Submitted by Hangjie Yuan 21 LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation DAMO Academy 1
Submitted by Tang 10 Few-Step Distillation for Text-to-Image Generation: A Practical Guide DAMO Academy 350 2
Submitted by Zeyu Zhang 7 BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation DAMO Academy 2
Submitted by taesiri 50 Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation DAMO Academy 119 2
Submitted by Siteng Huang 28 RynnVLA-002: A Unified Vision-Language-Action and World Model DAMO Academy 951 2
Submitted by Hangjie Yuan 38 UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback DAMO Academy 153 1
Submitted by Chenghao Xiao 106 Scaling Language-Centric Omnimodal Representation Learning DAMO Academy 38 4
Submitted by Siteng Huang 15 High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting DAMO Academy 56 2
Submitted by Siteng Huang 12 Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors DAMO Academy 28 3
Submitted by Hou Pong (Ken) Chan 114 Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning DAMO Academy 4