5 papers
Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space
SiYuan Ma, Albert Gao, Chunzheng Zhu +6
Scientific discovery systems typically optimize experiments within a fixed hypothesis space. This creates a failure mode when all available candidates omit the same missing mechani…
CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning
Siyuan Ma, Bo Gao, Zikai Xiao +6
Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over w…
SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis
Jianhui Wei, Zikai Xiao, Danyu Sun +4
Surgical video understanding is pivotal for enabling automated intraoperative decision-making, skill assessment, and postoperative quality improvement. However, progress in develop…
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding
Zikai Xiao, Ziyang Wang, Wen Ma +5
While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs,…
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
Yichen Li, Zhiting Fan, Ruizhe Chen +4
Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit insta…