Lune

Profiles2020-2026

Yulun Zhang

Shanghai Jiao Tong University

63Papers
25Last author
63Unique co-authors
2First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers63

  1. Quantized Visual Geometry Grounded TransformerAuthor 9 of 11ICLR 2026 · 17 citations
  2. Grounding-IQA: Grounding Multimodal Language Model for Image Quality AssessmentAuthor 10 of 10ICLR 2026 · 12 citations
  3. Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language ModelsAuthor 6 of 6ICLR 2026 · 11 citations
  4. QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention SparsificationAuthor 9 of 11ICLR 2026 · 8 citations
  5. FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion DeblurringAuthor 6 of 6ICLR 2026 · 5 citations
  6. RobuQ: Pushing DiTs to W1.58A2 via Robust Activation QuantizationAuthor 7 of 7ICML 2026 · 5 citations
  7. PT2^2-LLM: Post-Training Ternarization for Large Language ModelsAuthor 9 of 9ICLR 2026 · 4 citations
  8. Fast-SAM3D: 3Dfy Anything in Images but FasterAuthor 10 of 13ICML 2026 · 2 citations
  9. Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-ResolutionAuthor 6 of 6ICML 2026 · 2 citations
  10. DenoiseGS: Gaussian Reconstruction Model for Burst DenoisingAuthor 3 of 3CVPR Findings 2026 · 1 citation
  11. Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image CompressionAuthor 6 of 6AAAI 2026 · 1 citation
  12. VEQ: Modality-Adaptive Quantization for MoE Vision-Language ModelsAuthor 6 of 6ICML 2026 · 1 citation
  13. AdaSVD: Singular Value Decomposition with Adaptive Mechanisms for Large Multimodal ModelsAuthor 7 of 8CVPR 2026
  14. Condition Number Based Low-Bit Quantization for Image Super-ResolutionAuthor 8 of 8ICML 2026
  15. InfVSR: Toward Consistency-Driven Streaming Generative Video Super-ResolutionAuthor 8 of 8ICML 2026
  16. Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light EnhancementAuthor 5 of 6ICML 2026
  17. LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-ResolutionAuthor 8 of 8ICML 2026
  18. QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-ResolutionAuthor 6 of 6AAAI 2026
  19. SODiff:Semantic-Oriented Diffusion Model for JPEG Compression Artifacts RemovalAuthor 6 of 6AAAI 2026
  20. DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-ResolutionAuthor 7 of 7NeurIPS 2025 · 31 citations
  21. OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratesAuthor 9 of 9NeurIPS 2025 · 25 citations
  22. QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video GenerationAuthor 4 of 7ICCV 2025 · 20 citations
  23. Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion DiscriminatorAuthor 6 of 8NeurIPS 2025 · 18 citations
  24. Compression-Aware One-Step Diffusion Model for JPEG Artifact RemovalAuthor 5 of 5ICCV 2025 · 5 citations
  25. HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt GuidanceAuthor 7 of 8NeurIPS 2025 · 5 citations
  26. ARB-LLM: Alternating Refined Binarizations for Large Language ModelsAuthor 9 of 10ICLR 2025
  27. BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-ResolutionAuthor 8 of 8ICML 2025
  28. DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup TablesAuthor 3 of 6CVPR 2025
  29. Human Body Restoration with One-Step Diffusion Model and A New BenchmarkAuthor 6 of 7ICML 2025
  30. One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationAuthor 5 of 5ICML 2025

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines