Jin Ma
2 papers · Latest:
Natural Language Processing
Pause or Fabricate? Training Language Models for Grounded Reasoning
GRIL is a new RL framework that trains LLMs to detect incomplete information, pause, and clarify, reducing fabrication and improving grounded reasoning.
2604.19656
Computer VisionStreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
StreamCacheVGGT improves 3D geometry reconstruction from video streams by reimagining cache management with robust scoring and hybrid compression.
2604.15237
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.