Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation
Research
Research News
New papers, breakthroughs and academic AI research
WorkGenesis: Building the Worlds That Teach Agents to Work
Research
RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context Failures
Research
ASH: Agents that Self-Hone in Long-Horizon Worlds
Research
Beyond the Current Scene: Event-Referential Grasping with Active View Selection
Research
Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video
Research
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
Research
Billiger.de Products: A Bilingual Entity Matching Benchmark
Research
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Research
dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale
Research
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
Research
MEMO: Multi-Level Entity-Aware Memory for Streaming Video Understanding
Research