Gongfan Fang

12

Papers

407

Total Citations

1

Affiliations

Affiliations

National University of Singapore

Papers (12)

DeepCache: Accelerating Diffusion Models for Free

dKV-Cache: The Cache for Diffusion Language Models

Thinkless: LLM Learns When to Think

VeriThinker: Learning to Verify Makes Reasoning Model Efficient

NeurIPS 2025arXiv

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Diffusion Model is Effectively Its Own Teacher

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

TinyFusion: Diffusion Transformers Learned Shallow

DepGraph: Towards Any Structural Pruning

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Structural Pruning for Diffusion Models

LLM-Pruner: On the Structural Pruning of Large Language Models