collaborators

13 papers

cs.DC2026

Bole: Efficient Tree Speculation for Hybrid-Attention Language Models

Li Wang, Yi Su, Xiabao Wu +9

Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memo…

cs.CL2026

PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention

Hong Liu, Yuan Cheng, Lin Niu +5

Token-level sparse attention, as implemented by DeepSeek Sparse Attention (DSA) in production systems, makes the downstream attention efficient but shifts the bottleneck to the ind…

cs.LG2026

LongFlow: Efficient KV Cache Compression for Reasoning Models

Yi Su, Zhenxu Tian, Dan Qiao +3

Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this perform…

cs.CL2026

Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries

Zhenxu Tian, Yi Su, Juntao Li +1

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV…

cs.IR2026

Quantized Inference for OneRec-V2

Yi Su, Xinchen Luo, Hongtao Cheng +7

Quantized inference has demonstrated substantial system-level benefits in large language models while preserving model quality. In contrast, reliably applying low-precision quantiz…

cs.IR2026

OpenOneRec Technical Report

Guorui Zhou, Honghui Bao, Jiaming Huang +44

While the OneRec series has successfully unified the fragmented recommendation pipeline into an end-to-end generative framework, a significant gap remains between recommendation sy…