← Search

Dong Fang

2 accepted papers

2026

Conditional Equivalence of DPO and RLHF: Assumptions, Failure Modes, and Provable Alignment

ICML 2026spotlight

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is _conditional_ rather than universal, depending on an implicit assumption frequent…

Cited by 0SourceScholar
2026

Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language Models

ICLR 2026poster

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking techniques can corrupt the reasoning flow by applying pseudo-random…

Cited by 0SourceScholar