6 papers
A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training
Xinyu Wang, Zhiwei Zhai, Yu Gu +6
Kronecker-preconditioned optimizers recompute a cached curvature eigendecomposition only periodically, and implementations and adaptive methods control this through the refresh fre…
G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm
Zijun Yu, Yu Gu, Vahid Partovi Nia +1
Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a…
Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
Yu Gu, Zijun Yu, Vahid Partovi Nia +1
Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a sin…
LungCURE: Benchmarking Multimodal Real-World Clinical Reasoning for Precision Lung Cancer Diagnosis and Treatment
Fangyu Hao, Jiayu Yang, Yifan Zhu +14
Lung cancer clinical decision support demands precise reasoning across complex, multi-stage oncological workflows. Existing multimodal large language models (MLLMs) fail to handle…
Beyond Procedure: Substantive Fairness in Conformal Prediction
Pengqi Liu, Zijun Yu, Mouloud Belbahri +3
Conformal prediction (CP) offers distribution-free uncertainty quantification for machine learning models, yet its interplay with fairness in downstream decision-making remains und…
A Note on a Recent Attempt to Prove the Irrationality of
Keyu Chen, Wei He, Yixin He +7
Recently Shekhar Suman [arXiv: 2407.07121v6 [math.GM] 3 Aug 2024] made an attempt to prove the irrationality of . But unfortunately the proof is not correct. In this note, we…