Skip to content
IFAI

复旦大学

Company3 stories

  1. Open sourceReach 48

    Fudan and Tencent open-source Prism for native 2K video-audio generation

    Researchers from Fudan University, Tencent Hunyuan, and Zhejiang University just open-sourced Prism, a framework designed for native 2K joint video-audio generation. Instead of wasting compute across every pixel, Prism uses dynamic sparse attention to focus on sound-producing and rapidly changing visual regions, speeding up training by 2.5x while keeping audio and video tightly synchronized. Preview weights and inference scripts are already available on Hugging Face.

  2. Open sourceReach 48

    Fudan's Hallo-Live streams real-time AI avatars from text

    Fudan researchers just unveiled Hallo-Live, a streaming framework that synthesizes synchronized talking-head video and speech directly from text. Powered by dual-stream diffusion and preference-guided distillation, it hits 20.38 FPS with a 0.94-second latency on two NVIDIA H200 GPUs. It clears a major bottleneck for interactive, real-time digital humans.

  3. Open sourceReach 48

    GlyphPrinter fixes AI image text rendering

    Researchers just released GlyphPrinter, an open-source framework designed to stop AI from botching text in generated images. Built on FLUX.1-dev with region-level preference optimization, it accurately renders notoriously difficult Chinese, Japanese, Korean, and Thai glyphs, along with realistic carvings and symbols.