4 papers
ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels
Bingyang Wu, Chao Jin, Zili Zhang +6
LLMs scale Mixture-of-Experts (MoE) parameters for superior intelligence, but massive weights and dynamic computation impede efficient serving. Existing instance-level prefill-deco…
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
Zhang Li, Zhibo Lin, Qiang Liu +7
We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides,…
Heddle: A Distributed Orchestration System for Agentic RL Rollout
Zili Zhang, Yinmin Zhong, Chengxu Yang +5
Agentic Reinforcement Learning (RL) enables LLMs to solve complex tasks by alternating between a data-collection rollout phase and a policy training phase. During rollout, the agen…
Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization
Junjie Lu, Yuliang Liu, Chaofeng Qu +4
Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular,…