Linye Wei | Meng Li's Homepagehttps://mengli.me/authors/linye_wei_2025g/Linye WeiWowchemy (https://wowchemy.com)en-ushttps://mengli.me/media/icon_hu_ad1e0b0e8ea3c209.pngLinye Weihttps://mengli.me/authors/linye_wei_2025g/TEAM: Temporal–Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Accelerationhttps://mengli.me/publication/icml-2026-team/Fri, 01 May 2026 00:00:00 +0000https://mengli.me/publication/icml-2026-team/Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Modelshttps://mengli.me/publication/dac-2026-odbllm/Tue, 24 Feb 2026 00:00:00 +0000https://mengli.me/publication/dac-2026-odbllm/No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Renderinghttps://mengli.me/publication/iccad-2025-3dgs/Mon, 27 Oct 2025 00:00:00 +0000https://mengli.me/publication/iccad-2025-3dgs/SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decodinghttps://mengli.me/publication/dac-2025-specasr/Tue, 25 Feb 2025 00:00:00 +0000https://mengli.me/publication/dac-2025-specasr/