← Authors

Anirudh Goyal

45 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (49) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (6) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (10) 🏠 Conference Loyalist (23) 🀝 Dynamic Duo (25) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (45) ⚑ Prolific Year (8) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (108)

Conferences

ICLR (23) ICML (11) NIPS (6) AISTATS (2) AAAI (1) EMNLP (1) NAACL (1)

Top co-authors

Yoshua Bengio (25) Nan Rosemary Ke (8) Kenji Kawaguchi (7) Alex Lamb (7) Bernhard SchΓΆlkopf (6) Sergey Levine (6) Michael Curtis Mozer (6) Sanjeev Arora (6) Nasim Rahaman (5) Hugo Larochelle (4)

Keywords

representation learning (6) variational inference (2) uncertainty estimation (2) out-of-distribution generalization (2) information bottleneck (2) self-supervised learning (2) attention mechanism (2) recurrent neural network (2) large language model (2) distribution shift (2) contrastive learning (1) robotic manipulation (1) offline reinforcement learning (1) anomaly detection (1) causal inference (1) sample efficiency (1) preference learning (1) catastrophic forgetting (1) deep reinforcement learning (1) mathematical reasoning (1)

Papers

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