5 papers
SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering
Long Shu, Shuochen Liu, Wei Chen +4
Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visual content. Typically, current m…
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 under Policy-Dependent Solvability
Zhaomeng Zhou, Lan Zhang, Junyang Wang +6
Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by compressing re…
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…
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…