From the 23 of 454 papers with an AI index.
75 citations
- University of Chinese Academy of SciencesCN138 papers
- Peking UniversityCN123 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT110 papers
- University of Science and Technology of ChinaCN108 papers
- Université Paris-SaclayFR99 papers
- Rutherford Appleton LaboratoryGB98 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT97 papers
- Jagiellonian UniversityPL97 papers
- The Ohio State UniversityUS97 papers
- South China Normal UniversityCN95 papers
- AGH University of KrakowPL93 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di Roma IIT93 papers
22 papers · 1 filter
HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
Wenshuo Peng, Kaipeng Zhang
Video-to-audio (V2A) generation faces significant challenges in achieving precise temporal synchronization and high perceptual quality due to the complex, ambiguous relationship be…
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…
Nexus: Native Mesh Generation with Diffusion
Hanxiao Wang, Ying-Tian Liu, Yuan-Chen Guo +5
The paper introduces Nexus, a diffusion-based approach that generates high-quality triangle meshes by separately modeling vertex positions with an octree-based diffusion process an…
IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance
Gongyang Li, Zhen Bai, Runmin Cong +3
Existing Salient Object Detection in Optical Remote Sensing Image (ORSI-SOD) methods mainly adopt the static inference strategy, which uses fixed trained model parameters for salie…
OpenGlass: A Sensing-Computing Split Architecture for Local MLLM-Driven Real-Time Visual Assistance
Mengzhang Li, Yuan Yao
We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users. Cloud M…
2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Features
Ruihan Yu, Tianyu Huang, Jingwang Ling +1
2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-kn…