6 papers
CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen +3
Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. W…
Modeling LLM Agent Reviewer Dynamics in Elo-Ranked Review System
Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen +1
In this work, we explore the Large Language Model (LLM) agent reviewer dynamics in an Elo-ranked review system using real-world conference paper submissions. Multiple LLM agent rev…
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…
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…
TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
Jen-Hao Cheng, Vivian Wang, Huayu Wang +11
Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress vid…