Sinan Fan

Orcid: 0009-0008-5186-8834

According to our database1, Sinan Fan authored at least 8 papers between 2025 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation.
CoRR, May, 2026

On the Step Length Confounding in LLM Reasoning Data Selection.
CoRR, April, 2026

Hallucination Begins Where Saliency Drops.
CoRR, January, 2026

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning.
CoRR, January, 2026

2025
MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models.
CoRR, July, 2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025


  Loading...