BadWAM: When World-Action Models Dream Right but Act Wrong
Paper • 2607.15207 • Published • 44
Stoney Kang
sikang99
AI & ML interests
Remote Control based on Vision
Recent Activity
upvoted a paper about 17 hours ago
BadWAM: When World-Action Models Dream Right but Act WrongOrganizations
upvoted a paper about 17 hours ago
upvoted 3
papers 1 day ago
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Paper • 2607.13285 • Published • 196
AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling
Paper • 2607.10995 • Published • 7
RoboTTT: Context Scaling for Robot Policies
Paper • 2607.15275 • Published • 16
upvoted 5
papers 3 days ago
LightMem-Ego: Your AI Memory for Everyday Life
Paper • 2607.11487 • Published • 44
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Paper • 2607.11643 • Published • 39
ABot-N1: Toward a General Visual Language Navigation Foundation Model
Paper • 2607.10383 • Published • 98
A Sovereign, Open-Source Foundation Model for German and English
Paper • 2607.09424 • Published • 8
Multi-Agent LLMs Fail to Explore Each Other
Paper • 2607.11250 • Published • 14
upvoted 2
papers 4 days ago
upvoted 5
papers 9 days ago
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
Paper • 2607.02515 • Published • 18
From Foundation to Application: Improving VLA Models in Practice
Paper • 2607.06403 • Published • 20
Gemma 4 Technical Report
Paper • 2607.02770 • Published • 67
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Paper • 2607.06559 • Published • 94
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
Paper • 2607.06558 • Published • 78
upvoted 2
papers 10 days ago
upvoted 2
papers 11 days ago