Lune

Profiles2019-2026

Hanwang Zhang

Nanyang Technological University

81Papers
41Last author
156Unique co-authors
0First author
0Solo

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

Recent papers81

  1. Real-Time Motion-Controllable Autoregressive Video DiffusionAuthor 8 of 8ICLR 2026 · 10 citations
  2. DEPO: Dual-Efficiency Preference Optimization for LLM AgentsAuthor 6 of 8AAAI 2026 · 2 citations
  3. DeepAlign: Mitigating Modality Conflict through Modality-Specific AlignmentAuthor 5 of 6CVPR 2026
  4. Object Fusion via Diffusion Time-step for Customized Image Editing with Single ExampleAuthor 4 of 5AAAI 2026
  5. Co-Reinforcement Learning for Unified Multimodal Understanding and GenerationAuthor 4 of 5NeurIPS 2025 · 15 citations
  6. Unsupervised Visual Chain-of-Thought Reasoning via Preference OptimizationAuthor 4 of 4ICCV 2025 · 3 citations
  7. SGDiff: Scene Graph Guided Diffusion Model for Image Collaborative SegCaptioningAuthor 3 of 7AAAI 2025 · 2 citations
  8. AnyEdit: Mastering Unified High-Quality Image Editing for Any IdeaAuthor 9 of 10CVPR 2025
  9. CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual InteractionAuthor 7 of 7CVPR 2025
  10. Generative Multimodal Pretraining with Discrete Diffusion Timestep TokensAuthor 9 of 9CVPR 2025
  11. Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual SceneAuthor 6 of 7CVPR 2025
  12. On Path to Multimodal Generalist: General-Level and General-BenchAuthor 32 of 32ICML 2025
  13. Project-Probe-Aggregate: Efficient Fine-Tuning for Group RobustnessAuthor 3 of 4CVPR 2025
  14. Towards Semantic Equivalence of Tokenization in Multimodal LLMAuthor 5 of 7ICLR 2025
  15. Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, EditingAuthor 3 of 7NeurIPS 2024 · 100 citations
  16. Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias CorrectingAuthor 6 of 6NeurIPS 2024 · 36 citations
  17. Exploring Diffusion Time-steps for Unsupervised Representation LearningAuthor 6 of 6ICLR 2024 · 33 citations
  18. Towards Unified Multimodal Editing with Enhanced Knowledge CollaborationAuthor 8 of 9NeurIPS 2024 · 27 citations
  19. Unified Generative and Discriminative Training for Multi-modal Large Language ModelsAuthor 9 of 10NeurIPS 2024 · 19 citations
  20. Action Imitation in Common Action Space for Customized Action Image SynthesisAuthor 11 of 13NeurIPS 2024 · 17 citations
  21. Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling PriorAuthor 5 of 5CVPR 2024 · 15 citations
  22. Lever LM: Configuring In-Context Sequence to Lever Large Vision Language ModelsAuthor 7 of 7NeurIPS 2024 · 13 citations
  23. MGNet: Learning Correspondences via Multiple GraphsAuthor 3 of 4AAAI 2024 · 12 citations
  24. Dual-Perspective Knowledge Enrichment for Semi-supervised 3D Object DetectionAuthor 5 of 5AAAI 2024 · 11 citations
  25. Robust Fine-tuning of Zero-shot Models via Variance ReductionAuthor 3 of 3NeurIPS 2024 · 9 citations
  26. Selective Vision-Language Subspace Projection for Few-shot CLIPAuthor 6 of 6ACM MM 2024 · 8 citations
  27. Diffusion Time-step Curriculum for One Image to 3D GenerationAuthor 6 of 6CVPR 2024 · 7 citations
  28. Discriminative Probing and Tuning for Text-to-Image GenerationAuthor 4 of 6CVPR 2024 · 7 citations
  29. Doubly Abductive Counterfactual Inference for Text-Based Image EditingAuthor 3 of 6CVPR 2024 · 7 citations
  30. Few-Shot Learner Parameterization by Diffusion Time-StepsAuthor 4 of 5CVPR 2024 · 7 citations

Showing the 30 most recent indexed papers.

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