Lune

Profiles2023-2026

Gongfan Fang

National University of Singapore

17Papers
0Last author
12Unique co-authors
6First author
0Solo

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

Recent papers17

  1. dParallel: Learnable Parallel Decoding for dLLMsAuthor 2 of 5ICLR 2026 · 64 citations
  2. Invisible Safety Threat: Malicious Finetuning for LLM via SteganographyAuthor 3 of 4ICLR 2026 · 4 citations
  3. CoT-Valve: Length-Compressible Chain-of-Thought TuningAuthor 4 of 5ACL 2025 · 162 citations
  4. Thinkless: LLM Learns When to ThinkAuthor 1 of 3NeurIPS 2025 · 128 citations
  5. VeriThinker: Learning to Verify Makes Reasoning Model EfficientAuthor 3 of 5NeurIPS 2025 · 30 citations
  6. Collaborative Decoding Makes Visual Auto-Regressive Modeling EfficientAuthor 3 of 4CVPR 2025
  7. Diffusion Model is Effectively Its Own TeacherAuthor 4 of 5CVPR 2025
  8. TinyFusion: Diffusion Transformers Learned ShallowAuthor 1 of 4CVPR 2025
  9. Learning-to-Cache: Accelerating Diffusion Transformer via Layer CachingAuthor 2 of 4NeurIPS 2024 · 167 citations
  10. DeepCache: Accelerating Diffusion Models for FreeAuthor 2 of 3CVPR 2024 · 87 citations
  11. MaskLLM: Learnable Semi-Structured Sparsity for Large Language ModelsAuthor 1 of 8NeurIPS 2024 · 72 citations
  12. AsyncDiff: Parallelizing Diffusion Models by Asynchronous DenoisingAuthor 3 of 5NeurIPS 2024 · 33 citations
  13. Remix-DiT: Mixing Diffusion Transformers for Multi-Expert DenoisingAuthor 1 of 3NeurIPS 2024 · 7 citations
  14. SlimSAM: 0.1% Data Makes Segment Anything SlimAuthor 2 of 4NeurIPS 2024
  15. LLM-Pruner: On the Structural Pruning of Large Language ModelsAuthor 2 of 3NeurIPS 2023 · 994 citations
  16. Structural Pruning for Diffusion ModelsAuthor 1 of 3NeurIPS 2023 · 257 citations
  17. DepGraph: Towards Any Structural PruningAuthor 1 of 5CVPR 2023
Dusk over the sea between two cliffs drawn in fine vertical lines