collaborators

12 papers

cs.CV2026

Prototype-Based Test-Time Adaptation of Vision-Language Models

Zhaohong Huang, Yuxin Zhang, Wenjing Liu +2

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works hav…

cs.CV2026

ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference

Zhaohong Huang, Wenjing Liu, Yuxin Zhang +2

Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token im…

cs.CL2026

Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts

Wenhao Li, Daohai Yu, Gen Luo +7

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whos…

cs.CL2026

CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling

Wenhao Li, Bangcheng Sun, Weihao Ye +4

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, naïve context extension imposes significant computation…

cs.CV2025

Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers

Yunshan Zhong, Yuyao Zhou, Yuxin Zhang +5

Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Tr…

cs.CL2025

Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval

Wenhao Li, Yuxin Zhang, Gen Luo +4

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintai…