PPaperPicks

Jingwen He

9 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
  2. Imagine360: Immersive 360 Video Generation from Perspective Anchor
  3. Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation
  4. MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation
  5. ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance
  6. ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
  7. DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior
  8. Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
  9. Towards Real-world Video Face Restoration: A New Benchmark