Repurposing Obsolete Representations for Post-Deployment Adaptation
Research
Research News
New papers, breakthroughs and academic AI research
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Research
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Research
4Director: Controlling Video World Models with Rigid 3D Geometry
Research
On Language Drift during RLVR Post-Training
Research
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
Research
HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
Research
Local Support Learning
Research
DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication
Research
HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution
Research
SoftServe: A Scalable Quasi-Newton Method for Deep Learning
Research
Embedding Prediction Helps Image Generation
Research