collaborators

17 papers

cs.CL2026

UniSVQ: 2-bit Unified Scalar-Vector Quantization

Haoyu Wang, Haiyan Zhao, Xingyu Yu +4

Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantization (SQ) and vector quantizat…

cs.CL2026

Rethinking the Role of Efficient Attention in Hybrid Architectures

Ziqing Qiao, Yinuo Xu, Chaojun Xiao +6

Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent se…

cs.CV2026

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention

Yuxiang Huang, Mingye Li, Xu Han +7

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods e…

cs.CL2026

StateX: Enhancing RNN Recall via Post-training State Expansion

Xingyu Shen, Yingfa Chen, Zhen Leng Thai +3

Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token complexity when processing long contexts.…

cs.CL2026

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts

Yingfa Chen, Zhen Leng Thai, Zihan Zhou +6

Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for long-conte…

cs.CL2026

NOSA: Native and Offloadable Sparse Attention

Yuxiang Huang, Pengjie Wang, Jicheng Han +9

Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-free KV cache offloa…