collaborators

5 papers

cs.AI2026

LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs

Yirui Liu, Ruoling Qi, Longwen Wang +5

LLM serving is increasingly accelerated by position-independent caching (PIC). Existing PIC methods, however, are built for full-attention models, where a token-indexed KV cache un…

cs.AI2026

Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks

Yiliang Song, Hongjun An, Jiangan Chen +4

Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Tes…

cs.CL2026

Ruyi2 Technical Report

Huan Song, Shuyu Tian, Junyi Hao +5

Large Language Models (LLMs) face significant challenges regarding deployment costs and latency, necessitating adaptive computing strategies. Building upon the AI Flow framework, w…

cs.AI2026

CreditAudit: 2 Dimension for LLM Evaluation and Selection

Yiliang Song, Hongjun An, Jiangong Xiao +3

Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scor…

cs.CV2026

Single-Pixel Vision-Language Model for Intrinsic Privacy-Preserving Behavioral Intelligence

Hongjun An, Yiliang Song, Jiawei Shao +2

Adverse social interactions, such as bullying, harassment, and other illicit activities, pose significant threats to individual well-being and public safety, leaving profound impac…