Mengwei Li — accepted AI-conference papers

2026

PosPrune: Visual Token Pruning with Positional Bias Correction for Efficient Large Vision-Language Models

Ziyang Wang, Mengwei Li, Hao Yin, Wenhao Liu, Zilei Wang

AAAI 2026technical

Large Vision-Language Models (LVLMs) enhance performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs). However, the large number of visual tokens introduces significant computational overhead. Existing token pruning method

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Rethinking Open-world Prompt Tuning: A Systematic Framework for Evaluation and Optimization

Mengwei Li, Zilei Wang, Yixin Zhang

AAAI 2026technical

Prompt Tuning (PT) is a widely used strategy for adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks. Conventional PT methods evaluate performance separately on known (base) and unknown (new) classes. However, in real-world scenarios, models often encounter inputs without

Cited by 0 Source ↗PDF ↗Scholar ↗