Lune

Profiles2021-2026ORCID 0000-0001-5866-2283

Huaibo Huang

University of Chinese Academy of Sciences

28Papers
4Last author
33Unique co-authors
1First author
0Solo

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

Recent papers28

  1. Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative ModelsAuthor 5 of 6CVPR 2026 · 8 citations
  2. T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree SearchAuthor 7 of 7AAAI 2026 · 2 citations
  3. Random Wins All: Rethinking Grouping Strategies for Vision TokensAuthor 3 of 3CVPR 2026 · 1 citation
  4. Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super ResolutionAuthor 2 of 6ICML 2026
  5. Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D GenerationAuthor 5 of 5CVPR 2026
  6. Towards Fine-Grained Attribution: Instance-Aware Preference Optimization for Aligning Diffusion ModelsAuthor 5 of 6CVPR 2026
  7. Rectifying Magnitude Neglect in Linear AttentionAuthor 2 of 4ICCV 2025 · 14 citations
  8. DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion ModelingAuthor 6 of 9NeurIPS 2025 · 8 citations
  9. Vision Transformer with Sparse Scan PriorAuthor 3 of 3ACM MM 2025 · 2 citations
  10. Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision TokensAuthor 2 of 4ICCV 2025 · 1 citation
  11. Breaking the Low-Rank Dilemma of Linear AttentionAuthor 2 of 3CVPR 2025
  12. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMsAuthor 7 of 9ICLR 2025
  13. DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset CurationAuthor 3 of 7NeurIPS 2024 · 81 citations
  14. FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMsAuthor 3 of 9ACM MM 2024 · 46 citations
  15. Heterogeneous Test-Time Training for Multi-Modal Person Re-identificationAuthor 2 of 4AAAI 2024 · 22 citations
  16. Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content GenerationAuthor 5 of 6NeurIPS 2024 · 10 citations
  17. ZePo: Zero-Shot Portrait Stylization with Faster SamplingAuthor 2 of 6ACM MM 2024 · 6 citations
  18. Visual Anchors Are Strong Information Aggregators For Multimodal Large Language ModelAuthor 5 of 6NeurIPS 2024 · 5 citations
  19. Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image RestorationAuthor 2 of 5CVPR 2024
  20. RMT: Retentive Networks Meet Vision TransformersAuthor 2 of 5CVPR 2024
  21. Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation TransformerAuthor 3 of 5CVPR 2024
  22. Lightweight Vision Transformer with Bidirectional InteractionAuthor 2 of 4NeurIPS 2023 · 59 citations
  23. Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal ClassificationAuthor 3 of 6NeurIPS 2023 · 30 citations
  24. Pluralistic Aging Diffusion AutoencoderAuthor 3 of 5ICCV 2023 · 25 citations
  25. Rethinking Image Cropping: Exploring Diverse Compositions from Global ViewsAuthor 2 of 4CVPR 2022 · 19 citations
  26. Artistic Style Discovery with Independent ComponentsAuthor 3 of 6CVPR 2022 · 16 citations
  27. Information Bottleneck Disentanglement for Identity SwappingAuthor 2 of 5CVPR 2021
  28. Memory Oriented Transfer Learning for Semi-Supervised Image DerainingAuthor 1 of 3CVPR 2021
Dusk over the sea between two cliffs drawn in fine vertical lines