Jacob Andreas

251 papers A* 49B 12Misc 1Journal 139Unranked 48
YearRankTypeTitle / Venue / Authors
2026 J jnl
Do LLMs Benefit From Their Own Words?
CoRR
Jenny Y. Huang, Leshem Choshen, Ramón Fernandez Astudillo, Tamara Broderick, Jacob Andreas
2026 J jnl
Pitfalls in Evaluating Interpretability Agents.
CoRR
Tal Haklay, Nikhil Prakash, Sana Pandey, Antonio Torralba, Aaron Mueller, Jacob Andreas, Tamar Rott Shaham, Yonatan Belinkov
2026 J jnl
Policy Learning with a Language Bottleneck.
Trans. Mach. Learn. Res.
Megha Srivastava, Cédric Colas, Dorsa Sadigh, Jacob Andreas
2026 J jnl
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models.
CoRR
Isha Puri, Mehul Damani, Idan Shenfeld, Marzyeh Ghassemi, Jacob Andreas, Yoon Kim
2026 J jnl
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.
Trans. Mach. Learn. Res.
Bairu Hou, Yang Zhang, Jiabao Ji, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang
2025 A* conf
(How) Do Language Models Track State?
ICML
Belinda Z. Li, Zifan Carl Guo, Jacob Andreas
2025 J jnl
(How) Do Language Models Track State?
CoRR
Belinda Z. Li, Zifan Carl Guo, Jacob Andreas
2025 A* conf
A Hitchhiker's Guide to Scaling Law Estimation.
ICML
Leshem Choshen, Yang Zhang, Jacob Andreas
2025 — conf
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation.
NAACL (Long Papers)
Bairu Hou, Yang Zhang, Jacob Andreas, Shiyu Chang
2025 J jnl
ARC Is a Vision Problem!
CoRR
Keya Hu, Ali Cy, Linlu Qiu, Xiaoman Delores Ding, Runqian Wang, Yeyin Eva Zhu, Jacob Andreas, Kaiming He
2025 J jnl
Assessing Adaptive World Models in Machines with Novel Games.
CoRR
Lance Ying, Katherine M. Collins, Prafull Sharma, Cédric Colas, Kaiya Ivy Zhao, Adrian Weller, Zenna Tavares, Phillip Isola, Samuel J. Gershman, Jacob Andreas, Thomas L. Griffiths, François Chollet, Kelsey R. Allen, Joshua B. Tenenbaum
2025 J jnl
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent.
CoRR
Christy Li, Josep López Camuñas, Jake Thomas Touchet, Jacob Andreas, Àgata Lapedriza, Antonio Torralba, Tamar Rott Shaham
2025 J jnl
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty.
CoRR
Mehul Damani, Isha Puri, Stewart Slocum, Idan Shenfeld, Leshem Choshen, Yoon Kim, Jacob Andreas
2025 J jnl
Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents.
CoRR
Kaivalya Hariharan, Uzay Girit, Atticus Wang, Jacob Andreas
2025 J jnl
CONCUR: A Framework for Continual Constrained and Unconstrained Routing.
CoRR
Peter Baile Chen, Weiyue Li, Dan Roth, Michael J. Cafarella, Samuel Madden, Jacob Andreas
2025 J jnl
Can Gradient Descent Simulate Prompting?
CoRR
Eric Zhang, Leshem Choshen, Jacob Andreas
2025 J jnl
Code-enabled language models can outperform reasoning models on diverse tasks.
CoRR
Cedegao E. Zhang, Cédric Colas, Gabriel Poesia, Joshua B. Tenenbaum, Jacob Andreas
2025 J jnl
Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models.
Trans. Assoc. Comput. Linguistics
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin, Unnathi U. Kumar, Setayesh Radkani, Thomas Hikaru Clark, Carina Kauf, Jennifer Hu, R. T. Pramod, Gabriel Grand, Vivian C. Paulun, Maria Ryskina, Ekin Akyürek, Ethan Gotlieb Wilcox, Nafisa Rashid, Leshem Choshen, Roger Levy, Evelina Fedorenko, Joshua B. Tenenbaum, Jacob Andreas
2025 A* conf
Eliciting Human Preferences with Language Models.
ICLR
Belinda Z. Li, Alex Tamkin, Noah D. Goodman, Jacob Andreas
2025 — conf
LLM Agents for Coordinating Multi-User Information Gathering.
ACL (Findings)
Harsh Jhamtani, Jacob Andreas, Benjamin Van Durme
2025 J jnl
LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users.
CoRR
Almog Hilel, Idan Shenfeld, Jacob Andreas, Leshem Choshen
2025 J jnl
LM Agents for Coordinating Multi-User Information Gathering.
CoRR
Harsh Jhamtani, Jacob Andreas, Benjamin Van Durme
2025 — conf
Language Modeling with Editable External Knowledge.
NAACL (Findings)
Belinda Z. Li, Emmy Liu, Alexis Ross, Abbas Zeitoun, Graham Neubig, Jacob Andreas
2025 B conf
Language and Experience: A Computational Model of Social Learning in Complex Novel Tasks.
CogSci
Cédric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah D. Goodman, Jacob Andreas, Joshua B. Tenenbaum
2025 J jnl
Language and Experience: A Computational Model of Social Learning in Complex Tasks.
CoRR
Cédric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah D. Goodman, Jacob Andreas, Joshua B. Tenenbaum
2025 A* conf
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation.
ICLR
Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas
2025 J jnl
Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors.
CoRR
Alexis Ross, Jacob Andreas
2025 J jnl
Line of Sight: On Linear Representations in VLLMs.
CoRR
Achyuta Rajaram, Sarah Schwettmann, Jacob Andreas, Arthur Conmy
2025 J jnl
Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation.
CoRR
Peter Baile Chen, Yi Zhang, Dan Roth, Samuel Madden, Jacob Andreas, Michael J. Cafarella
2025 B conf
Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models.
CogSci
Lionel Wong, Katherine M. Collins, Lance Ying, Cedegao E. Zhang, Adrian Weller, Tobias Gerstenberg, Timothy O'Donnell, Alexander K. Lew, Jacob Andreas, Tyler Brooke-Wilson, Joshua B. Tenenbaum
2025 J jnl
Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models.
CoRR
Lionel Wong, Katherine M. Collins, Lance Ying, Cedegao E. Zhang, Adrian Weller, Tobias Gerstenberg, Timothy O'Donnell, Alexander K. Lew, Jacob Andreas, Joshua B. Tenenbaum, Tyler Brooke-Wilson
2025 J jnl
Modeling Student Learning with 3.8 Million Program Traces.
CoRR
Alexis Ross, Megha Srivastava, Jeremiah J. Blanchard, Jacob Andreas
2025 J jnl
OpenEstimate: Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data.
CoRR
Alana Renda, Jillian Ross, Michael J. Cafarella, Jacob Andreas
2025 J jnl
Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting.
CoRR
Michael Y. Hu, Benjamin Van Durme, Jacob Andreas, Harsh Jhamtani
2025 J jnl
Self-Steering Language Models.
CoRR
Gabriel Grand, Joshua B. Tenenbaum, Vikash K. Mansinghka, Alexander K. Lew, Jacob Andreas
2025 J jnl
Sequential-Parallel Duality in Prefix Scannable Models.
CoRR
Morris Yau, Sharut Gupta, Valerie Engelmayer, Kazuki Irie, Stefanie Jegelka, Jacob Andreas
2025 J jnl
Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People.
CoRR
Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum
2025 A* conf
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning.
ICML
Ekin Akyürek, Mehul Damani, Adam Zweiger, Linlu Qiu, Han Guo, Jyothish Pari, Yoon Kim, Jacob Andreas
2025 J jnl
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.
CoRR
Bairu Hou, Yang Zhang, Jiabao Ji, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang
2025 J jnl
Training Language Models to Explain Their Own Computations.
CoRR
Belinda Z. Li, Zifan Carl Guo, Vincent Huang, Jacob Steinhardt, Jacob Andreas
2024 J jnl
A Hitchhiker's Guide to Scaling Law Estimation.
CoRR
Leshem Choshen, Yang Zhang, Jacob Andreas
2024 A* conf
A Multimodal Automated Interpretability Agent.
ICML
Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba
2024 J jnl
A Multimodal Automated Interpretability Agent.
CoRR
Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba
2024 J jnl
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation.
CoRR
Bairu Hou, Yang Zhang, Jacob Andreas, Shiyu Chang
2024 Misc conf
Adaptive Language-Guided Abstraction from Contrastive Explanations.
CoRL
Andi Peng, Belinda Z. Li, Ilia Sucholutsky, Nishanth Kumar, Julie Shah, Jacob Andreas, Andreea Bobu
2024 J jnl
Adaptive Language-Guided Abstraction from Contrastive Explanations.
CoRR
Andi Peng, Belinda Z. Li, Ilia Sucholutsky, Nishanth Kumar, Julie A. Shah, Jacob Andreas, Andreea Bobu
2024 A* conf
Algorithmic Capabilities of Random Transformers.
NeurIPS
Ziqian Zhong, Jacob Andreas
2024 J jnl
Algorithmic Capabilities of Random Transformers.
CoRR
Ziqian Zhong, Jacob Andreas
2024 J jnl
An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models.
CoRR
Emmy Liu, Graham Neubig, Jacob Andreas
2024 J jnl
Automatic Discovery of Visual Circuits.
CoRR
Achyuta Rajaram, Neil Chowdhury, Antonio Torralba, Jacob Andreas, Sarah Schwettmann
2024 J jnl
Bayesian Preference Elicitation with Language Models.
CoRR
Kunal Handa, Yarin Gal, Ellie Pavlick, Noah D. Goodman, Jacob Andreas, Alex Tamkin, Belinda Z. Li
2024 J jnl
Decision-Oriented Dialogue for Human-AI Collaboration.
Trans. Assoc. Comput. Linguistics
Jessy Lin, Nicholas Tomlin, Jacob Andreas, Jason Eisner
2024 A* conf
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling.
ICML
Bairu Hou, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang, Yang Zhang
2024 — conf
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability.
ACL (Findings)
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen, Derry Wijaya, Jacob Andreas
2024 J jnl
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability.
CoRR
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen, Derry Wijaya, Jacob Andreas
2024 J jnl
Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models.
CoRR
Anna A. Ivanova, Aalok Sathe, Benjamin Lipkin, Unnathi U. Kumar, Setayesh Radkani, Thomas Hikaru Clark, Carina Kauf, Jennifer Hu, R. T. Pramod, Gabriel Grand, Vivian C. Paulun, Maria Ryskina, Ekin Akyürek, Ethan Wilcox, Nafisa Rashid, Leshem Choshen, Roger Levy, Evelina Fedorenko, Joshua B. Tenenbaum, Jacob Andreas
2024 A* conf
In-Context Language Learning: Architectures and Algorithms.
ICML
Ekin Akyürek, Bailin Wang, Yoon Kim, Jacob Andreas
2024 J jnl
In-Context Language Learning: Architectures and Algorithms.
CoRR
Ekin Akyürek, Bailin Wang, Yoon Kim, Jacob Andreas
2024 — conf
Interpreting User Requests in the Context of Natural Language Standing Instructions.
NAACL-HLT (Findings)
Nikita Moghe, Patrick Xia, Jacob Andreas, Jason Eisner, Benjamin Van Durme, Harsh Jhamtani
2024 A* conf
LILO: Learning Interpretable Libraries by Compressing and Documenting Code.
ICLR
Gabriel Grand, Lionel Wong, Matthew Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas
2024 J jnl
Language Modeling with Editable External Knowledge.
CoRR
Belinda Z. Li, Emmy Liu, Alexis Ross, Abbas Zeitoun, Graham Neubig, Jacob Andreas
2024 A* conf
Language-to-Code Translation with a Single Labeled Example.
EMNLP
Kaj Bostrom, Harsh Jhamtani, Hao Fang, Sam Thomson, Richard Shin, Patrick Xia, Benjamin Van Durme, Jason Eisner, Jacob Andreas
2024 A* conf
Learning Grounded Action Abstractions from Language.
ICLR
Lionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, Jacob Andreas
2024 J jnl
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation.
CoRR
Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas
2024 J jnl
Learning Linear Attention in Polynomial Time.
CoRR
Morris Yau, Ekin Akyürek, Jiayuan Mao, Joshua B. Tenenbaum, Stefanie Jegelka, Jacob Andreas
2024 J jnl
Learning Phonotactics from Linguistic Informants.
CoRR
Canaan Breiss, Alexis Ross, Amani Maina-Kilaas, Roger Levy, Jacob Andreas
2024 A* conf
Learning with Language-Guided State Abstractions.
ICLR
Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie Shah
2024 J jnl
Learning with Language-Guided State Abstractions.
CoRR
Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie A. Shah
2024 — conf
Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling.
ACL (Findings)
Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas
2024 J jnl
Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling.
CoRR
Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas
2024 A* conf
Linearity of Relation Decoding in Transformer Language Models.
ICLR
Evan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau
2024 J jnl
LoRA vs Full Fine-tuning: An Illusion of Equivalence.
CoRR
Reece Shuttleworth, Jacob Andreas, Antonio Torralba, Pratyusha Sharma
2024 B conf
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling.
CogSci
Gabriel Grand, Valerio Pepe, Jacob Andreas, Josh Tenenbaum
2024 J jnl
Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Sampling.
CoRR
Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum
2024 A* conf
MisinfoEval: Generative AI in the Era of "Alternative Facts".
EMNLP
Saadia Gabriel, Liang Lyu, James Siderius, Marzyeh Ghassemi, Jacob Andreas, Asuman E. Ozdaglar
2024 J jnl
MisinfoEval: Generative AI in the Era of "Alternative Facts".
CoRR
Saadia Gabriel, Liang Lyu, James Siderius, Marzyeh Ghassemi, Jacob Andreas, Asuman E. Ozdaglar
2024 A* conf
Modeling Boundedly Rational Agents with Latent Inference Budgets.
ICLR
Athul Paul Jacob, Abhishek Gupta, Jacob Andreas
2024 A* conf
Natural Language Decomposition and Interpretation of Complex Utterances.
IJCAI
Harsh Jhamtani, Hao Fang, Patrick Xia, Eran Levy, Jacob Andreas, Benjamin Van Durme
2024 B conf
Naturalistic Transmission of Causal Knowledge between Machines and Humans.
CogSci
Cédric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah D. Goodman, Jacob Andreas, Josh Tenenbaum
2024 J jnl
Policy Learning with a Language Bottleneck.
CoRR
Megha Srivastava, Cédric Colas, Dorsa Sadigh, Jacob Andreas
2024 — conf
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks.
NAACL-HLT
Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim
2024 — conf
Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning.
NAACL-HLT
Athul Paul Jacob, Gabriele Farina, Jacob Andreas
2024 A* conf
The Consensus Game: Language Model Generation via Equilibrium Search.
ICLR
Athul Paul Jacob, Yikang Shen, Gabriele Farina, Jacob Andreas
2024 J jnl
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning.
CoRR
Ekin Akyürek, Mehul Damani, Linlu Qiu, Han Guo, Yoon Kim, Jacob Andreas
2024 — conf
Toward In-Context Teaching: Adapting Examples to Students' Misconceptions.
ACL (1)
Alexis Ross, Jacob Andreas
2024 J jnl
Toward In-Context Teaching: Adapting Examples to Students' Misconceptions.
CoRR
Alexis Ross, Jacob Andreas
2024 J jnl
Unforgettable Generalization in Language Models.
CoRR
Eric Zhang, Leshem Choshen, Jacob Andreas
2024 — conf
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes.
NAACL-HLT
Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas
2023 J jnl
A Function Interpretation Benchmark for Evaluating Interpretability Methods.
CoRR
Sarah Schwettmann, Tamar Rott Shaham, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba
2023 B conf
Alignment via Mutual Information.
CoNLL
Shinjini Ghosh, Yoon Kim, Ramón Fernandez Astudillo, Tahira Naseem, Jacob Andreas
2023 A* conf
Characterizing intrinsic compositionality in transformers with Tree Projections.
ICLR
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2023 A* conf
Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?
EMNLP
Kevin Liu, Stephen Casper, Dylan Hadfield-Menell, Jacob Andreas
2023 J jnl
Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?
CoRR
Kevin Liu, Stephen Casper, Dylan Hadfield-Menell, Jacob Andreas
2023 J jnl
Decision-Oriented Dialogue for Human-AI Collaboration.
CoRR
Jessy Lin, Nicholas Tomlin, Jacob Andreas, Jason Eisner
2023 J jnl
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling.
CoRR
Bairu Hou, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang, Yang Zhang
2023 J jnl
Eliciting Human Preferences with Language Models.
CoRR
Belinda Z. Li, Alex Tamkin, Noah D. Goodman, Jacob Andreas
2023 J jnl
Evaluating the Utility of Model Explanations for Model Development.
CoRR
Shawn Im, Jacob Andreas, Yilun Zhou
2023 A* conf
FIND: A Function Description Benchmark for Evaluating Interpretability Methods.
NeurIPS
Sarah Schwettmann, Tamar Rott Shaham, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba
2023 J jnl
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought.
CoRR
Lionel Wong, Gabriel Grand, Alexander K. Lew, Noah D. Goodman, Vikash K. Mansinghka, Jacob Andreas, Joshua B. Tenenbaum
2023 — conf
Grokking of Hierarchical Structure in Vanilla Transformers.
ACL (2)
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2023 J jnl
Grokking of Hierarchical Structure in Vanilla Transformers.
CoRR
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2023 A* conf
Guiding Pretraining in Reinforcement Learning with Large Language Models.
ICML
Yuqing Du, Olivia Watkins, Zihan Wang, Cédric Colas, Trevor Darrell, Pieter Abbeel, Abhishek Gupta, Jacob Andreas
2023 J jnl
Guiding Pretraining in Reinforcement Learning with Large Language Models.
CoRR
Yuqing Du, Olivia Watkins, Zihan Wang, Cédric Colas, Trevor Darrell, Pieter Abbeel, Abhishek Gupta, Jacob Andreas
2023 J jnl
Interpreting User Requests in the Context of Natural Language Standing Instructions.
CoRR
Nikita Moghe, Patrick Xia, Jacob Andreas, Jason Eisner, Benjamin Van Durme, Harsh Jhamtani
2023 J jnl
LILO: Learning Interpretable Libraries by Compressing and Documenting Code.
CoRR
Gabriel Grand, Lionel Wong, Matthew Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas
2023 J jnl
LaMPP: Language Models as Probabilistic Priors for Perception and Action.
CoRR
Belinda Z. Li, William Chen, Pratyusha Sharma, Jacob Andreas
2023 — conf
Language Modeling with Latent Situations.
ACL (Findings)
Belinda Z. Li, Maxwell I. Nye, Jacob Andreas
2023 J jnl
Language Models Trained on Media Diets Can Predict Public Opinion.
CoRR
Eric Chu, Jacob Andreas, Stephen Ansolabehere, Deb Roy
2023 J jnl
Learning adaptive planning representations with natural language guidance.
CoRR
Lionel Wong, Jiayuan Mao, Pratyusha Sharma, Zachary S. Siegel, Jiahai Feng, Noa Korneev, Joshua B. Tenenbaum, Jacob Andreas
2023 — conf
LexSym: Compositionality as Lexical Symmetry.
ACL (1)
Ekin Akyürek, Jacob Andreas
2023 J jnl
Linearity of Relation Decoding in Transformer Language Models.
CoRR
Evan Hernandez, Arnab Sen Sharma, Tal Haklay, Kevin Meng, Martin Wattenberg, Jacob Andreas, Yonatan Belinkov, David Bau
2023 J jnl
Measuring and Manipulating Knowledge Representations in Language Models.
CoRR
Evan Hernandez, Belinda Z. Li, Jacob Andreas
2023 J jnl
Modeling Boundedly Rational Agents with Latent Inference Budgets.
CoRR
Athul Paul Jacob, Abhishek Gupta, Jacob Andreas
2023 J jnl
Natural Language Decomposition and Interpretation of Complex Utterances.
CoRR
Harsh Jhamtani, Hao Fang, Patrick Xia, Eran Levy, Jacob Andreas, Benjamin Van Durme
2023 A* conf
PromptBoosting: Black-Box Text Classification with Ten Forward Passes.
ICML
Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang
2023 A* conf
Pushdown Layers: Encoding Recursive Structure in Transformer Language Models.
EMNLP
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2023 J jnl
Pushdown Layers: Encoding Recursive Structure in Transformer Language Models.
CoRR
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2023 J jnl
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks.
CoRR
Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim
2023 J jnl
Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning.
CoRR
Athul Paul Jacob, Gabriele Farina, Jacob Andreas
2023 A* conf
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks.
NeurIPS
Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas
2023 J jnl
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks.
CoRR
Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas
2023 J jnl
The Consensus Game: Language Model Generation via Equilibrium Search.
CoRR
Athul Paul Jacob, Yikang Shen, Gabriele Farina, Jacob Andreas
2023 — conf
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding.
ACL (Findings)
Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, Dan Klein
2023 J jnl
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes.
CoRR
Chengxu Zhuang, Evelina Fedorenko, Jacob Andreas
2023 A* conf
What learning algorithm is in-context learning? Investigations with linear models.
ICLR
Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou
2022 J jnl
Characterizing Intrinsic Compositionality in Transformers with Tree Projections.
CoRR
Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning
2022 J jnl
Compositionality as Lexical Symmetry.
CoRR
Ekin Akyürek, Jacob Andreas
2022 — conf
Correcting Robot Plans with Natural Language Feedback.
Robotics: Science and Systems
Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis, Chris Paxton, Tucker Hermans, Antonio Torralba, Jacob Andreas, Dieter Fox
2022 J jnl
Correcting Robot Plans with Natural Language Feedback.
CoRR
Pratyusha Sharma, Balakumar Sundaralingam, Valts Blukis, Chris Paxton, Tucker Hermans, Antonio Torralba, Jacob Andreas, Dieter Fox
2022 — conf
Guided K-best Selection for Semantic Parsing Annotation.
ACL (demo)
Anton Belyy, Chieh-Yang Huang, Jacob Andreas, Emmanouil Antonios Platanios, Sam Thomson, Richard Shin, Subhro Roy, Aleksandr Nisnevich, Charles Chen, Benjamin Van Durme
2022 A* conf
Hierarchical Phrase-Based Sequence-to-Sequence Learning.
EMNLP
Bailin Wang, Ivan Titov, Jacob Andreas, Yoon Kim
2022 J jnl
Hierarchical Phrase-based Sequence-to-Sequence Learning.
CoRR
Bailin Wang, Ivan Titov, Jacob Andreas, Yoon Kim
2022 B conf
Identifying concept libraries from language about object structure.
CogSci
Catherine Wong, William P. McCarthy, Gabriel Grand, Yoni Friedman, Josh Tenenbaum, Jacob Andreas, Robert D. Hawkins, Judith E. Fan
2022 J jnl
Identifying concept libraries from language about object structure.
CoRR
Catherine Wong, William P. McCarthy, Gabriel Grand, Yoni Friedman, Joshua B. Tenenbaum, Jacob Andreas, Robert D. Hawkins, Judith E. Fan
2022 J jnl
Language Modeling with Latent Situations.
CoRR
Belinda Z. Li, Maxwell I. Nye, Jacob Andreas
2022 — conf
Language Models as Agent Models.
EMNLP (Findings)
Jacob Andreas
2022 J jnl
Language Models as Agent Models.
CoRR
Jacob Andreas
2022 A* conf
Modeling Strong and Human-Like Gameplay with KL-Regularized Search.
ICML
Athul Paul Jacob, David J. Wu, Gabriele Farina, Adam Lerer, Hengyuan Hu, Anton Bakhtin, Jacob Andreas, Noam Brown
2022 A* conf
Natural Language Descriptions of Deep Visual Features.
ICLR
Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, Jacob Andreas
2022 J jnl
Natural Language Descriptions of Deep Visual Features.
CoRR
Evan Hernandez, Sarah Schwettmann, David Bau, Teona Bagashvili, Antonio Torralba, Jacob Andreas
2022 J jnl
ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications.
CoRR
Alex Gu, Tamara Mitrovska, Daniela Velez, Jacob Andreas, Armando Solar-Lezama
2022 A* conf
Pre-Trained Language Models for Interactive Decision-Making.
NeurIPS
Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Akyürek, Anima Anandkumar, Jacob Andreas, Igor Mordatch, Antonio Torralba, Yuke Zhu
2022 J jnl
Pre-Trained Language Models for Interactive Decision-Making.
CoRR
Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Akyürek, Anima Anandkumar, Jacob Andreas, Igor Mordatch, Antonio Torralba, Yuke Zhu
2022 J jnl
PromptBoosting: Black-Box Text Classification with Ten Forward Passes.
CoRR
Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang
2022 — conf
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks.
NAACL-HLT
Belinda Z. Li, Jane A. Yu, Madian Khabsa, Luke Zettlemoyer, Alon Y. Halevy, Jacob Andreas
2022 — conf
Skill Induction and Planning with Latent Language.
ACL (1)
Pratyusha Sharma, Antonio Torralba, Jacob Andreas
2022 A* conf
Subspace Regularizers for Few-Shot Class Incremental Learning.
ICLR
Afra Feyza Akyürek, Ekin Akyürek, Derry Wijaya, Jacob Andreas
2022 J jnl
Teachable Reinforcement Learning via Advice Distillation.
CoRR
Olivia Watkins, Trevor Darrell, Pieter Abbeel, Jacob Andreas, Abhishek Gupta
2022 J jnl
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding.
CoRR
Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, Dan Klein
2022 — conf
Towards Tracing Knowledge in Language Models Back to the Training Data.
EMNLP (Findings)
Ekin Akyürek, Tolga Bolukbasi, Frederick Liu, Binbin Xiong, Ian Tenney, Jacob Andreas, Kelvin Guu
2022 J jnl
Tracing Knowledge in Language Models Back to the Training Data.
CoRR
Ekin Akyürek, Tolga Bolukbasi, Frederick Liu, Binbin Xiong, Ian Tenney, Jacob Andreas, Kelvin Guu
2022 J jnl
What learning algorithm is in-context learning? Investigations with linear models.
CoRR
Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou
2021 J jnl
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales.
CoRR
Jacob Andreas, Gasper Begus, Michael M. Bronstein, Roee Diamant, Denley Delaney, Shane Gero, Shafi Goldwasser, David F. Gruber, Sarah de Haas, Peter Malkin, Roger Payne, Giovanni Petri, Daniela Rus, Pratyusha Sharma, Dan Tchernov, Pernille Tønnesen, Antonio Torralba, Daniel M. Vogt, Robert J. Wood
2021 — conf
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention.
NAACL-HLT
Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su, Sam Thomson, Jacob Andreas
2021 J jnl
FairyTailor: A Multimodal Generative Framework for Storytelling.
CoRR
Eden Bensaid, Mauro Martino, Benjamin Hoover, Jacob Andreas, Hendrik Strobelt
2021 J jnl
How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction.
CoRR
D. Anthony Bau, Jacob Andreas
2021 — conf
How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution Prediction.
EMNLP (1)
D. Anthony Bau, Jacob Andreas
2021 — conf
Implicit Representations of Meaning in Neural Language Models.
ACL/IJCNLP (1)
Belinda Z. Li, Maxwell I. Nye, Jacob Andreas
2021 J jnl
Implicit Representations of Meaning in Neural Language Models.
CoRR
Belinda Z. Li, Maxwell I. Nye, Jacob Andreas
2021 B conf
Language as a bootstrap for compositional visual reasoning.
CogSci
Catherine Wong, Yoni Friedman, Jacob Andreas, Josh Tenenbaum
2021 A* conf
Learning to Recombine and Resample Data For Compositional Generalization.
ICLR
Ekin Akyürek, Afra Feyza Akyürek, Jacob Andreas
2021 A* conf
Leveraging Language to Learn Program Abstractions and Search Heuristics.
ICML
Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum, Jacob Andreas
2021 J jnl
Leveraging Language to Learn Program Abstractions and Search Heuristics.
CoRR
Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum, Jacob Andreas
2021 — conf
Lexicon Learning for Few Shot Sequence Modeling.
ACL/IJCNLP (1)
Ekin Akyürek, Jacob Andreas
2021 J jnl
Lexicon Learning for Few-Shot Neural Sequence Modeling.
CoRR
Ekin Akyürek, Jacob Andreas
2021 J jnl
Modeling Strong and Human-Like Gameplay with KL-Regularized Search.
CoRR
Athul Paul Jacob, David J. Wu, Gabriele Farina, Adam Lerer, Anton Bakhtin, Jacob Andreas, Noam Brown
2021 — conf
Multitasking Inhibits Semantic Drift.
NAACL-HLT
Athul Paul Jacob, Mike Lewis, Jacob Andreas
2021 J jnl
Multitasking Inhibits Semantic Drift.
CoRR
Athul Paul Jacob, Mike Lewis, Jacob Andreas
2021 J jnl
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks.
CoRR
Belinda Z. Li, Jane A. Yu, Madian Khabsa, Luke Zettlemoyer, Alon Y. Halevy, Jacob Andreas
2021 A* conf
Representing Partial Programs with Blended Abstract Semantics.
ICLR
Maxwell I. Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama
2021 J jnl
Skill Induction and Planning with Latent Language.
CoRR
Pratyusha Sharma, Antonio Torralba, Jacob Andreas
2021 J jnl
Subspace Regularizers for Few-Shot Class Incremental Learning.
CoRR
Afra Feyza Akyürek, Ekin Akyürek, Derry Wijaya, Jacob Andreas
2021 A* conf
Teachable Reinforcement Learning via Advice Distillation.
NeurIPS
Olivia Watkins, Abhishek Gupta, Trevor Darrell, Pieter Abbeel, Jacob Andreas
2021 B conf
The Low-Dimensional Linear Geometry of Contextualized Word Representations.
CoNLL
Evan Hernandez, Jacob Andreas
2021 J jnl
The Low-Dimensional Linear Geometry of Contextualized Word Representations.
CoRR
Evan Hernandez, Jacob Andreas
2021 A* conf
Toward a Visual Concept Vocabulary for GAN Latent Space.
ICCV
Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba
2021 J jnl
Toward a Visual Concept Vocabulary for GAN Latent Space.
CoRR
Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba
2021 — conf
Value-Agnostic Conversational Semantic Parsing.
ACL/IJCNLP (1)
Emmanouil Antonios Platanios, Adam Pauls, Subhro Roy, Yuchen Zhang, Alexander Kyte, Alan Guo, Sam Thomson, Jayant Krishnamurthy, Jason Andrew Wolfe, Jacob Andreas, Dan Klein
2021 — conf
What Context Features Can Transformer Language Models Use?
ACL/IJCNLP (1)
Joe O'Connor, Jacob Andreas
2021 J jnl
What Context Features Can Transformer Language Models Use?
CoRR
Joe O'Connor, Jacob Andreas
2020 A* conf
A Benchmark for Systematic Generalization in Grounded Language Understanding.
NeurIPS
Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake
2020 J jnl
A Benchmark for Systematic Generalization in Grounded Language Understanding.
CoRR
Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake
2020 J jnl
Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction.
CoRR
Eric Chu, Deb Roy, Jacob Andreas
2020 A* conf
Compositional Explanations of Neurons.
NeurIPS
Jesse Mu, Jacob Andreas
2020 J jnl
Compositional Explanations of Neurons.
CoRR
Jesse Mu, Jacob Andreas
2020 — conf
Experience Grounds Language.
EMNLP (1)
Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph P. Turian
2020 J jnl
Experience Grounds Language.
CoRR
Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph P. Turian
2020 A* conf
Good-Enough Compositional Data Augmentation.
ACL
Jacob Andreas
2020 — conf
Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment.
MICCAI (2)
Geeticka Chauhan, Ruizhi Liao, William M. Wells III, Jacob Andreas, Xin Wang, Seth J. Berkowitz, Steven Horng, Peter Szolovits, Polina Golland
2020 J jnl
Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment.
CoRR
Geeticka Chauhan, Ruizhi Liao, William M. Wells III, Jacob Andreas, Xin Wang, Seth J. Berkowitz, Steven Horng, Peter Szolovits, Polina Golland
2020 J jnl
Learning to Recombine and Resample Data for Compositional Generalization.
CoRR
Ekin Akyürek, Afra Feyza Akyürek, Jacob Andreas
2020 J jnl
Representing Partial Programs with Blended Abstract Semantics.
CoRR
Maxwell I. Nye, Yewen Pu, Matthew Bowers, Jacob Andreas, Joshua B. Tenenbaum, Armando Solar-Lezama
2020 J jnl
Task-Oriented Dialogue as Dataflow Synthesis.
CoRR
Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Andrew Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov
2020 J jnl
Task-Oriented Dialogue as Dataflow Synthesis.
Trans. Assoc. Comput. Linguistics
Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Andrew Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov
2020 J jnl
Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data.
CoRR
Alana Marzoev, Samuel Madden, M. Frans Kaashoek, Michael J. Cafarella, Jacob Andreas
2019 A* conf
A Survey of Reinforcement Learning Informed by Natural Language.
IJCAI
Jelena Luketina, Nantas Nardelli, Gregory Farquhar, Jakob N. Foerster, Jacob Andreas, Edward Grefenstette, Shimon Whiteson, Tim Rocktäschel
2019 J jnl
A Survey of Reinforcement Learning Informed by Natural Language.
CoRR
Jelena Luketina, Nantas Nardelli, Gregory Farquhar, Jakob N. Foerster, Jacob Andreas, Edward Grefenstette, Shimon Whiteson, Tim Rocktäschel
2019 J jnl
Good-Enough Compositional Data Augmentation.
CoRR
Jacob Andreas
2019 — conf
Guiding Policies with Language via Meta-Learning.
ICLR (Poster)
John D. Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, Jacob Andreas, John DeNero, Pieter Abbeel, Sergey Levine
2019 — conf
Measuring Compositionality in Representation Learning.
ICLR (Poster)
Jacob Andreas
2019 J jnl
Measuring Compositionality in Representation Learning.
CoRR
Jacob Andreas
2019 — conf
Pragmatically Informative Text Generation.
NAACL-HLT (1)
Sheng Shen, Daniel Fried, Jacob Andreas, Dan Klein
2019 J jnl
Pragmatically Informative Text Generation.
CoRR
Sheng Shen, Daniel Fried, Jacob Andreas, Dan Klein
2018 A* conf
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
ICML
Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon M. Kleinberg
2018 — conf
Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?
ICLR (Workshop)
Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon M. Kleinberg
2018 — conf
Explainable Neural Computation via Stack Neural Module Networks.
ECCV (7)
Ronghang Hu, Jacob Andreas, Trevor Darrell, Kate Saenko
2018 J jnl
Explainable Neural Computation via Stack Neural Module Networks.
CoRR
Ronghang Hu, Jacob Andreas, Trevor Darrell, Kate Saenko
2018 — —
Learning from Language.
Jacob Andreas
2018 — conf
Learning with Latent Language.
NAACL-HLT
Jacob Andreas, Dan Klein, Sergey Levine
2018 A* conf
Speaker-Follower Models for Vision-and-Language Navigation.
NeurIPS
Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, Trevor Darrell
2018 J jnl
Speaker-Follower Models for Vision-and-Language Navigation.
CoRR
Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach, Jacob Andreas, Louis-Philippe Morency, Taylor Berg-Kirkpatrick, Kate Saenko, Dan Klein, Trevor Darrell
2018 — conf
Unified Pragmatic Models for Generating and Following Instructions.
NAACL-HLT
Daniel Fried, Jacob Andreas, Dan Klein
2017 — conf
A Minimal Span-Based Neural Constituency Parser.
ACL (1)
Mitchell Stern, Jacob Andreas, Dan Klein
2017 J jnl
A Minimal Span-Based Neural Constituency Parser.
CoRR
Mitchell Stern, Jacob Andreas, Dan Klein
2017 A* conf
Analogs of Linguistic Structure in Deep Representations.
EMNLP
Jacob Andreas, Dan Klein
2017 J jnl
Analogs of Linguistic Structure in Deep Representations.
CoRR
Jacob Andreas, Dan Klein
2017 J jnl
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
CoRR
Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon M. Kleinberg
2017 A* conf
Learning to Reason: End-to-End Module Networks for Visual Question Answering.
ICCV
Ronghang Hu, Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Kate Saenko
2017 J jnl
Learning to Reason: End-to-End Module Networks for Visual Question Answering.
CoRR
Ronghang Hu, Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Kate Saenko
2017 J jnl
Learning with Latent Language.
CoRR
Jacob Andreas, Dan Klein, Sergey Levine
2017 A* conf
Modeling Relationships in Referential Expressions with Compositional Modular Networks.
CVPR
Ronghang Hu, Marcus Rohrbach, Jacob Andreas, Trevor Darrell, Kate Saenko
2017 A* conf
Modular Multitask Reinforcement Learning with Policy Sketches.
ICML
Jacob Andreas, Dan Klein, Sergey Levine
2017 — ed.
Proceedings of the First Workshop on Language Grounding for Robotics, RoboNLP@ACL 2017, Vancouver, Canada, August 3, 2017
RoboNLP@ACL
Mohit Bansal, Cynthia Matuszek, Jacob Andreas, Yoav Artzi, Yonatan Bisk
2017 — conf
Translating Neuralese.
ACL (1)
Jacob Andreas, Anca D. Dragan, Dan Klein
2017 J jnl
Translating Neuralese.
CoRR
Jacob Andreas, Anca D. Dragan, Dan Klein
2017 J jnl
Unified Pragmatic Models for Generating and Following Instructions.
CoRR
Daniel Fried, Jacob Andreas, Dan Klein
2016 — conf
Learning to Compose Neural Networks for Question Answering.
HLT-NAACL
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
2016 J jnl
Learning to Compose Neural Networks for Question Answering.
CoRR
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
2016 J jnl
Modeling Relationships in Referential Expressions with Compositional Modular Networks.
CoRR
Ronghang Hu, Marcus Rohrbach, Jacob Andreas, Trevor Darrell, Kate Saenko
2016 J jnl
Modular Multitask Reinforcement Learning with Policy Sketches.
CoRR
Jacob Andreas, Dan Klein, Sergey Levine
2016 A* conf
Neural Module Networks.
CVPR
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
2016 J jnl
Reasoning About Pragmatics with Neural Listeners and Speakers.
CoRR
Jacob Andreas, Dan Klein
2016 A* conf
Reasoning about Pragmatics with Neural Listeners and Speakers.
EMNLP
Jacob Andreas, Dan Klein
2015 A* conf
Alignment-Based Compositional Semantics for Instruction Following.
EMNLP
Jacob Andreas, Dan Klein
2015 J jnl
Alignment-based compositional semantics for instruction following.
CoRR
Jacob Andreas, Dan Klein
2015 J jnl
Deep Compositional Question Answering with Neural Module Networks.
CoRR
Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein
2015 — conf
On the Accuracy of Self-Normalized Log-Linear Models.
NIPS
Jacob Andreas, Maxim Rabinovich, Michael I. Jordan, Dan Klein
2015 J jnl
On the accuracy of self-normalized log-linear models.
CoRR
Jacob Andreas, Maxim Rabinovich, Dan Klein, Michael I. Jordan
2015 — conf
When and why are log-linear models self-normalizing?
HLT-NAACL
Jacob Andreas, Dan Klein
2014 B conf
Grounding Language with Points and Paths in Continuous Spaces.
CoNLL
Jacob Andreas, Dan Klein
2014 — conf
How much do word embeddings encode about syntax?
ACL (2)
Jacob Andreas, Dan Klein
2014 — conf
Unsupervised Transcription of Piano Music.
NIPS
Taylor Berg-Kirkpatrick, Jacob Andreas, Dan Klein
2013 — conf
A Generative Model of Vector Space Semantics.
CVSM@ACL
Jacob Andreas, Zoubin Ghahramani
2013 — conf
Parsing Graphs with Hyperedge Replacement Grammars.
ACL (1)
David Chiang, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Bevan K. Jones, Kevin Knight
2013 — conf
Semantic Parsing as Machine Translation.
ACL (2)
Jacob Andreas, Andreas Vlachos, Stephen Clark
2012 B conf
Annotating Agreement and Disagreement in Threaded Discussion.
LREC
Jacob Andreas, Sara Rosenthal, Kathleen R. McKeown
2012 B conf
Semantics-Based Machine Translation with Hyperedge Replacement Grammars.
COLING
Bevan K. Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, Kevin Knight
2012 J jnl
The Complexity of Learning Principles and Parameters Grammars
CoRR
Jacob Andreas
2011 — conf
Fuzzy Syntactic Reordering for Phrase-based Statistical Machine Translation.
WMT@EMNLP
Jacob Andreas, Nizar Habash, Owen Rambow
2010 — conf
Corpus Creation for New Genres: A Crowdsourced Approach to PP Attachment.
Mturk@HLT-NAACL
Mukund Jha, Jacob Andreas, Kapil Thadani, Sara Rosenthal, Kathleen R. McKeown
2010 B conf
Towards Semi-Automated Annotation for Prepositional Phrase Attachment.
LREC
Sara Rosenthal, William Lipovsky, Kathleen R. McKeown, Kapil Thadani, Jacob Andreas