6 papers
Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs
Kyeongyoon Lee, Hongyeob Kim, Youngeun Kim +1
Omni-modal LLMs jointly process audio, video, and text, but long multimodal sequences incur substantial prefill and KV-cache costs. Existing omni-modal compression methods primaril…
Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
Youjia Zhang, Youngeun Kim, Young-Geun Choi +3
Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challen…
ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models
Youngeun Kim, Youjia Zhang, Huiling Liu +3
Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates this issue, yet existi…
DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
Jungbin Cho, Junwan Kim, Jisoo Kim +5
Human motion is inherently continuous and dynamic, posing significant challenges for generative models. While discrete generation methods are widely used, they suffer from limited…
Question-Aware Gaussian Experts for Audio-Visual Question Answering
Hongyeob Kim, Inyoung Jung, Dayoon Suh +3
Audio-Visual Question Answering (AVQA) requires not only question-based multimodal reasoning but also precise temporal grounding to capture subtle dynamics for accurate prediction.…
RA-Touch: Retrieval-Augmented Touch Understanding with Enriched Visual Data
Yoorhim Cho, Hongyeob Kim, Semin Kim +3
Visuo-tactile perception aims to understand an object's tactile properties, such as texture, softness, and rigidity. However, the field remains underexplored because collecting tac…