Anirudh Goyal

A Systematic Examination of Preference Learning through the Lens of Instruction-Following NAACL 2025 Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? ICML 2025 Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning ICLR 2025 On the Transfer of Object-Centric Representation Learning ICLR 2025 SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement ICLR 2025 Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron ICLR 2025 Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025 αTC-VAE: On the relationship between Disentanglement and Diversity ICLR 2024 Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling NeurIPS 2024 Can Models Learn Skill Composition from Examples? NeurIPS 2024 Cycle Consistency Driven Object Discovery ICLR 2024 Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates NeurIPS 2024 Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving NeurIPS 2024 Reasoning Robustness of LLMs to Adversarial Typographical Errors EMNLP 2024 SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models ICLR 2024 Discrete Key-Value Bottleneck ICML 2023 GFlowOut: Dropout with Generative Flow Networks ICML 2023 Learning to Induce Causal Structure ICLR 2023 Representation Learning in Deep RL via Discrete Information Bottleneck AISTATS 2023 Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning ICLR 2023 Test-time Adaptation with Slot-Centric Models ICML 2023 Coordination Among Neural Modules Through a Shared Global Workspace ICLR 2022 Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning NeurIPS 2022 Learning by Directional Gradient Descent ICLR 2022 Retrieval-Augmented Reinforcement Learning ICML 2022 Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning NeurIPS 2022 CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning ICLR 2021 DIBS: Diversity Inducing Information Bottleneck in Model Ensembles AAAI 2021 Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments ICLR 2021 Fast And Slow Learning Of Recurrent Independent Mechanisms ICLR 2021 Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers AISTATS 2021 On Disentangled Representations Learned from Correlated Data ICML 2021 Recurrent Independent Mechanisms ICLR 2021 Robust Representation Learning via Perceptual Similarity Metrics ICML 2021 Spatially Structured Recurrent Modules ICLR 2021 A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms ICLR 2020 Learning the Arrow of Time for Problems in Reinforcement Learning ICLR 2020 Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules ICML 2020 Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives ICLR 2020 Small-GAN: Speeding up GAN Training using Core-Sets ICML 2020 The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget ICLR 2020 InfoBot: Transfer and Exploration via the Information Bottleneck ICLR 2019 Modeling the Long Term Future in Model-Based Reinforcement Learning ICLR 2019 Recall Traces: Backtracking Models for Efficient Reinforcement Learning ICLR 2019 State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations ICML 2019