CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 7 days ago • 251
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo Paper • 2605.16257 • Published 5 days ago • 48
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published Feb 5 • 353
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery Paper • 2601.19325 • Published Jan 27 • 81
