logo
today local_bar

Gongfan Fang

PhD student, National University of Singapore

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

2 papers
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Thinkless: LLM Learns When to Think
#4015 · Gongfan Fang, Xinyin Ma, Xinchao Wang

Large Reasoning Model learns when to think via Decoupled GRPO.
VeriThinker: Learning to Verify Makes Reasoning Model Efficient
#5413 · Zigeng Chen, Xinyin Ma, Gongfan Fang, Ruonan Yu, Xinchao Wang

We introduce VeriThinker, a simple yet effective approach for CoT compression.

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
dKV-Cache: The Cache for Diffusion Language Models
#1808 · Xinyin Ma, Runpeng Yu, Gongfan Fang, Xinchao Wang

We propose the delayed KV-Cache for diffusion language models.