2.4k citations
- Beijing Academy of Artificial IntelligenceCN102 papers
- Shanghai Jiao Tong UniversityCN46 papers
- Chinese University of Hong KongHK26 papers
- Tsinghua UniversityCN25 papers
- Fudan UniversityCN21 papers
- Group Sense (China)CN17 papers
- Northwestern Polytechnical UniversityCN14 papers
- ShangHai JiAi Genetics & IVF InstituteCN14 papers
- University of Science and Technology of ChinaCN14 papers
- University of Hong KongHK13 papers
- Peking UniversityCN11 papers
- Tongji UniversityCN11 papers
68 papers · 1 filter
OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching
Minghao Liu, Tutian Tang
Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking signals. Existing approaches are…
DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse
Yuyang Chen, Runxin Zhong, Zan Zong +3
Recent advances in AI-generated content have driven widespread adoption of Diffusion Transformers (DiTs) for high-resolution, long-duration content generation. While parallelizatio…
Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
Haifeng Huang, Yilun Chen, Zehan Wang +2
Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object…
MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration
Jiahui Peng, He Yao, Jingwen Li +9
Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignmen…
SS4D: Native 4D Generative Model via Structured Spacetime Latents
Zhibing Li, Mengchen Zhang, Tong Wu +3
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimi…
BrepLLM: Enabling Large Language Models to Understand Boundary Representations
Liyuan Deng, Hao Guo, Yongkang Dai +5
Current token-sequence-based Large Language Models (LLMs) struggle to directly process 3D Boundary Representation (B-rep) models that contain complex geometric and topological info…