4 papers
Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
Miaosen Zhang, Yishan Liu, Shuxia Lin +8
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL's use…
Distribution-Conditional Generation: From Class Distribution to Creative Generation
Fu Feng, Yucheng Xie, Xu Yang +2
Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize tr…
Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization
Huiyi Chen, Jiawei Peng, Kaihua Tang +2
In-context learning (ICL) enables Large Vision-Language Models (LVLMs) to adapt to new tasks without parameter updates, using a few demonstrations from a large support set. However…
Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
Fu Feng, Yucheng Xie, Xu Yang +2
``Creative'' remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concept…