Publications | Academichttps://shuzhangzhong.github.io/publication/PublicationsHugo Blox Builder (https://hugoblox.com)en-usWed, 25 Jun 2025 00:00:00 +0000https://shuzhangzhong.github.io/media/icon_hu0b7a4cb9992c9ac0e91bd28ffd38dd00_9727_512x512_fill_lanczos_center_3.pngPublicationshttps://shuzhangzhong.github.io/publication/H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inferencehttps://shuzhangzhong.github.io/publication/iccad-2025-h2eal/Wed, 25 Jun 2025 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2025-h2eal/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processinghttps://shuzhangzhong.github.io/publication/iccad-2025-hdmoe/Wed, 25 Jun 2025 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2025-hdmoe/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inferencehttps://shuzhangzhong.github.io/publication/dac-2025-specasr/Tue, 25 Feb 2025 00:00:00 +0000https://shuzhangzhong.github.io/publication/dac-2025-specasr/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decodinghttps://shuzhangzhong.github.io/publication/dac-2025-hybrimoe/Tue, 25 Feb 2025 00:00:00 +0000https://shuzhangzhong.github.io/publication/dac-2025-hybrimoe/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inferencehttps://shuzhangzhong.github.io/publication/iccad-2024-adapmoe/Sun, 27 Oct 2024 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2024-adapmoe/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationhttps://shuzhangzhong.github.io/publication/iccad-2024-privquant/Sun, 27 Oct 2024 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2024-privquant/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decodinghttps://shuzhangzhong.github.io/publication/iccad-2024-propd/Sun, 27 Oct 2024 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2024-propd/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->Memory-aware scheduling for complex wired networks with iterative graph optimizationhttps://shuzhangzhong.github.io/publication/iccad-2023-mem/Tue, 24 Oct 2023 00:00:00 +0000https://shuzhangzhong.github.io/publication/iccad-2023-mem/<!-- <div class="alert alert-note"> <div> Click the <em>Cite</em> button above to demo the feature to enable visitors to import publication metadata into their reference management software. </div> </div> <div class="alert alert-note"> <div> Create your slides in Markdown - click the <em>Slides</em> button to check out the example. </div> </div> Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/). -->