Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics Paper • 2604.08503 • Published 3 days ago • 2
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published 3 days ago • 87
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 9 days ago • 347
UniRecGen: Unifying Multi-View 3D Reconstruction and Generation Paper • 2604.01479 • Published 11 days ago • 7
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published 13 days ago • 339
LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset Paper • 2603.23607 • Published 19 days ago • 18
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization Paper • 2603.19835 • Published 23 days ago • 330
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published 17 days ago • 153
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published Feb 13 • 216
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 263