9 papers
A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
Jianghan Shen, Siqi Luo, Yue Li +9
Policy gradient algorithms for language models optimize the same objective , which has exactly two factors: the trajectory probability…
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models
Siqi Luo, Jianghan Shen, Yi Xin +9
Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One prima…
LayerT2V: A Unified Multi-Layer Video Generation Framework
Guangzhao Li, Kangrui Cen, Baixuan Zhao +5
Text-to-video generation has advanced rapidly, but existing methods typically output only the final composited video and lack editable layered representations, limiting their use i…
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
Yi Xin, Jianjiang Yang, Siqi Luo +10
Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these mod…
Enhancing Test Time Adaptation with Few-shot Guidance
Siqi Luo, Yi Xin, Yuntao Du +3
Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Tim…
TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
Siqi Luo, Haoran Yang, Yi Xin +4
Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tu…