Sungnyun Kim

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation

MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition