8 citations · 12 across the 18 of their papers we have counts for
9 papers · 1 filter
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
Mahtab Bigverdi, Zelun Luo, Cheng-Yu Hsieh +4
Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit…
NVILA: Efficient Frontier Visual Language Models
Zhijian Liu, Ligeng Zhu, Baifeng Shi +24
Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a…
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh +5
Network pruning has emerged as a potential solution to make LLMs cheaper to deploy. However, existing LLM pruning approaches universally rely on the C4 dataset as the calibration d…
The Hard Positive Truth about Vision-Language Compositionality
Amita Kamath, Cheng-Yu Hsieh, Kai-Wei Chang +1
Several benchmarks have concluded that our best vision-language models (e.g., CLIP) are lacking in compositionality. Given an image, these benchmarks probe a model's ability to ide…
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Matt Deitke, Christopher Clark, Sangho Lee +47
Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good perfor…
Self-Enhancing Video Data Management System for Compositional Events with Large Language Models [Technical Report]
Enhao Zhang, Nicole Sullivan, Brandon Haynes +2
Complex video queries can be answered by decomposing them into modular subtasks. However, existing video data management systems assume the existence of predefined modules for each…
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li +8
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phe…
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh +3
When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccur…
Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
Yu-Guan Hsieh, Cheng-Yu Hsieh, Shih-Ying Yeh +7
Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop mode…