← Search

Junyong Kang

2 accepted papers

2026

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

ICML 2026poster

Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answer…

Cited by 0SourceScholar
2026

Rethinking Direct Preference Optimization in Diffusion Models

AAAI 2026technical

Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While Direct Preference Optimization (DPO) has established a foundation for preference learning in large language models (LLMs), its extension to diffusion models remains limited in ali

Cited by 0SourcePDFScholar