collaborators

6 papers

cs.CV2026

Energy-Guided Flow Matching

Haoyang Tong, Yu He, Fang Li +6

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flo…

cs.CL2026

Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment

Yu Li, Xiuyu Li, Mingyang Yi +5

Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of "rollout then update", which inevitably results in off-policy training da…

cs.LG2026

Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning

Hu Xu, Zhaolong Xing, Congcong Liu +5

Calibration data are often treated as a minor implementation detail in post-training LLM pruning because averaged evaluations suggest only modest effects. We show that this conclus…

cs.CV2026

Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

Xiaolong Fu, Lichen Ma, Zipeng Guo +9

The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these ga…

cs.DB2026

OxyEcomBench: Benchmarking Multimodal Foundation Models across E-Commerce Ecosystems

Yong Liu, Ximan Liu, Guoqing Yang +5

LLMs and MLLMs have become indispensable tools across a wide range of applications. E-commerce, however, poses distinctive challenges -- including intricate domain knowledge, long-…

cs.CV2025

RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning

Zipeng Guo, Lichen Ma, Xiaolong Fu +13

In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional…