6 papers
The Hidden Power of Scaling Factor in LoRA Optimization
Zicheng Zhang, Haoran Li, Jiaxing Wang +10
In Low-Rank Adaptation (LoRA), the scaling factor is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly understood. In this p…
The Primacy of Magnitude in Low-Rank Adaptation
Zicheng Zhang, Haoran Li, Yifeng Zhang +5
Low-Rank Adaptation (LoRA) offers a parameter-efficient paradigm for tuning large models. While recent spectral initialization methods improve convergence and performance over the…
FastVID: Dynamic Density Pruning for Fast Video Large Language Models
Leqi Shen, Guoqiang Gong, Tao He +4
Video Large Language Models have demonstrated strong video understanding capabilities, yet their practical deployment is hindered by substantial inference costs caused by redundant…
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Leqi Shen, Guoqiang Gong, Tianxiang Hao +6
The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-la…
LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
Leqi Shen, Tao He, Guoqiang Gong +5
Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches i…
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
Leqi Shen, Tianxiang Hao, Tao He +5
Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, re…