Abhinav Gupta

Hierarchical Reason-of-Contact Detection in Retail Banking Customer Interactions via LLM-Driven Taxonomy Induction ACL 2026 Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation CORL 2025 AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization ACL 2025 HRP: Human affordances for Robotic Pre-training RSS 2024 Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning ECCV 2024 Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation ECCV 2024 Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling ICML 2024 G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis CVPR 2024 Legolas: Deep Leg-Inertial Odometry CORL 2024 DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset RSS 2024 Affordance Diffusion: Synthesizing Hand-Object Interactions CVPR 2023 An Unbiased Look at Datasets for Visuo-Motor Pre-Training CORL 2023 Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations ICCV 2023 Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips ICCV 2023 Learning Multi-Objective Curricula for Robotic Policy Learning CORL 2022 The Challenges of Continuous Self-Supervised Learning ECCV 2022 Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction CVPR 2022 Learning State-Aware Visual Representations from Audible Interactions NIPS 2022 Last-Mile Embodied Visual Navigation CORL 2022 What's in Your Hands? 3D Reconstruction of Generic Objects in Hands CVPR 2022 R3M: A Universal Visual Representation for Robot Manipulation CORL 2022 Human-to-Robot Imitation in the Wild RSS 2022 Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation? L4DC 2022 The Unsurprising Effectiveness of Pre-Trained Vision Models for Control ICML 2022 Learn-To-Race: A Multimodal Control Environment for Autonomous Racing ICCV 2021 PixelTransformer: Sample Conditioned Signal Generation ICML 2021 Dynamic population-based meta-learning for multi-agent communication with natural language NIPS 2021 No RL, No Simulation: Learning to Navigate without Navigating NIPS 2021 Shelf-Supervised Mesh Prediction in the Wild CVPR 2021 Supervoxel Attention Graphs for Long-Range Video Modeling WACV 2021 Wanderlust: Online Continual Object Detection in the Real World ICCV 2021 KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA CVPR 2021 Interesting Object, Curious Agent: Learning Task-Agnostic Exploration NIPS 2021 Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning ICLR 2021 Hierarchical Neural Dynamic Policies RSS 2021 Audio-Visual Floorplan Reconstruction ICCV 2021 The Functional Correspondence Problem ICCV 2021 Where2Act: From Pixels to Actions for Articulated 3D Objects ICCV 2021 A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation CORL 2021 ReSkin: versatile, replaceable, lasting tactile skins CORL 2021 Robots on Demand: A Democratized Robotics Research Cloud CORL 2021 Neural Topological SLAM for Visual Navigation CVPR 2020 Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping CORL 2020 Visual Imitation Made Easy CORL 2020 DeepMPCVS: Deep Model Predictive Control for Visual Servoing CORL 2020 Transformers for One-Shot Visual Imitation CORL 2020 Compositionality and Capacity in Emergent Languages ACL 2020 Swoosh! Rattle! Thump! - Actions that Sound RSS 2020 Learning Robot Skills with Temporal Variational Inference ICML 2020 Intrinsic Motivation for Encouraging Synergistic Behavior ICLR 2020 Discovering Motor Programs by Recomposing Demonstrations ICLR 2020 Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning ICLR 2020 Learning To Explore Using Active Neural SLAM ICLR 2020 Dynamics-Aware Embeddings ICLR 2020 Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases NIPS 2020 Object Goal Navigation using Goal-Oriented Semantic Exploration NIPS 2020 Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects CVPR 2020 Articulation-Aware Canonical Surface Mapping CVPR 2020 ClusterFit: Improving Generalization of Visual Representations CVPR 2020 Neural Dynamic Policies for End-to-End Sensorimotor Learning NIPS 2020 See, Hear, Explore: Curiosity via Audio-Visual Association NIPS 2020 Semantic Curiosity for Active Visual Learning ECCV 2020 Aligning Videos in Space and Time ECCV 2020 Object-centric Forward Modeling for Model Predictive Control CORL 2019 Canonical Surface Mapping via Geometric Cycle Consistency ICCV 2019 Seeded self-play for language learning EMNLP 2019 Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies ICLR 2019 3D-RelNet: Joint Object and Relational Network for 3D Prediction ICCV 2019 Learning Exploration Policies for Navigation ICLR 2019 Environment Probing Interaction Policies ICLR 2019 Task-Driven Modular Networks for Zero-Shot Compositional Learning ICCV 2019 Compositional Video Prediction ICCV 2019 Scaling and Benchmarking Self-Supervised Visual Representation Learning ICCV 2019 Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller NIPS 2019 Visual Semantic Navigation using Scene Priors ICLR 2019 Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces ICLR 2019 Self-Supervised Exploration via Disagreement ICML 2019 Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation CORL 2018 Beyond Grids: Learning Graph Representations for Visual Recognition NIPS 2018 Hardware Conditioned Policies for Multi-Robot Transfer Learning NIPS 2018 Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias NIPS 2018 Learning by Asking Questions CVPR 2018 Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs CVPR 2018 Iterative Visual Reasoning Beyond Convolutions CVPR 2018 Actor and Observer: Joint Modeling of First and Third-Person Videos CVPR 2018 Non-Local Neural Networks CVPR 2018 Interpretable Intuitive Physics Model ECCV 2018 Videos as Space-Time Region Graphs ECCV 2018 Compositional Learning for Human Object Interaction ECCV 2018 Spatial Memory for Context Reasoning in Object Detection ICCV 2017 The Pose Knows: Video Forecasting by Generating Pose Futures ICCV 2017 What Actions Are Needed for Understanding Human Actions in Videos? ICCV 2017 Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection ICCV 2017 Transitive Invariance for Self-Supervised Visual Representation Learning ICCV 2017 Revisiting Unreasonable Effectiveness of Data in Deep Learning Era ICCV 2017 Visual Semantic Planning Using Deep Successor Representations ICCV 2017 The More You Know: Using Knowledge Graphs for Image Classification CVPR 2017 A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection CVPR 2017 Binge Watching: Scaling Affordance Learning From Sitcoms CVPR 2017 From Red Wine to Red Tomato: Composition With Context CVPR 2017 ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification CVPR 2017 Learning From Noisy Large-Scale Datasets With Minimal Supervision CVPR 2017 Asynchronous Temporal Fields for Action Recognition CVPR 2017 What's in a Question: Using Visual Questions as a Form of Supervision CVPR 2017 Robust Adversarial Reinforcement Learning ICML 2017 Training Region-Based Object Detectors With Online Hard Example Mining CVPR 2016 Marr Revisited: 2D-3D Alignment via Surface Normal Prediction CVPR 2016 Cross-Stitch Networks for Multi-Task Learning CVPR 2016 Actions ~ Transformations CVPR 2016 3D Shape Attributes CVPR 2016 Webly Supervised Learning of Convolutional Networks ICCV 2015 Unsupervised Visual Representation Learning by Context Prediction ICCV 2015 Single Image 3D Without a Single 3D Image ICCV 2015 Designing Deep Networks for Surface Normal Estimation CVPR 2015 Unsupervised Learning of Visual Representations Using Videos ICCV 2015 Dense Optical Flow Prediction From a Static Image ICCV 2015 Sense Discovery via Co-Clustering on Images and Text CVPR 2015 Patch to the Future: Unsupervised Visual Prediction CVPR 2014 Enriching Visual Knowledge Bases via Object Discovery and Segmentation CVPR 2014 Representing Videos Using Mid-level Discriminative Patches CVPR 2013 Mid-level Visual Element Discovery as Discriminative Mode Seeking NIPS 2013 Building Part-Based Object Detectors via 3D Geometry ICCV 2013 Data-Driven 3D Primitives for Single Image Understanding ICCV 2013 NEIL: Extracting Visual Knowledge from Web Data ICCV 2013 Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces NIPS 2010 A ``Shape Aware'' Model for semi-supervised Learning of Objects and its Context NIPS 2008