Yu Shen
5 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platforms.
HadAgent introduces a decentralized AI serving system that replaces resource-intensive Proof-of-Work with Proof-of-Inference (PoI) to secure LLM agent operations and achieve fast, verifiable consensus.
ProactiveLLM introduces a novel framework that enables streaming LLMs to actively decide when to interact with incoming data by leveraging the model's internal states, significantly reducing latency while maintaining quality.
RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.
This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.
Papers
CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring
Xuan Lu, Haohang Huang, Yingqi Fan, Junlong Tong +4 more
This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.