News

Jul 09, 2026 We released OPSD-V, an on-policy self-distillation project for post-training few-step autoregressive video generators.
Jun 30, 2026 LACON: Training Text-to-Image Model from Uncurated Data is accepted to ECCV 2026.
Jun 02, 2026 We released DyaPlex, NVIDIA’s full-duplex speech-motion model for dyadic interaction.
May 26, 2026 We released the LongCat-Video-Avatar 1.5 Technical Report, an open-source audio-driven avatar video generation system.
Apr 09, 2026 UIKA was selected as a Highlight at CVPR 2026.
Feb 20, 2026 3 papers are accepted to CVPR 2026.
Jan 25, 2026 3 papers are accepted to ICLR 2026.
Sep 28, 2025 HeadArtist-VL is accepted to TPAMI 2025.
Aug 20, 2025 Follow-Your-Emoji-Faster is accepted to IJCV 2025.
Feb 26, 2025 AvatarArtist is accepted to CVPR 2025.
Jul 01, 2024 Follow-Your-Emoji paper is accepted to SIGGRAPH Asia 2024.
May 01, 2024 We released a survey paper:LLMs Meet Multimodal Generation and Editing: A Survey.
Mar 01, 2024 HeadArtist is accepted to SIGGRAPH 2024.
Feb 01, 2024 CAD is accepted to CVPR 2024.
Mar 01, 2023 XFormer is accepted to IJCAI 2023.
Feb 01, 2023 CLCAE is accepted to CVPR 2023.
Jan 01, 2023 Human MotionFormer is accepted to ICLR 2023.
Sep 01, 2022 FFCLIP is accepted to NeurIPS 2022 as spotlight.
Sep 01, 2022 I am starting my PhD at HKUST.