Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent Paper • 2411.02265 • Published 13 days ago • 23
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models Paper • 2409.17146 • Published Sep 25 • 101
DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation Paper • 2409.03755 • Published Sep 5 • 3
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution Paper • 2409.12961 • Published Sep 19 • 24
Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model Paper • 2408.00754 • Published Aug 1 • 21
Efficient Inference of Vision Instruction-Following Models with Elastic Cache Paper • 2407.18121 • Published Jul 25 • 16