collaborators

13 papers

cs.MM2026

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Che Liu, Lichao Ma, Xiangyu Tony Zhang +4

Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer…

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.CV2026

A Synthetic Eye Movement Dataset for Script Reading Detection: Real Trajectory Replay on a 3D Simulator

Kidus Zewde, Yuchen Zhou, Dennis Ng +6

Large vision-language models have achieved remarkable capabilities by training on massive internet-scale data, yet a fundamental asymmetry persists: while LLMs can leverage self-su…

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.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…