TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision Paper • 2609.20869 • Published 14 days ago • 2
The information geometry of large language models is shared, learned, and controllable Paper • 2609.11063 • Published 19 days ago • 6
Towards Full Pipeline FP8 Reinforcement Learning for LLMs Paper • 2609.22870 • Published 10 days ago • 17
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents Paper • 2609.23377 • Published 9 days ago • 50
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion Paper • 2609.24220 • Published 8 days ago • 68
Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published 17 days ago • 224