxiv.org/abs/1712.01867" - } - }, - { - "title": "IQA: Visual Question Answering in Interactive Environments", - "authors": [ - "Daniel Gordon", - "Aniruddha Kembhavi", - "Mohammad Rastegari", - "Joseph Redmon", - "Dieter Fox", - "Ali Farhadi" - ], - "year": "2018", - "venue": "CVPR 2018", - "award": "NVIDIA Pioneering Research Award", - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/iqa.pdf", - "project page": "https://danielgordon10.github.io/papers/iqa.html", - "code": "https://github.com/danielgordon10/thor-iqa-cvpr-2018" - } - }, - { - "title": "Neural Speed Reading via Skim-RNN", - "authors": [ - "Minjoon Seo", - "Sewon Min", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2018", - "venue": "ICLR 2018", - "links": { - "pdf": "https://arxiv.org/abs/1711.02085" - } - }, - { - "title": "Re3: Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects", - "authors": [ - "Daniel Gordon", - "Ali Farhadi", - "Dieter Fox" - ], - "year": "2018", - "venue": "RAL 2018", - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/re3.pdf", - "project page": "https://danielgordon10.github.io/papers/re3.html", - "code": "https://gitlab.com/danielgordon10/re3-tensorflow" - } - }, - { - "title": "AJILE Movement Prediction: Multimodal Deep Learning for Natural Human Neural Recordings and Video", - "authors": [ - "Nancy Xin Ru Wang", - "Ali Farhadi", - "Rajesh Rao", - "Bingni Brunton" - ], - "year": "2018", - "venue": "AAAI 2018", - "links": { - "pdf": "https://arxiv.org/abs/1709.05939" - } - }, - { - "title": "AI2-THOR: An Interactive 3D Environment for Visual AI", - "thumbnail": "/ai2thor.jpg", - "authors": [ - "Eric Kolve", - "Roozbeh Mottaghi", - "Winson Han", - "Eli VanderBilt", - "Luca Weihs", - "Alvaro Herrasti", - "Matt Deitke", - "Kiana Ehsani", - "Daniel Gordon", - "Yuke Zhu", - "Aniruddha Kembhavi", - "Abhinav Gupta", - "Ali Farhadi" - ], - "year": "2017", - "venue": null, - "links": { - "pdf": "https://arxiv.org/abs/1712.05474", - "project page": "https://ai2thor.allenai.org/", - "code": "https://github.com/allenai/ai2thor" - } - }, - { - "title": "Visual Semantic Planning using Deep Successor Representations", - "authors": [ - "Daniel Gordon*", - "Yuke Zhu*", - "Eric Kolve", - "Dieter Fox", - "Li Fei-Fei", - "Abhinav Gupta", - "Roozbeh Mottaghi", - "Ali Farhadi" - ], - "year": "2017", - "venue": "ICCV 2017", - "links": { - "pdf": "https://danielgordon10.github.io/pdfs/vsp.pdf" - } - }, - { - "title": "See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content", - "authors": [ - "Roozbeh Mottaghi", - "Connor Schenck", - "Dieter Fox", - "Ali Farhadi" - ], - "year": "2017", - "venue": "ICCV 2017", - "links": { - "pdf": "https://arxiv.org/abs/1701.02718" - } - }, - { - "title": "YOLO9000: Better, Faster, Stronger", - "authors": [ - "Joseph Redmon", - "Ali Farhadi" - ], - "year": "2017", - "award": "Best Paper Honorable Mention", - "venue": "CVPR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1612.08242", - "project page": "https://pjreddie.com/darknet/yolo/" - } - }, - { - "title": "Are You Smarter Than A Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension", - "authors": [ - "Aniruddha Kembhavi", - "Minjoon Seo", - "Eric Klove", - "Dustin Schwenk", - "Hannaneh Hajishirzi", - "Ali Farhadi" - ], - "year": "2017", - "venue": "CVPR 2017", - "links": { - "pdf": "http://ai2-website.s3.amazonaws.com/publications/CVPR17_TQA.pdf", - "project page": "http://vuchallenge.org/tqa.html" - } - }, - { - "title": "LCNN: Lookup-based Convolutional Neural Network", - "authors": [ - "Hessam Bagherinezhad", - "Mohammad Rastegari", - "Ali Farhadi" - ], - "year": "2017", - "venue": "CVPR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1611.06473", - "code": "https://github.com/hessamb/lcnn" - } - }, - { - "title": "Commonly Uncommon: Semantic Sparsity in Situation Recognition", - "authors": [ - "Mark Yatskar", - "Vicente Ord\u00f3\u00f1ez", - "Luke Zettlemoyer", - "Ali Farhadi" - ], - "year": "2017", - "venue": "CVPR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1612.00901" - } - }, - { - "title": "Asynchronous Temporal Fields for Action Recognition", - "authors": [ - "Gunnar A Sigurdsson", - "Santosh Divvala", - "Ali Farhadi", - "Abhinav Gupta" - ], - "year": "2017", - "venue": "CVPR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1612.06371" - } - }, - { - "title": "Query-Reduction Networks for Question Answering", - "authors": [ - "Minjoon Seo", - "Sewon Min", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2017", - "venue": "ICLR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1606.04582", - "code": "https://github.com/uwnlp/qrn" - } - }, - { - "title": "Bidirectional Attention Flow for Machine Comprehension", - "authors": [ - "Minjoon Seo", - "Aniruddha Kembhavi", - "Ali Farhadi", - "Hannaneh Hajishirzi" - ], - "year": "2017", - "venue": "ICLR 2017", - "links": { - "pdf": "https://arxiv.org/abs/1611.01603", - "project page": "https://allenai.github.io/bi-att-flow/", - "code": "https://github.com/allenai/bi-att-flow" - } - }, - { - "title": "Target-driven visual navigation in indoor scenes using deep reinforcement learning", - "authors": [ - "Yuke Zhu", - "Roozbeh Mottaghi", - "Eric Kolve", - "Joseph Lim", - "Abhinav Gupta", - "Fei-Fei Li", - "Ali Farhadi" - ], - "year": "2017", - "venue": "ICRA 2017", - "links": { - "pdf": "https://arxiv.org/abs/1609.05143" - } - }, - { - "title": "Summarizing unconstrained videos using salient montages", - "authors": [ - "Min Sun", - "Ali Farhadi", - "Ben Taskar", - "Steve Seitz" - ], - "year": "2017", - "venue": "TPAMI 2017", - "links": { - "pdf": "https://ieeexplore.ieee.org/document/7779036" - } - }, - { - "title": "Semantic Highlight Retrieval and Term Prediction", - "authors": [ - "Min Sun", - "Kuo-Hao Zeng", - "Yen-Chen Lin", - "Ali Farhadi" - ], - "year": "2017", - "venue": "TIP 2017", - "links": { - "pdf": "https://ieeexplore.ieee.org/document/7852483" - } - }, - { - "title": "XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks", - "authors": [ - "Mohammad Rastegari", - "Vicente Ordonez", - "Joseph Redmon", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "http://arxiv.org/abs/1603.05279", - "code": "https://github.com/allenai/XNOR-Net" - } - }, - { - "title": "Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks", - "authors": [ - "Junyuan Xie", - "Ross B. Girshick", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "https://arxiv.org/abs/1604.03650", - "code": "https://github.com/piiswrong/deep3d" - } - }, - { - "title": "A Diagram Is Worth A Dozen Images", - "authors": [ - "Ani Kembhavi", - "Mike Salvato", - "Eric Kolve", - "Minjoon Seo", - "Hannaneh Hajishirzi", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "https://arxiv.org/abs/1603.07396", - "code": "https://github.com/allenai/dqa-net" - } - }, - { - "title": "\"What happens if...\" Learning to predict the effect of forces in images", - "authors": [ - "Roozbeh Mottaghi", - "Mohammad Rastegari", - "Abhinav Gupta", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "https://arxiv.org/abs/1603.05600" - } - }, - { - "title": "Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding", - "authors": [ - "Gunnar Sigurdsson", - "Gul Varol", - "Xiaolong Wang", - "Ali Farhadi", - "Ivan Laptev", - "Abhinav Gupta" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "https://arxiv.org/abs/1604.01753", - "project page": "http://allenai.org/plato/charades/" - } - }, - { - "title": "FigureSeer:Parsing Result-Figures in Research Papers", - "authors": [ - "Noah Siegel", - "Santosh Divvala", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ECCV 2016", - "links": { - "pdf": "http://ai2-website.s3.amazonaws.com/publications/Siegel16eccv.pdf", - "project page": "https://prior.allenai.org/projects/figureseer" - } - }, - { - "title": "You Only Look Once: Unified, Real-Time Object Detection", - "authors": [ - "Joseph Redmon", - "Santosh Divvala", - "Ross Girshick", - "Ali Farhadi" - ], - "year": "2016", - "award": "OpenCV People's Choice Award", - "venue": "CVPR 2016", - "links": { - "pdf": "http://arxiv.org/abs/1506.02640", - "project page": "https://pjreddie.com/darknet/yolo/" - } - }, - { - "title": "Situation Recognition: Visual Semantic Role Labeling for Image Understanding", - "authors": [ - "Mark Yatskar", - "Luke Zettlemoyer", - "Ali Farhadi" - ], - "year": "2016", - "venue": "CVPR 2016", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/SituationRecognition.pdf", - "code": "https://github.com/my89/SituationCrf" - } - }, - { - "title": "Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images", - "authors": [ - "Roozbeh Mottaghi", - "Hessam Bagherinezhad", - "Mohammad Rastegari", - "Ali Farhadi" - ], - "year": "2016", - "venue": "CVPR 2016", - "links": { - "pdf": "https://arxiv.org/abs/1511.04048", - "project page": "http://allenai.org/plato/newtonian-understanding/" - } - }, - { - "title": "Actions~Transformation", - "authors": [ - "Xiaolong Wang", - "Ali Farhadi", - "Abhinav Gupta" - ], - "year": "2016", - "venue": "CVPR 2016", - "links": { - "pdf": "https://arxiv.org/abs/1512.00795" - } - }, - { - "title": "A Task-Oriented Approach for Cost-sensitive Recognition", - "authors": [ - "Roozbeh Mottaghi", - "Hannaneh Hajishirzi", - "Ali Farhadi" - ], - "year": "2016", - "venue": "CVPR 2016", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Tasks.pdf" - } - }, - { - "title": "Unsupervised Deep Embedding for Clustering Analysis", - "authors": [ - "Junyuan Xie", - "Ross B. Girshick", - "Ali Farhadi" - ], - "year": "2016", - "venue": "ICML 2016", - "links": { - "pdf": "http://proceedings.mlr.press/v48/xieb16.html", - "code": "https://github.com/piiswrong/dec" - } - }, - { - "title": "Stating the Obvious: Extracting Visual Common Sense Knowledge", - "authors": [ - "Mark Yatskar", - "Vicente Ord\u00f3\u00f1ez", - "Ali Farhadi" - ], - "year": "2016", - "venue": "NAACL 2016", - "links": { - "pdf": "https://www.aclweb.org/anthology/N16-1023" - } - }, - { - "title": "Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects", - "authors": [ - "Hessam Bagherinezhad", - "Hannaneh Hajishirzi", - "Yejin Choi", - "Ali Farhadi" - ], - "year": "2016", - "venue": "AAAI 2016", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Abnormality.pdf" - } - }, - { - "title": "Toward a Taxonomy and Computational Models of Abnormalities in Images", - "authors": [ - "Babak Saleh", - "Ahmed Elgammal", - "Jacob Feldman", - "Ali Farhadi" - ], - "year": "2016", - "venue": "AAAI 2016", - "award": "Best Student Paper Award", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Tasks.pdf" - } - }, - { - "title": "Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing", - "authors": [ - "Hamid Izadinia", - "Fereshteh Sadeghi", - "Santosh K Divvala", - "Hannaneh Hajishirzi", - "Yejin Choi", - "Ali Farhadi" - ], - "year": "2015", - "venue": "ICCV 2015", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/spt.pdf" - } - }, - { - "title": "Generating Notifications for Missing Actions: Don\u2019t forget to turn the lights off!", - "authors": [ - "Bilge Soran", - "Ali Farhadi", - "Linda Shapiro" - ], - "year": "2015", - "venue": "ICCV 2015", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/alarm-iccv.pdf" - } - }, - { - "title": "VISALOGY: Answering Visual Analogy Questions", - "authors": [ - "Fereshteh Sadeghi", - "Larry Zittnick", - "Ali Farhadi" - ], - "year": "2015", - "venue": "NeurIPS 2015", - "links": { - "pdf": "https://papers.nips.cc/paper/5777-visalogy-answering-visual-analogy-questions" - } - }, - { - "title": "Real-Time Grasp Detection Using Convolutional Neural Networks", - "authors": [ - "Joseph Redmon", - "Anelia Angelova" - ], - "year": "2015", - "venue": "ICRA 2015", - "links": { - "pdf": "http://arxiv.org/abs/1506.02640" - } - }, - { - "title": "Solving Geometry Problems: Combining Text and Diagram Interpretation", - "authors": [ - "Minjoon Seo", - "Hannaneh Hajishirzi", - "Ali Farhadi", - "Oren Etzioni", - "Clint Malcolm" - ], - "year": "2015", - "venue": "EMNLP 2015", - "links": { - "pdf": "https://www.aclweb.org/anthology/D15-1171", - "project page": "https://geometry.allenai.org/" - } - }, - { - "title": "VisKE: Visual Knowledge Extraction and Question Answering by Visual Verification of Relation Phrases", - "authors": [ - "Fereshteh Sadeghi", - "Santosh K Divvala", - "Ali Farhadi" - ], - "year": "2015", - "venue": "CVPR 2015", - "links": { - "pdf": "http://viske.allenai.org/paper/fsadeghi_VisKE.pdf", - "project page": "http://viske.allenai.org/" - } - }, - { - "title": "Discriminative and Consistent Similarities in Instance-Level Multiple Instance Learning", - "authors": [ - "Mohammad Rastegari", - "Hannaneh Hajishirzi", - "Ali Farhadi" - ], - "year": "2015", - "venue": "CVPR 2015", - "links": { - "pdf": "http://ssli.ee.washington.edu/~hannaneh/papers/MIL.pdf" - } - }, - { - "title": "Learning to Select and Order Vacation Photographs", - "authors": [ - "Fereshteh Sadeghi", - "J Rafael Tena", - "Ali Farhadi", - "Leonid Sigal" - ], - "year": "2015", - "venue": "WACV 2015", - "links": { - "pdf": "http://homes.cs.washington.edu/~fsadeghi/papers/fsadeghi_album_wacv15.pdf" - } - }, - { - "title": "Learning Everything about Anything: Webly-Supervised Visual Concept Learning", - "authors": [ - "Santosh K Divvala", - "Ali Farhadi", - "Carlos Guestrin" - ], - "year": "2014", - "venue": "CVPR 2014", - "links": { - "pdf": "http://levan.cs.washington.edu/ngrams/objectNgrams_cvpr14.pdf", - "project page": "http://levan.cs.uw.edu/" - } - }, - { - "title": "Incorporating Scene Context and Object Layout into Appearance Modeling", - "authors": [ - "Hamid Izadinia", - "Fereshteh Sadeghi", - "Ali Farhadi" - ], - "year": "2014", - "venue": "CVPR 2014", - "links": { - "pdf": "http://grail.cs.washington.edu/pub/papers/izadinia2014isc.pdf" - } - }, - { - "title": "Failure Prediction in Vision Systems", - "authors": [ - "Peng Zhang", - "Jiuling Wang", - "Ali Farhadi", - "Martial Hebert", - "Devi Parikh" - ], - "year": "2014", - "venue": "CVPR 2014", - "links": { - "pdf": "http://www.ri.cmu.edu/pub_files/2014/3/predicting_failures_of_vision_systems_CVPR2014.pdf" - } - }, - { - "title": "Towards Transparent Systems: Semantic Characterization of Failure Modes", - "authors": [ - "Aayush Bansal", - "Ali Farhadi", - "Devi Parikh" - ], - "year": "2014", - "venue": "ECCV 2014", - "links": { - "pdf": "http://www.cs.cmu.edu/~aayushb/pubs/characterizing_mistakes_eccv2014.pdf" - } - }, - { - "title": "Salient montages from unconstrained videos", - "authors": [ - "Min Sun", - "Ali Farhadi", - "Ben Taskar", - "Steve Seitz" - ], - "year": "2014", - "venue": "ECCV 2014", - "links": { - "pdf": "http://grail.cs.washington.edu/pub/papers/sun2014smf.pdf" - } - }, - { - "title": "Ranking Domain-Specific Highlights by Analyzing Edited Videos", - "authors": [ - "Min Sun", - "Ali Farhadi", - "Steve Seitz" - ], - "year": "2014", - "venue": "ECCV 2014", - "links": { - "pdf": "http://grail.cs.washington.edu/pub/papers/sun2014rdh.pdf" - } - }, - { - "title": "Diagram Understanding in Geometry Questions", - "authors": [ - "Minjoon Seo", - "Hannaneh Hajishirzi", - "Ali Farhadi", - "Oren Etzioni" - ], - "year": "2014", - "venue": "AAAI 2014", - "links": { - "pdf": "http://homes.cs.washington.edu/~minjoon/papers/geosolver/diagram_understanding.pdf", - "project page": "https://geometry.allenai.org/" - } - }, - { - "title": "Multi Resolution Language Grounding with Weak Supervision", - "authors": [ - "Rik Koncel Kedziorski", - "Hannaneh Hajishirzi", - "and Ali Farhadi" - ], - "year": "2014", - "venue": "EMNLP 2014", - "links": { - "pdf": "http://ssli.ee.washington.edu/~hannaneh/segmentation-emnlp14.pdf" - } - }, - { - "title": "Action Recognition in the Presence of One Egocentric and Multiple Static Cameras", - "authors": [ - "Bilge Soran", - "Ali Farhadi", - "Linda Shapiro" - ], - "year": "2014", - "venue": "ACCV 2014", - "links": { - "pdf": "http://homes.cs.washington.edu/~shapiro/accv2014finalpaper.pdf" - } - }, - { - "title": "Multi-Attribute Queries: To Merge or Not to Merge?", - "authors": [ - "Mohammad Rastegari", - "Ali Diba", - "Devi Parikh", - "Ali Farhadi" - ], - "year": "2013", - "venue": "CVPR 2013", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/MultiAtr_CVPR13.pdf" - } - }, - { - "title": "Object-Centric Anomaly Detection by Attribute-Based Reasoning", - "authors": [ - "Babak Saleh", - "Ali Farhadi", - "Ahmed Elgammal" - ], - "year": "2013", - "venue": "CVPR 2013", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Abnormality_CVPR13.pdf" - } - }, - { - "title": "Adding Unlabeled Samples to Categories by Learned Attributes", - "authors": [ - "Jonghyun Choi", - "Mohammad Rastegari", - "Ali Farhadi", - "Larry Davis" - ], - "year": "2013", - "venue": "CVPR 2013", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Adding_CVPR13.pdf" - } - }, - { - "title": "Attribute Discovery via Predictable Discriminative Binary Codes", - "authors": [ - "Mohammad Rastegari", - "Ali Farhadi", - "David Forsyth" - ], - "year": "2012", - "venue": "ECCV 2012", - "links": { - "pdf": "http://www.cs.umd.edu/~mrastega/Site/Publications_files/dbc.pdf" - } - }, - { - "title": "Semantic Understanding of Proefessional Soccer Commentaries", - "authors": [ - "Hannaneh Hajishirzi", - "Mohammad Rastegari", - "Ali Farhadi", - "Jessica Hodgins" - ], - "year": "2012", - "venue": "UAI 2012", - "links": { - "pdf": "http://homes.cs.washington.edu/~hannaneh/soccer-UAI.pdf" - } - }, - { - "title": "Building a Dictionary of Image Fragments", - "authors": [ - "Zicheng Liao", - "Ali Farhadi", - "Yang Wang", - "Ian Endres", - "David Forsyth" - ], - "year": "2012", - "venue": "CVPR 2012", - "links": { - "pdf": "http://web.engr.illinois.edu/~liao17/data/fragdict-cvpr12.pdf" - } - }, - { - "title": "Understanding Egocentric Activities", - "authors": [ - "Alireza Fathi", - "Ali Farhadi", - "James Rehg" - ], - "year": "2011", - "venue": "ICCV 2011", - "links": { - "pdf": "http://www.cc.gatech.edu/~afathi3/publication/ICCV11.pdf" - } - }, - { - "title": "Recognition Using Visual Phrases", - "authors": [ - "Ali Farhadi", - "Amin Sadeghi" - ], - "year": "2011", - "venue": "CVPR 2011", - "award": "Best Student Paper Award", - "links": { - "pdf": "http://vision.cs.uiuc.edu/phrasal/recognition_using_visual_phrases.pdf" - } - }, - { - "title": "Using Classification to Protect the Integrity of Spectrum Measurements in White Space Networks", - "authors": [ - "Omid Fatemieh", - "Ali Farhadi", - "Ranveer Chandra", - "Carl Gunter" - ], - "year": "2011", - "venue": "NDSS 2011", - "links": { - "pdf": "http://seclab.uiuc.edu/pubs/FatemiehFCG11.pdf" - } - }, - { - "title": "Every Picture Tells a Story: Generating Sentences for Images", - "authors": [ - "Ali Farhadi", - "Mohsen Hejrati", - "Amin Sadeghi", - "Peter Young", - "Cyrus Rashtchian", - "Julia Hockenmaier", - "David Forsyth" - ], - "year": "2010", - "venue": "ECCV 2010", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/sentence.pdf" - } - }, - { - "title": "Attribute-Centric Recognition for Cross-Category Generalization", - "authors": [ - "Ali Farhadi", - "Ian Endres", - "Derek Hoiem" - ], - "year": "2010", - "venue": "CVPR 2010", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/attributes_2010.pdf" - } - }, - { - "title": "A Latent Model of Discriminative Aspect", - "authors": [ - "Ali Farhadi", - "Mostafa Kamali", - "Ian Endres", - "David Forsyth" - ], - "year": "2009", - "venue": "ICCV 2009", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/ICCV09_Aspect.pdf" - } - }, - { - "title": "Unlabeled Data Improves Word Prediction", - "authors": [ - "Nicolas Loeff", - "Ali Farhadi", - "Ian Endres", - "David Forsyth" - ], - "year": "2009", - "venue": "ICCV 2009", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/ICCV09_manifold.pdf" - } - }, - { - "title": "Describing Objects by their Attributes", - "authors": [ - "Ali Farhadi", - "Ian Endres", - "Derek Hoiem", - "David Forsyth" - ], - "year": "2009", - "venue": "CVPR 2009", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Attributes.pdf" - } - }, - { - "title": "Learning to Recognize Activities from a Wrong Viewpoint", - "authors": [ - "Ali Farhadi", - "Mostafa Kamali" - ], - "year": "2008", - "venue": "ECCV 2008", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Activity_transfer.pdf" - } - }, - { - "title": "Scene Discovery by Matrix Factorization", - "authors": [ - "Nicolas Loeff", - "Ali Farhadi" - ], - "year": "2008", - "venue": "ECCV 2008", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/scene_discovery.pdf" - } - }, - { - "title": "Transfer Learning in Sign Language", - "authors": [ - "Ali Farhadi", - "David Forsyth", - "Ryan White" - ], - "year": "2007", - "venue": "CVPR 2007", - "links": { - "pdf": "https://homes.cs.washington.edu/~ali/papers/Transfer_Learning_ASL.pdf" - } - }, { "title": "Aligning ASL for Statistical Translation Using a Discriminative Word Model", "authors": [