11 papers
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Kaixin Ding, Yang Zhou, Xi Chen +5
Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performa…
Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
Rongkun Zheng, Lu Qi, Xi Chen +3
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires pre…
Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
Mingkang Zhu, Xi Chen, Bei Yu +2
Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems, and reinforcement learning (RL) has become a key…
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
Mingkang Zhu, Xi Chen, Bei Yu +2
Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs w…
Enhancing LLM Knowledge Learning through Generalization
Mingkang Zhu, Xi Chen, Zhongdao Wang +3
As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge.…
FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
Xi Chen, Hengshuang Zhao
Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often s…