Author

Yang Li

h-index 5 View on Semantic Scholar

We have 2 of 13 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories

TopoCompress is introduced, a training-free and model-agnostic framework that compresses long contexts by selecting coherent semantic spans by selecting coherent semantic spans and achieves performance comparable to the strongest baseline while using a 4x smaller compression budget.

Daniel Agyei Asante, Yang Li · 1 citation

#machine learning Preprint Aug 2026

The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

It is explained how roleplay can produce compliance despite retained evidence of harm and identify a concrete target for future safeguards: maintaining the connection from harm recognition to refusal.

M. Chowdhury, Er-Nie Chang, Yang Li · 0 citations