activity
20242026
collaborators

6 papers

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.CV2025

Omni-Referring Image Segmentation

Qiancheng Zheng, Yunhang Shen, Gen Luo +5

In this paper, we propose a novel task termed Omni-Referring Image Segmentation (OmniRIS) towards highly generalized image segmentation. Compared with existing unimodally condition…

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…

cs.LG2025

Training Long-Context LLMs Efficiently via Chunk-wise Optimization

Wenhao Li, Yuxin Zhang, Gen Luo +2

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. T…

cs.CV2025

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models

Mingrui Wu, Xinyue Cai, Jiayi Ji +7

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through test-time optimization of a learnable latent variable…

cs.CV2024

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression

Bo Tong, Bokai Lai, Yiyi Zhou +5

Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent effor…