Author

Yushi Huang

Institutions: Hong Kong University of Science and Technology, Sensetime (China)

Observed institutions: Hong Kong University of Science and Technology, Sensetime (China)

OpenAlex ID: A5129742168

SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning

2026 · Lingkun Long, Rubing Yang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 3

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing

2026 · Lingkun Long, Yushi Huang, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting

Works count: 2

Citation count: 3

H-index: 1

I10-index: