Research Papers Institution
A leading comprehensive research university in Nanjing, China, whose NJU-LINK team leads this work.
Multimodal Models · Shanghai AI Laboratory
InternVideo3 is an 8B video model that scores 73.8 on Video-MME single-pass, then adds +2.7 from an agentic reasoning loop on top. M2LA attention holds 768K tokens on one H200 where the base OOMs at 512K.
Vision-Language-Action · CASIA
World Pilot adds two world-model priors to a VLA policy and hits 84.7% total success on LIBERO-Plus zero-shot OOD, up 4.2 over the ABot-M0 base, and the scene prior works even from a world model never action-trained.
Multimodal Models · Nanjing University
HYDRA-X unifies image and video tokenization in one ViT; tubelet attention and hierarchical temporal patchify improve DAVIS rFVD to 11.19 and editing overall to 4.34.
Video Generation · Nanjing University
CoVEBench: Can Video Editors Follow Complex Instructions? turns complex instruction following for video editing into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
AI Agents · Nanjing University
TELBench asks models to find the span that broke a 12-step research trajectory. DRIFT audits claims against evidence, lifting macro-F1 to 54.91% with Claude-Sonnet-4.6, up to 30 points over raw inspection.