10 papers
Xiaomi-GUI-0 Technical Report
Wanxia Cao, Chengzhen Duan, Pei Fu +29
Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, tex…
Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
Baoteng Li, Xianghao Zang, Xinran Wang +8
Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimi…
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
YuXin Song, Yu Lu, Haoyuan Sun +6
Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for…
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
Yifu Luo, Haoyuan Sun, Xinhao Hu +12
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is h…
Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
Yifu Luo, Xinhao Hu, Keyu Fan +6
Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or aut…
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
Kai Qin, Jiaqi Wu, Jianxiang He +8
As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM un…
The Hidden Link Between RLHF and Contrastive Learning
Xufei Lv, Kehai Chen, Haoyuan Sun +3
Alignment of large language models (LLMs) with human values has recently garnered significant attention, with prominent examples including the canonical yet costly Reinforcement Le…
Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
Haoyuan Sun, Jiaqi Wu, Bo Xia +7
Standing in 2025, at a critical juncture in the pursuit of Artificial General Intelligence (AGI), reinforcement fine-tuning (RFT) has demonstrated significant potential in enhancin…
Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through -divergence Minimization
Haoyuan Sun, Bo Xia, Yongzhe Chang +1
Direct Preference Optimization (DPO) has recently expanded its successful application from aligning large language models (LLMs) to aligning text-to-image models with human prefere…
A Method on Searching Better Activation Functions
Haoyuan Sun, Zihao Wu, Bo Xia +5
The success of artificial neural networks (ANNs) hinges greatly on the judicious selection of an activation function, introducing non-linearity into network and enabling them to mo…