9 papers
Predicting LLM Output Length via Entropy-Guided Representations
Huanyi Xie, Yubin Chen, Liangyu Wang +2
The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to excessive padding in batched…
Evaluating Proactive Risk Awareness of Large Language Models
Xuan Luo, Yubin Chen, Zhiyu Hou +4
As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward antici…
SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents
Zhirui Zhang, Hongbo Zhang, Haoxiang Fei +11
Although large language models (LLMs) have demonstrated impressive coding capabilities, their ability to autonomously build production-scale software from explicit specifications r…
Evaluating Frontier LLMs on PhD-Level Mathematical Reasoning: A Benchmark on a Textbook in Theoretical Computer Science about Randomized Algorithms
Yang Cao, Yubin Chen, Xuyang Guo +4
The rapid advancement of large language models (LLMs) has led to significant breakthroughs in automated mathematical reasoning and scientific discovery. Georgiev, Gmez-Serran…
GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
Xin Li, Qizhi Chu, Yubin Chen +7
Graphs are widely used for modeling relational data in real-world scenarios, such as social networks and urban computing. Existing LLM-based graph analysis approaches either integr…
Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria
Yang Cao, Yubin Chen, Zhao Song +1
Generative modelling has seen significant advances through simulation-free paradigms such as Flow Matching, and in particular, the MeanFlow framework, which replaces instantaneous…