collaborators

6 papers

cs.AI2026

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…

cs.LG2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…