activity
20242026
most citedMixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

2 citations · 2 across the 3 of their papers we have counts for

collaborators

11 papers

cs.CL2026

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs

Tengxuan Liu, Shiyao Li, Jiayi Yang +7

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT rea…

cs.AI2026

Agentic evolution of physically constrained foundation models

Jiangwei Zhang, Wen Sun, Chong Wang +7

Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatib…

cs.LG2025

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

Tianyu Fu, Haofeng Huang, Xuefei Ning +10

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods ty…

cs.CL2025

LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K

Tao Yuan, Xuefei Ning, Dong Zhou +10

State-of-the-art large language models (LLMs) are now claiming remarkable supported context lengths of 256k or even more. In contrast, the average context lengths of mainstream ben…

cs.CV2025

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

Shiyao Li, Yingchun Hu, Xuefei Ning +10

Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significa…

cs.CV2025

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Tianchen Zhao, Tongcheng Fang, Haofeng Huang +10

Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, la…