Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting
Paper • 2303.14100 • Published
Animesh Garg
animesh-garg
AI & ML interests
Reinforcement Learning, Robotics Foundation Models, Causality
Recent Activity
authored a paper 16 days ago
Errors are Useful Prompts: Instruction Guided Task Programming with
Verifier-Assisted Iterative Prompting authored a paper 16 days ago
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and
Stochastic Transitions authored a paper 16 days ago
A Persistent Spatial Semantic Representation for High-level Natural
Language Instruction ExecutionOrganizations
None yet
authored 16
papers 16 days ago
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Paper • 2106.04165 • Published
A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution
Paper • 2107.05612 • Published
RePLan: Robotic Replanning with Perception and Language Models
Paper • 2401.04157 • Published • 3
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
Paper • 2203.15086 • Published
Value Gradient weighted Model-Based Reinforcement Learning
Paper • 2204.01464 • Published
ProgPrompt: Generating Situated Robot Task Plans using Large Language Models
Paper • 2209.11302 • Published
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
Paper • 1810.10191 • Published • 1
AnyPlace: Learning Generalized Object Placement for Robot Manipulation
Paper • 2502.04531 • Published
Scaling Laws in Scientific Discovery with AI and Robot Scientists
Paper • 2503.22444 • Published • 12
SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation
Paper • 2410.18065 • Published
Angular Visual Hardness
Paper • 1912.02279 • Published • 1
OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation
Paper • 2506.01196 • Published
Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
Paper • 2511.04831 • Published
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
Paper • 2603.17117 • Published • 87
Modular Action Concept Grounding in Semantic Video Prediction
Paper • 2011.11201 • Published