news

Mar 12, 2026 Congratulations! Our paper RCTS: Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger has been marked as ICML 2025 Spotlight Paper! 😮
Mar 12, 2026 Congratulations! Our paper R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs has been accepted by CVPR!
Aug 28, 2025 Our paper R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs is now available on arXiv! R-4B achieves SOTA across 25 benchmarks.
May 21, 2025 Our large-scale model paper Hunyuan-TurboS is now available, ranking top 7 on LMSYS Chatbot Arena!
Sep 06, 2024 Our paper Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis is now available on arXiv!
Apr 06, 2024 Congratulations on our paper Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation being marked as CVPR 2024 Highlight Paper! 😮
Feb 29, 2024 Congratulations on our paper Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation being accepted by CVPR 2024! 😄
Oct 15, 2023 Congratulations on our paper Continual Semantic Segmentation via Scalable Contrastive Clustering and Background Diversity being accepted by IEEE ICDM 2023!😄