3 papers
cs.LG2025
NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
Chongjie Si, Kangtao Lv, Jingjing Jiang +6
Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existin…
cs.CV2025
Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
Jingjing Jiang, Chongjie Si, Jun Luo +2
This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at sim…
cs.LG2025
Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades
Chongjie Si, Jingjing Jiang, Wei Shen
This paper presents a pioneering exploration of the mechanisms underlying large foundation models' (LFMs) weights, aiming to simplify AI research. Through extensive observation and…