← Search

Shangpin Peng

2 accepted papers

2026

Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs

ICLR 2026poster

Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based methods typically treat all preference pairs equally, overlooking substantial variations in data quality and learni…

Cited by 0SourceScholar
2025

Mitigating Object Hallucinations via Sentence-Level Early Intervention

ICCV 2025poster

Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur prohibitive computational costs or introduce distribution misma…