3 papers
cs.LG2026
MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
Guangchen Lan, Sipeng Zhang, Tianle Wang +7
As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving perfor…
cs.CV2025
Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
Daoan Zhang, Guangchen Lan, Dong-Jun Han +8
Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffer…
cs.LG2025
Gradient Correction in Federated Learning with Adaptive Optimization
Evan Chen, Shiqiang Wang, Jianing Zhang +3
In federated learning (FL), model training performance is strongly impacted by data heterogeneity across clients. Client-drift compensation methods have recently emerged as a solut…