Shuzhang Zhong | Meng Li's Homepagehttps://mengli.me/authors/shuzhang_zhong_2023g/Shuzhang ZhongWowchemy (https://wowchemy.com)en-ushttps://mengli.me/media/icon_hu_ad1e0b0e8ea3c209.pngShuzhang Zhonghttps://mengli.me/authors/shuzhang_zhong_2023g/HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reductionhttps://mengli.me/publication/icml-2026-hyper/Fri, 01 May 2026 00:00:00 +0000https://mengli.me/publication/icml-2026-hyper/Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Explorationhttps://mengli.me/publication/osdi-2026-brb/Mon, 30 Mar 2026 00:00:00 +0000https://mengli.me/publication/osdi-2026-brb/NASiC: 3D NAND-based CAM-Selected Multibit CIM Architecture for Efficient On-Device Mixture-of-Experts LLM Inferencehttps://mengli.me/publication/dac-2026-nasic/Tue, 24 Feb 2026 00:00:00 +0000https://mengli.me/publication/dac-2026-nasic/H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inferencehttps://mengli.me/publication/iccad-2025-h2eal/Mon, 27 Oct 2025 00:00:00 +0000https://mengli.me/publication/iccad-2025-h2eal/HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processinghttps://mengli.me/publication/iccad-2025-hdmoe/Mon, 27 Oct 2025 00:00:00 +0000https://mengli.me/publication/iccad-2025-hdmoe/HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inferencehttps://mengli.me/publication/dac-2025-hybrimoe/Tue, 25 Feb 2025 00:00:00 +0000https://mengli.me/publication/dac-2025-hybrimoe/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/AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inferencehttps://mengli.me/publication/iccad-2024-adapmoe/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/publication/iccad-2024-adapmoe/PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationhttps://mengli.me/publication/iccad-2024-privquant/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/publication/iccad-2024-privquant/ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decodinghttps://mengli.me/publication/iccad-2024-propd/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/publication/iccad-2024-propd/Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimizationhttps://mengli.me/publication/iccad-2023-mem/Tue, 24 Oct 2023 00:00:00 +0000https://mengli.me/publication/iccad-2023-mem/