Paper 'ConsisID' accepted by CVPR 2025 (Highlight, Top 3%)
Paper 'MagicTime' accepted by IEEE TPAMI 2025 and featured by University of Rochester News
Paper 'PromptLLM' accepted by IEEE TPAMI 2025
Paper 'MoE-LLaVA' accepted by IEEE TMM 2025
Paper 'TACO' accepted by EMNLP Main 2025
Papers 'OpenS2V-Nexus' and 'VideoRAG' accepted by NeurIPS 2025 (Main and D&B Track)
Survey 'Next-Gen AIGC' accepted by Frontiers of Computer Science 2025
Survey 'Medical LLM Survey' accepted by Nature Reviews Bioengineering 2025
Survey 'AR-Visual Survey' accepted by TMLR 2025
Two papers (1 Poster, 1 Spotlight) accepted by ICLR 2025
One paper accepted by AAAI 2025
One short paper accepted by COLING 2025
One paper accepted by EMNLP 2024 Findings
One Spotlight paper accepted by NeurIPS 2024 Datasets & Benchmarks Track
One paper accepted by ACL 2024 Findings
One paper accepted by ACM TIST 2024
One paper accepted by npj Digital Medicine (Impact Factor: 15.357) in 2024
One survey on camouflaged object detection accepted by CAAI Transactions on Intelligence Technology (IF: 8.4)
Released multiple open-source repositories and surveys: LatentCoT-Horizon, Awesome Autoregressive Models in Vision, ChronoMagic-Bench (benchmark for text-to-video generation), and MagicTime (metamorphic time-lapse video generation model)