Jesse Thomason

Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations ACL 2026 Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning AAAI 2026 Can VLMs Recall Factual Associations From Visual References? EMNLP 2025 Efficient Evaluation of Multi-Task Robot Policies With Active Experiment Selection CoRL 2025 Language Models Can Infer Action Semantics for Symbolic Planners from Environment Feedback NAACL 2025 Large Language Models Do Multi-Label Classification Differently EMNLP 2025 ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations CoRL 2025 The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge NAACL 2025 Why Do Some Inputs Break Low-Bit LLM Quantization? EMNLP 2025 Contrast Sets for Evaluating Language-Guided Robot Policies CoRL 2024 Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks NAACL 2024 Efficient End-to-End Visual Document Understanding with Rationale Distillation NAACL 2024 Selective “Selective Prediction”: Reducing Unnecessary Abstention in Vision-Language Reasoning ACL 2024 THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation RSS 2024 When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models EMNLP 2024 Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding NAACL 2024 WINOVIZ: Probing Visual Properties of Objects Under Different States NAACL 2024 Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering EMNLP 2023 Improving Sign Recognition with Phonology EACL 2023 Iterative Vision-and-Language Navigation CVPR 2023 Multimodal Speech Recognition for Language-Guided Embodied Agents Interspeech 2023 Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation EMNLP 2023 ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments EMNLP 2022 CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks NeurIPS 2022 Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems EMNLP 2022 TEACh: Task-Driven Embodied Agents That Chat AAAI 2022 Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions ACL 2022 Language Grounding with 3D Objects CoRL 2021 ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks CVPR 2020 Experience Grounds Language EMNLP 2020 RMM: A Recursive Mental Model for Dialogue Navigation EMNLP 2020 The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation CoRL 2020 Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP) NAACL 2019 Shifting the Baseline: Single Modality Performance on Visual Navigation & QA NAACL 2019 Vision-and-Dialog Navigation CoRL 2019 Multi-modal Predicate Identification using Dynamically Learned Robot Controllers IJCAI 2018 Improving Black-box Speech Recognition using Semantic Parsing IJCNLP 2017 Integrated Learning of Dialog Strategies and Semantic Parsing EACL 2017 Multi-Modal Word Synset Induction IJCAI 2017 Opportunistic Active Learning for Grounding Natural Language Descriptions CoRL 2017 Learning Multi-Modal Grounded Linguistic Semantics by Playing “I Spy” IJCAI 2016 Learning to Interpret Natural Language Commands through Human-Robot Dialog IJCAI 2015 Integrating Language and Vision to Generate Natural Language Descriptions of Videos in the Wild COLING 2014 Differences in User Responses to a Wizard-of-Oz versus Automated System NAACL 2013