InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models Paper • 2512.08829 • Published 20 days ago • 18
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published Aug 25 • 211
InternVL3.5 Collection This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28 • 103
4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture Paper • 2507.05163 • Published Jul 7 • 41
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving Paper • 2506.08052 • Published Jun 9 • 1