Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation
Paper • 2408.11812 • Published • 6
Embodied AI
Embodiment enables interaction of model with environment. Key is to anticipate what change could've come with its current action.
-
-
WebArena: A Realistic Web Environment for Building Autonomous Agents
Paper • 2307.13854 • Published • 27 -
Agent Workflow Memory
Paper • 2409.07429 • Published • 32 -
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
Paper • 2409.08264 • Published • 48 -
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
Paper • 2408.06327 • Published • 17 -
Tree Search for Language Model Agents
Paper • 2407.01476 • Published • 1 -
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Paper • 2406.11896 • Published • 20 -
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Paper • 2405.10292 • Published • 2 -
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
Paper • 2409.10277 • Published • 1 -
UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity
Paper • 2409.04081 • Published • 3 -
Achieving Human Level Competitive Robot Table Tennis
Paper • 2408.03906 • Published • 28 -
Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation
Paper • 2409.09135 • Published • 2 -
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
Paper • 2409.12798 • Published • 1 -
The Rise and Potential of Large Language Model Based Agents: A Survey
Paper • 2309.07864 • Published • 8 -
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
Paper • 2409.12192 • Published • 4 -
MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling
Paper • 2409.16160 • Published • 34 -
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
Paper • 2410.02089 • Published • 13 -
Learning Evolving Tools for Large Language Models
Paper • 2410.06617 • Published • 2 -
Agent S: An Open Agentic Framework that Uses Computers Like a Human
Paper • 2410.08164 • Published • 26 -
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Paper • 2410.07484 • Published • 51 -
Augmented Physics: Creating Interactive and Embedded Physics Simulations from Static Textbook Diagrams
Paper • 2405.18614 • Published • 2 -
AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
Paper • 2410.13825 • Published • 1 -
TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
Paper • 2410.04221 • Published • 3 -
One Step Diffusion via Shortcut Models
Paper • 2410.12557 • Published • 1 -
LeLaN: Learning A Language-Conditioned Navigation Policy from In-the-Wild Videos
Paper • 2410.03603 • Published • 1 -
Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
Paper • 2408.16228 • Published • 1 -
OpenVLA: An Open-Source Vision-Language-Action Model
Paper • 2406.09246 • Published • 44 -
In-Context Learning Enables Robot Action Prediction in LLMs
Paper • 2410.12782 • Published • 1 -
AgentKit: Flow Engineering with Graphs, not Coding
Paper • 2404.11483 • Published • 2 -
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Paper • 2504.00906 • Published • 27 -
BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation
Paper • 2504.14538 • Published • 30 -
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
Paper • 2509.00997 • Published • 2 -
Social World Models
Paper • 2509.00559 • Published • 1 -
Dynamic Speculative Agent Planning
Paper • 2509.01920 • Published • 6 -
World-in-World: World Models in a Closed-Loop World
Paper • 2510.18135 • Published • 78 -
From Masks to Worlds: A Hitchhiker's Guide to World Models
Paper • 2510.20668 • Published • 8