collaborators

7 papers

cs.LG2025

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…

cs.LG2025

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…

cs.SD2025

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

Chengyao Wang, Zhisheng Zhong, Bohao Peng +7

We present MGM-Omni, a unified Omni LLM for omni-modal understanding and expressive, long-horizon speech generation. Unlike cascaded pipelines that isolate speech synthesis, MGM-Om…

cs.LG2025

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Mingkang Zhu, Xi Chen, Zhongdao Wang +3

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Prox…

cs.CV2025

RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models

Yuqi Liu, Qin Jin, Tianyuan Qu +4

Understanding accurate atomic temporal event is essential for video comprehension. However, current video-language benchmarks often fall short to evaluate Large Multi-modal Models'…

cs.CV2025

Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation

Mingkang Zhu, Xi Chen, Zhongdao Wang +3

Recent diffusion model customization has shown impressive results in incorporating subject or style concepts with a handful of images. However, the modular composition of multiple…