Stoney Kang

sikang99's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 4 days ago

RealtimeWAM: One-Step Asynchronous World Action Models

Paper • 2610.06617 • Published 6 days ago • 24

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Paper • 2610.01762 • Published 10 days ago • 236

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 13 days ago • 202

upvoted 2 papers 9 days ago

In-Context Learning for Robots: Methods and Applications

Paper • 2609.36012 • Published 13 days ago • 322

World Observer: Joint Actor-Observer Generation for Persistent World Modeling

Paper • 2610.02162 • Published 10 days ago • 89

upvoted 3 papers 10 days ago

Context Language Models

Paper • 2609.37725 • Published 12 days ago • 46

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published 12 days ago • 39

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 13 days ago • 130

upvoted a paper 11 days ago

PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation

Paper • 2609.34759 • Published 13 days ago • 153

upvoted 6 papers 12 days ago

DroneWAM: Efficient World Action Model for Drone Visual Navigation

Paper • 2609.33148 • Published 14 days ago • 5

Precise Editing and Flexible Referencing for Interactable Worlds

Paper • 2609.34470 • Published 13 days ago • 20

Program-Verified Self-Evolution for Vision-Language Models

Paper • 2609.33855 • Published 14 days ago • 14

Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence

Paper • 2609.35432 • Published 13 days ago • 109

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

Paper • 2609.32862 • Published 15 days ago • 27

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon

Paper • 2609.35560 • Published 13 days ago • 31

upvoted a paper 13 days ago

TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations

Paper • 2609.30222 • Published 17 days ago • 14

upvoted a paper 16 days ago

Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI

Paper • 2609.24815 • Published 18 days ago • 12

upvoted 2 papers 18 days ago

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

Paper • 2609.10706 • Published 23 days ago • 29

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

Paper • 2609.18620 • Published 24 days ago • 24

upvoted a paper 23 days ago

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published 24 days ago • 78