Karthik Narasimhan

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks COLING 2025 InstructEval: Systematic Evaluation of Instruction Selection Methods NAACL 2024 Language-guided World Models: A Model-based Approach to AI Control ACL 2024 QualEval: Qualitative Evaluation for Model Improvement NAACL 2024 Referral Augmentation for Zero-Shot Information Retrieval ACL 2024 SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering NeurIPS 2024 Anthropomorphization of AI: Opportunities and Risks EMNLP 2023 C-STS: Conditional Semantic Textual Similarity EMNLP 2023 InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback NeurIPS 2023 MUX-PLMs: Data Multiplexing for High-throughput Language Models EMNLP 2023 MUX-PLMs: Pre-training Language Models with Data Multiplexing ACL 2023 PruMUX: Augmenting Data Multiplexing with Model Compression ACL 2023 Reflexion: language agents with verbal reinforcement learning NeurIPS 2023 Toxicity in chatgpt: Analyzing persona-assigned language models EMNLP 2023 Tree of Thoughts: Deliberate Problem Solving with Large Language Models NeurIPS 2023 Can Rationalization Improve Robustness? NAACL 2022 CARETS: A Consistency And Robustness Evaluative Test Suite for VQA ACL 2022 DataMUX: Data Multiplexing for Neural Networks NeurIPS 2022 Learning Physics Constrained Dynamics Using Autoencoders NeurIPS 2022 Multi-Query Video Retrieval ECCV 2022 Using natural language and program abstractions to instill human inductive biases in machines NeurIPS 2022 WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents NeurIPS 2022 When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer NAACL 2022 Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ICML 2021 Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning ICML 2021 Improving Dialog Systems for Negotiation with Personality Modeling ACL 2021 Learning Rewards From Linguistic Feedback AAAI 2021 Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents NAACL 2021 Safe Reinforcement Learning with Natural Language Constraints NeurIPS 2021 Self-Attention Networks Can Process Bounded Hierarchical Languages ACL 2021 SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark NeurIPS 2021 Universal Adversarial Attacks with Natural Triggers for Text Classification NAACL 2021 Calibration, Entropy Rates, and Memory in Language Models ICML 2020 Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation NeurIPS 2020 Guiding Attention for Self-Supervised Learning with Transformers EMNLP 2020 Keep CALM and Explore: Language Models for Action Generation in Text-based Games EMNLP 2020 Multimodal Graph Networks for Compositional Generalization in Visual Question Answering NeurIPS 2020 Projection-Based Constrained Policy Optimization ICLR 2020 Robust and Interpretable Grounding of Spatial References with Relation Networks EMNLP 2020 Towards Unique and Informative Captioning of Images ECCV 2020 A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation NeurIPS 2019 Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation NeurIPS 2016 Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning EMNLP 2016 Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge EMNLP 2016 Nonparametric Spherical Topic Modeling with Word Embeddings ACL 2016 JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes ICML 2015 Language Understanding for Text-based Games using Deep Reinforcement Learning EMNLP 2015 Machine Comprehension with Discourse Relations ACL 2015 Morphological Segmentation for Keyword Spotting EMNLP 2014