DyLLM: Efficient Diffusion LLM Inference via Saliency-Based Token Selection and Partial Attention
May 02, 2026 · ICML
ICML, 2026
Selected research papers, journal articles and preprints.
-
-
From Tokens to Layers: Redefining Stall-Free Scheduling for LLM Serving with Layered Prefill
May 01, 2026 · MLSys
MLSys, 2026
-
LiLo: Harnessing the on-Chip Accelerators in Intel CPUs for Compressed LLM Inference Acceleration
February 01, 2026 · HPCA
HPCA, 2026
-
Understanding the Relationship between Core Constraints and Core-Selecting Payment Rules in Combinatorial Auctions
August 01, 2023 · IJTCS-FAW
IJTCS-FAW, 2023 (Nominated for Best Paper)