10 papers
From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models
Hyeonggeun Han, Taehyun Cho, Sangwoo Hong
Large vision-language models often exhibit object hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-Guided Vis…
Mitigating Sequential Reappearance in Diffusion Data-Point Unlearning
Donghyun Kim, Taehyuk Lee, Jinyeong Kim +4
Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same model. We identify sequential…
Mechanistic Circuit Identification for Controllable Data Generation
Nakyung Lee, Sangwoo Hong, Jungwoo Lee
While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. This black-box paradigm provide…
Function-Level Execution Feedback for Code Preference Optimization
Idris Nechnech, Sehwan Kim, Jimin Seo +4
Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, however, process supervision rem…
MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
Jung Min Lee, Dohyeok Lee, Seokhun Ju +5
Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informat…
Operator-aware shadow importance sampling for accurate fidelity estimation
Hyunho Cha, Sangwoo Hong, Jungwoo Lee
Estimating the fidelity between an unknown quantum state and a fixed target is a fundamental task in quantum information science. Direct fidelity estimation (DFE) enables this with…
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
Hyeonggeun Han, Sehwan Kim, Hyungjun Joo +2
Despite their impressive generative capabilities, text-to-image diffusion models often memorize and replicate training data, prompting serious concerns over privacy and copyright.…
Constructing Fair Latent Space for Intersection of Fairness and Explainability
Hyungjun Joo, Hyeonggeun Han, Sehwan Kim +2
As the use of machine learning models has increased, numerous studies have aimed to enhance fairness. However, research on the intersection of fairness and explainability remains i…
Mitigating Spurious Correlations via Disagreement Probability
Hyeonggeun Han, Sehwan Kim, Hyungjun Joo +2
Models trained with empirical risk minimization (ERM) are prone to be biased towards spurious correlations between target labels and bias attributes, which leads to poor performanc…
Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
Youngseok Yoon, Sangwoo Hong, Hyungjun Joo +3
Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the prob…