12 papers
DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
Lizhuo Luo, Shenggui Li, Yonggang Wen +1
Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block…
Efficient Fuzzy Private Set Intersection from Secret-shared OPRF
Xinpeng Yang, Meng Hao, Chenkai Weng +3
Private set intersection (PSI) enables a sender holding a set of size and a receiver holding a set of size to securely compute the intersection . Fuzzy PS…
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
Shenggui Li, Chao Wang, Yikai Zhu +14
Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to…
PromptTuner: SLO-Aware Elastic System for LLM Prompt Tuning
Wei Gao, Peng Sun, Dmitrii Ustiugov +2
Prompt tuning has become a prominent strategy for enhancing the performance of Large Language Models (LLMs) on downstream tasks. Many IT enterprises now offer Prompt-Tuning-as-a-Se…
SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating Procedures
Liangtao Lin, Zhaomeng Zhu, Tianwei Zhang +1
Standard Operating Procedures (SOPs) are essential for ensuring operational safety and consistency in industrial environments. However, retrieving and following these procedures pr…
Inference-time Alignment via Sparse Junction Steering
Runyi Hu, Jie Zhang, Shiqian Zhao +7
Token-level steering has emerged as a pivotal approach for inference-time alignment, enabling fine grained control over large language models by modulating their output distributio…