11 citations · 12 across the 13 of their papers we have counts for
5 papers · 1 filter
More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight
Yuchen Han, Cheng Yan, Wuyang Zhang
Pre-execution oversight is core to trusted monitoring in AI control: a fallible LLM monitor vets planned actions before irreversible execution. Over-blocking forfeits usefulness an…
UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention
Cheng Yan, Zhijun Fan, Guangyang Ye +4
While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and…
REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models
Xiang Xia, Cheng Yan, Yiming Zhang +3
Mixture-of-experts (MoE) models increase parameter capacity by activating only a small subset of experts for each token. This conditional-computation paradigm has enabled autoregre…
\(X\)-evolve: Solution space evolution powered by large language models
Yi Zhai, Zhiqiang Wei, Ruohan Li +7
While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individ…
A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
Yuting Huang, Leilei Ding, Zhipeng Tang +5
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However,…