Yusuke Sakai
5 papers · Latest:
Edit-level Majority Voting Mitigates Over-Correction in LLM-based Grammatical Error Correction
This paper introduces edit-level majority voting to reduce over-correction in LLM-based grammatical error correction, improving performance.
One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
This paper identifies hubness vulnerabilities in cross-modal encoders like CLIP by finding single hub texts that achieve high, unreasonable similarity scores.
HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists
HalluCiteChecker is a lightweight, CPU-efficient toolkit designed to detect and verify hallucinated citations in scientific papers, reducing reviewer workload.
CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and Authenticity
CArtBench is a new benchmark evaluating Vision-Language Models on complex Chinese art understanding, interpretation, and authenticity tasks.
Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks
This paper derives a closed-form upper bound for the maximum Hessian eigenvalue in smooth nonlinear neural networks with cross-entropy loss.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.