4 papers
Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting
Zipeng Gao, Zhi Zheng, Qingrong Xia +5
Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically…
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
Zhaomeng Zhou, Lan Zhang, Junyang Wang +2
Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by compressing re…
Serverless GPU Architecture for Enterprise HR Analytics: A Production-Scale BDaaS Implementation
Guilin Zhang, Wulan Guo, Ziqi Tan +8
Industrial and government organizations increasingly depend on data-driven analytics for workforce, finance, and regulated decision processes, where timeliness, cost efficiency, an…
VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
Junda Lin, Zhaomeng Zhou, Zhi Zheng +4
LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback…