Lune

Profiles2024-2026ORCID 0000-0001-9572-2345

Hehe Fan

Zhejiang University

19Papers
6Last author
31Unique co-authors
0First author
0Solo

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

Recent papers19

  1. One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query RefinementAuthor 6 of 6ACL 2026 · 3 citations
  2. Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion modelsAuthor 4 of 5ICLR 2026 · 2 citations
  3. Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual CuesAuthor 3 of 3CVPR 2026 · 1 citation
  4. TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal EstimationAuthor 2 of 3ICML 2026 · 1 citation
  5. A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow MatchingAuthor 2 of 2ICML 2026
  6. Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical WorldAuthor 4 of 4ICLR 2026
  7. GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved FocusAuthor 3 of 4WWW 2026
  8. RegionSLM: Region-aware Question Answering on Document ScreenshotsAuthor 2 of 6SIGIR 2026
  9. Prototypical Calibrating Ambiguous Samples for Micro-Action RecognitionAuthor 7 of 8AAAI 2025 · 55 citations
  10. Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action RecognitionAuthor 6 of 7ACM MM 2025 · 23 citations
  11. InfiniDreamer: Arbitrarily Long Human Motion Generation Via Segment Score DistillationAuthor 3 of 3ICCV 2025 · 6 citations
  12. TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting PriorsAuthor 2 of 5ACM MM 2025 · 6 citations
  13. Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMsAuthor 9 of 9EMNLP Findings 2025 · 4 citations
  14. ZeroMamba: Exploring Visual State Space Model for Zero-Shot LearningAuthor 5 of 6AAAI 2025 · 4 citations
  15. OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing AgentsAuthor 6 of 7ICLR 2025
  16. Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D StructuresAuthor 4 of 5ICML 2025
  17. Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video DiffusionAuthor 3 of 4CVPR 2025
  18. Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition LearningAuthor 2 of 5ICML 2024 · 49 citations
  19. TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-AlignmentAuthor 2 of 5NeurIPS 2024 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines