Animesh Garg

EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning ICLR 2025 Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning CORL 2025 TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies CORL 2025 PWM: Policy Learning with Multi-Task World Models ICLR 2025 AnyPlace: Learning Generalizable Object Placement for Robot Manipulation CORL 2025 QueST: Self-Supervised Skill Abstractions for Learning Continuous Control NIPS 2024 Discovering Robotic Interaction Modes with Discrete Representation Learning CORL 2024 Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation ICML 2024 SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation CORL 2024 Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward ICLR 2023 SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models NIPS 2023 SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models ICLR 2023 Geometry Matching for Multi-Embodiment Grasping CORL 2023 Composable Part-Based Manipulation CORL 2023 Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning ICLR 2022 Breaking Bad: A Dataset for Geometric Fracture and Reassembly NIPS 2022 Experience Replay with Likelihood-free Importance Weights L4DC 2022 MoCoDA: Model-based Counterfactual Data Augmentation NIPS 2022 RoboTube: Learning Household Manipulation from Human Videos with Simulated Twin Environments CORL 2022 Bayesian Object Models for Robotic Interaction with Differentiable Probabilistic Programming CORL 2022 SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments NIPS 2022 Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings AAAI 2022 Grasp’D: Differentiable Contact-Rich Grasp Synthesis for Multi-Fingered Hands ECCV 2022 X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval CVPR 2022 Neural Shape Mating: Self-Supervised Object Assembly With Adversarial Shape Priors CVPR 2022 Modular Action Concept Grounding in Semantic Video Prediction CVPR 2022 Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics ICML 2022 Accelerated Policy Learning with Parallel Differentiable Simulation ICLR 2022 Value Gradient weighted Model-Based Reinforcement Learning ICLR 2022 Latent Skill Planning for Exploration and Transfer ICLR 2021 Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions NIPS 2021 Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers NIPS 2021 Dynamic Bottleneck for Robust Self-Supervised Exploration NIPS 2021 A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution CORL 2021 Seeing Glass: Joint Point-Cloud and Depth Completion for Transparent Objects CORL 2021 S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics CORL 2021 DIBS: Diversity Inducing Information Bottleneck in Model Ensembles AAAI 2021 C-Learning: Horizon-Aware Cumulative Accessibility Estimation ICLR 2021 Conservative Safety Critics for Exploration ICLR 2021 Principled Exploration via Optimistic Bootstrapping and Backward Induction ICML 2021 Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition ICML 2021 Value Iteration in Continuous Actions, States and Time ICML 2021 Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning ICML 2021 Robust Value Iteration for Continuous Control Tasks RSS 2021 GIFT: Generalizable Interaction-aware Functional Tool Affordances without Labels RSS 2021 DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting RSS 2021 Angular Visual Hardness ICML 2020 Curriculum By Smoothing NIPS 2020 Causal Discovery in Physical Systems from Videos NIPS 2020 OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation UAI 2020 Counterfactual Data Augmentation using Locally Factored Dynamics NIPS 2020 Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion CORL 2020 Semi-Supervised StyleGAN for Disentanglement Learning ICML 2020 Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration CVPR 2019 Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation CORL 2019 AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers CORL 2019 Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos CVPR 2018 Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision RSS 2018 ROBOTURK: A Crowdsourcing Platform for Robotic Skill Learning through Imitation CORL 2018