5 papers
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
Zhanchao Xu, Haoyang Li, Qingfa Xiao +4
Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, ove…
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Jiaqi Tang, Jianmin Chen, Youyang Zhai +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corrupti…
LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues
Haoyang Li, Zhanchao Xu, Yiming Li +9
Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, exist…
AI and Deep Learning for Automated Segmentation and Quantitative Measurement of Spinal Structures in MRI
Praveen Shastry, Bhawana Sonawane, Kavya Mohan +9
Background: Accurate spinal structure measurement is crucial for assessing spine health and diagnosing conditions like spondylosis, disc herniation, and stenosis. Manual methods fo…
Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference
Qingfa Xiao, Jiachuan Wang, Haoyang Li +6
Recent advances in large language models (LLMs) have showcased exceptional performance in long-context tasks, while facing significant inference efficiency challenges with limited…