3 citations · 4 across the 11 of their papers we have counts for
7 papers · 1 filter
Deep Pre-Alignment for VLMs
Tianyu Yu, Kechen Fang, Zihao Wan +5
Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffer…
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
Kechen Fang, Yihua Qin, Chongyi Wang +3
Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typic…
LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
Shichu Sun, Yichen Zhang, Haolin Song +6
Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor globa…
TextVidBench: A Benchmark for Long Video Scene Text Understanding
Yangyang Zhong, Ji Qi, Yuan Yao +5
Despite recent progress on the short-video Text-Visual Question Answering (ViteVQA) task - largely driven by benchmarks such as M4-ViteVQA - existing datasets still suffer from lim…
An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
Ji Qi, Yuan Yao, Yushi Bai +4
Large Multimodal Models (LMMs) uniformly perceive video frames, creating computational inefficiency for videos with inherently varying temporal information density. This paper pres…
LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
Yipeng Zhang, Yifan Liu, Zonghao Guo +10
Vision transformers (ViTs) are widely employed in multimodal large language models (MLLMs) for visual encoding. However, they exhibit inferior performance on tasks regarding fine-g…
Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
Minghe Gao, Shuang Chen, Liang Pang +7
The remarkable performance of Multimodal Large Language Models (MLLMs) has unequivocally demonstrated their proficient understanding capabilities in handling a wide array of visual…