Chufan Shi
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
arXiv 2026
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
arXiv 2024
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast
arXiv 2024
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
arXiv 2024
A Thorough Examination of Decoding Methods in the Era of LLMs
arXiv 2024
ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
arXiv 2024
A Survey on the Honesty of Large Language Models
arXiv 2024
LLM2: Let Large Language Models Harness System 2 Reasoning
arXiv 2024
Affiliations
Frequent co-authors
10from 8 papers