Jacob Andreas

ARC Is a Vision Problem! CVPR 2026 A Hitchhiker’s Guide to Scaling Law Estimation ICML 2025 A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation NAACL 2025 Eliciting Human Preferences with Language Models ICLR 2025 (How) Do Language Models Track State? ICML 2025 Language Modeling with Editable External Knowledge NAACL 2025 Learning How Hard to Think: Input-Adaptive Allocation of LM Computation ICLR 2025 LLM Agents for Coordinating Multi-User Information Gathering ACL 2025 The Surprising Effectiveness of Test-Time Training for Few-Shot Learning ICML 2025 Adaptive Language-Guided Abstraction from Contrastive Explanations CoRL 2024 Algorithmic Capabilities of Random Transformers NeurIPS 2024 A Multimodal Automated Interpretability Agent ICML 2024 Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling ICML 2024 Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability ACL 2024 In-Context Language Learning: Architectures and Algorithms ICML 2024 Interpreting User Requests in the Context of Natural Language Standing Instructions NAACL 2024 Language-to-Code Translation with a Single Labeled Example EMNLP 2024 Learning Grounded Action Abstractions from Language ICLR 2024 Learning with Language-Guided State Abstractions ICLR 2024 Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling ACL 2024 LILO: Learning Interpretable Libraries by Compressing and Documenting Code ICLR 2024 Linearity of Relation Decoding in Transformer Language Models ICLR 2024 MisinfoEval: Generative AI in the Era of “Alternative Facts” EMNLP 2024 Modeling Boundedly Rational Agents with Latent Inference Budgets ICLR 2024 Natural Language Decomposition and Interpretation of Complex Utterances IJCAI 2024 Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks NAACL 2024 Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning NAACL 2024 The Consensus Game: Language Model Generation via Equilibrium Search ICLR 2024 Toward In-Context Teaching: Adapting Examples to Students’ Misconceptions ACL 2024 Visual Grounding Helps Learn Word Meanings in Low-Data Regimes NAACL 2024 Alignment via Mutual Information CoNLL 2023 Characterizing intrinsic compositionality in transformers with Tree Projections ICLR 2023 Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness? EMNLP 2023 FIND: A Function Description Benchmark for Evaluating Interpretability Methods NeurIPS 2023 Grokking of Hierarchical Structure in Vanilla Transformers ACL 2023 Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 Language Modeling with Latent Situations ACL 2023 LexSym: Compositionality as Lexical Symmetry ACL 2023 PromptBoosting: Black-Box Text Classification with Ten Forward Passes ICML 2023 Pushdown Layers: Encoding Recursive Structure in Transformer Language Models EMNLP 2023 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NeurIPS 2023 The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding ACL 2023 ​​What learning algorithm is in-context learning? Investigations with linear models ICLR 2023 Correcting Robot Plans with Natural Language Feedback RSS 2022 Guided K-best Selection for Semantic Parsing Annotation ACL 2022 Hierarchical Phrase-Based Sequence-to-Sequence Learning EMNLP 2022 Language Models as Agent Models EMNLP 2022 Modeling Strong and Human-Like Gameplay with KL-Regularized Search ICML 2022 Natural Language Descriptions of Deep Visual Features ICLR 2022 Pre-Trained Language Models for Interactive Decision-Making NeurIPS 2022 Quantifying Adaptability in Pre-trained Language Models with 500 Tasks NAACL 2022 Skill Induction and Planning with Latent Language ACL 2022 Subspace Regularizers for Few-Shot Class Incremental Learning ICLR 2022 Towards Tracing Knowledge in Language Models Back to the Training Data EMNLP 2022 Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention NAACL 2021 How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution Prediction EMNLP 2021 Implicit Representations of Meaning in Neural Language Models ACL 2021 Learning to Recombine and Resample Data For Compositional Generalization ICLR 2021 Leveraging Language to Learn Program Abstractions and Search Heuristics ICML 2021 Lexicon Learning for Few Shot Sequence Modeling ACL 2021 Multitasking Inhibits Semantic Drift NAACL 2021 Representing Partial Programs with Blended Abstract Semantics ICLR 2021 Teachable Reinforcement Learning via Advice Distillation NeurIPS 2021 The Low-Dimensional Linear Geometry of Contextualized Word Representations CoNLL 2021 Toward a Visual Concept Vocabulary for GAN Latent Space ICCV 2021 Value-Agnostic Conversational Semantic Parsing ACL 2021 What Context Features Can Transformer Language Models Use? ACL 2021 A Benchmark for Systematic Generalization in Grounded Language Understanding NeurIPS 2020 Compositional Explanations of Neurons NeurIPS 2020 Experience Grounds Language EMNLP 2020 Good-Enough Compositional Data Augmentation ACL 2020 A Survey of Reinforcement Learning Informed by Natural Language IJCAI 2019 Guiding Policies with Language via Meta-Learning ICLR 2019 Measuring Compositionality in Representation Learning ICLR 2019 Pragmatically Informative Text Generation NAACL 2019 Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? ICML 2018 Explainable Neural Computation via Stack Neural Module Networks ECCV 2018 Learning with Latent Language NAACL 2018 Speaker-Follower Models for Vision-and-Language Navigation NeurIPS 2018 Unified Pragmatic Models for Generating and Following Instructions NAACL 2018 A Minimal Span-Based Neural Constituency Parser ACL 2017 Analogs of Linguistic Structure in Deep Representations EMNLP 2017 Learning to Reason: End-To-End Module Networks for Visual Question Answering ICCV 2017 Modeling Relationships in Referential Expressions With Compositional Modular Networks CVPR 2017 Modular Multitask Reinforcement Learning with Policy Sketches ICML 2017 Translating Neuralese ACL 2017 Learning to Compose Neural Networks for Question Answering NAACL 2016 Neural Module Networks CVPR 2016 Proceedings of the NAACL Student Research Workshop NAACL 2016 Reasoning about Pragmatics with Neural Listeners and Speakers EMNLP 2016 Alignment-Based Compositional Semantics for Instruction Following EMNLP 2015 On the Accuracy of Self-Normalized Log-Linear Models NeurIPS 2015 When and why are log-linear models self-normalizing? NAACL 2015 Grounding Language with Points and Paths in Continuous Spaces CoNLL 2014 How much do word embeddings encode about syntax? ACL 2014 Unsupervised Transcription of Piano Music NeurIPS 2014 Parsing Graphs with Hyperedge Replacement Grammars ACL 2013 Semantic Parsing as Machine Translation ACL 2013 Semantics-Based Machine Translation with Hyperedge Replacement Grammars COLING 2012