13 papers
Detector-in-the-Loop Tracking: Active Memory Rectification for Stable Glottic Opening Localization
Huayu Wang, Bahaa Alattar, Cheng-Yen Yang +5
Temporal stability in glottic opening localization remains challenging due to the complementary weaknesses of single-frame detectors and foundation-model trackers: the former lacks…
Reasoning Matters for 3D Visual Grounding
Hsiang-Wei Huang, Kuang-Ming Chen, Wenhao Chai +3
The recent development of Large Language Models (LLMs) with strong reasoning ability has driven research in various domains such as mathematics, coding, and scientific discovery. M…
UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning
Zhongyu Jiang, Wenhao Chai, Lei Li +3
In recent years, there has been a growing interest in developing effective alignment pipelines to generate unified representations from different modalities for multi-modal fusion…
Warehouse Spatial Question Answering with LLM Agent
Hsiang-Wei Huang, Jen-Hao Cheng, Kuang-Ming Chen +8
Spatial understanding has been a challenging task for existing Multi-modal Large Language Models~(MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM's sp…
ToSA: Token Merging with Spatial Awareness
Hsiang-Wei Huang, Wenhao Chai, Kuang-Ming Chen +2
Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual t…
Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
Kunjun Li, Zigeng Chen, Cheng-Yen Yang +1
Visual Autoregressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction approach, which yields substantial improvements in efficiency, scal…