3 papers
cs.AI2025
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
Yifan Wang, Runjin Chen, Bolian Li +7
Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effecti…
cs.CL2025
Entropy-Based Adaptive Weighting for Self-Training
Xiaoxuan Wang, Yihe Deng, Mingyu Derek Ma +1
The mathematical problem-solving capabilities of large language models have become a focal point of research, with growing interests in leveraging self-generated reasoning paths as…
cs.CV2025
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
Yihe Deng, Hritik Bansal, Fan Yin +3
We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gai…