collaborators

11 papers

cs.DC2026

LOCAL: Enabling Learning On-device Contiguously for Agent LLMs

Xinxin Liu, Jiaxin Li, Zibo Wang +7

On-device LLM agents interact repeatedly with users on local hardware, producing private traces that are valuable for adaptation but should not be sent to a remote trainer. Ideally…

cs.LG2026

MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training

Yikai Wang, Chuansai Zhou, Yuhang Zhou +10

Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In…

cs.CL2026

SpecLA: Efficient Speculative Decoding for Linear-Attention Models

Zhibin Wang, Xuying Han, Zhaohua Yang +5

Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one token at a time. Speculati…

cs.OS2026

SSV: Sparse Speculative Verification for Efficient LLM Inference

Zhibin Wang, Ziyu Zhong, Nuo Shen +3

Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across m…

cs.DC2026

STAR: Decode-Phase Rescheduling for LLM Inference

Zhibin Wang, Zetao Hong, Xue Li +8

Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly f…

cs.LG2026

CoDec: Prefix-Shared Decoding Kernel for LLMs

Zhibin Wang, Rui Ning, Chao Fang +12

Prefix-sharing among multiple prompts presents opportunities to combine the operations of the shared prefix, while attention computation in the decode stage, which becomes a critic…