Current World Models Lack a Persistent State Core
Paper • 2606.20545 • Published • 16
Lin Haotian
zhaoruo
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
Current World Models Lack a Persistent State Core upvoted a paper 17 days ago
Watch, Remember, Reason: Human-View Video Understanding with MLLMsOrganizations
None yet
upvoted a paper 9 days ago
upvoted a paper 17 days ago
upvoted a paper 27 days ago
upvoted a paper about 1 month ago
upvoted 9
papers 3 months ago
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
Paper • 2604.07966 • Published • 10
WildDet3D: Scaling Promptable 3D Detection in the Wild
Paper • 2604.08626 • Published • 248
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
Paper • 2604.04911 • Published • 36
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 329
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping
Paper • 2604.08364 • Published • 103
LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model
Paper • 2603.27449 • Published • 6
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 352
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 373
upvoted 3
papers 4 months ago
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Paper • 2603.04597 • Published • 211
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Paper • 2602.08354 • Published • 266
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 526