Algorithm/Software | Meng Li's Homepagehttps://mengli.me/tag/algorithm/software/Algorithm/SoftwareWowchemy (https://wowchemy.com)en-usSat, 11 Jul 2026 00:00:00 +0000https://mengli.me/media/icon_hu_ad1e0b0e8ea3c209.pngAlgorithm/Softwarehttps://mengli.me/tag/algorithm/software/MatMoE: Matryoshka Mixture-of-Experts with Dynamic Mixed-Precision Quantization for Efficient Inferencehttps://mengli.me/publication/iccad-2026-matmoe/Sat, 11 Jul 2026 00:00:00 +0000https://mengli.me/publication/iccad-2026-matmoe/Helios: Melting Kernel Boundaries for GPU-Accelerated HE via Graph Rewriting and Microarchitecture-Aware Mappinghttps://mengli.me/publication/micro-2026-helios/Sun, 05 Jul 2026 00:00:00 +0000https://mengli.me/publication/micro-2026-helios/RePart: Efficient Hypergraph Partitioning with Logic Replication Optimization for Multi-FPGA Systemhttps://mengli.me/publication/iseda-2026-repart/Tue, 12 May 2026 00:00:00 +0000https://mengli.me/publication/iseda-2026-repart/Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapsehttps://mengli.me/publication/icml-2026-attn/Fri, 01 May 2026 00:00:00 +0000https://mengli.me/publication/icml-2026-attn/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/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/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/DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inferencehttps://mengli.me/publication/dac-2026-drift/Tue, 24 Feb 2026 00:00:00 +0000https://mengli.me/publication/dac-2026-drift/DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulationhttps://mengli.me/publication/dac-2026-dyslvla/Tue, 24 Feb 2026 00:00:00 +0000https://mengli.me/publication/dac-2026-dyslvla/KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planninghttps://mengli.me/publication/dac-2026-keep/Tue, 24 Feb 2026 00:00:00 +0000https://mengli.me/publication/dac-2026-keep/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/CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routinghttps://mengli.me/publication/neurips-2025-cryptomoe/Sun, 14 Dec 2025 00:00:00 +0000https://mengli.me/publication/neurips-2025-cryptomoe/EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrievalhttps://mengli.me/publication/neurips-2025-efficientnav/Sun, 14 Dec 2025 00:00:00 +0000https://mengli.me/publication/neurips-2025-efficientnav/MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inferencehttps://mengli.me/publication/neurips-2025-mpcache/Sun, 14 Dec 2025 00:00:00 +0000https://mengli.me/publication/neurips-2025-mpcache/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/Breaking the Layer Barrier: Remodeling Private Transformer Inference with Hybrid CKKS and MPChttps://mengli.me/publication/usenix-2025-blb/Wed, 14 May 2025 00:00:00 +0000https://mengli.me/publication/usenix-2025-blb/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/ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerancehttps://mengli.me/publication/dac-2025-realm/Tue, 25 Feb 2025 00:00:00 +0000https://mengli.me/publication/dac-2025-realm/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/SCALES: Boost Binary Neural Network for Image Super-Resolution with Efficient Scalingshttps://mengli.me/publication/date-2025-scales/Mon, 24 Feb 2025 00:00:00 +0000https://mengli.me/publication/date-2025-scales/ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Evictionhttps://mengli.me/publication/neurips-2024-arkvale/Sat, 14 Dec 2024 00:00:00 +0000https://mengli.me/publication/neurips-2024-arkvale/PrivCirNet: Efficient Private Inference via Block Circulant Transformationhttps://mengli.me/publication/neurips-2024-privcirnet/Sat, 14 Dec 2024 00:00:00 +0000https://mengli.me/publication/neurips-2024-privcirnet/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/FlexHE: A flexible Kernel Generation Framework for Homomorphic Encryption-Based Private Inferencehttps://mengli.me/publication/iccad-2024-flexhe/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/publication/iccad-2024-flexhe/MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollershttps://mengli.me/publication/iccad-2024-mcubert/Sun, 27 Oct 2024 00:00:00 +0000https://mengli.me/publication/iccad-2024-mcubert/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/FastQuery: Communication-efficient Embedding Table Query for Private LLMs inferencehttps://mengli.me/publication/dac-2024-fastquery/Sun, 07 Jul 2024 00:00:00 +0000https://mengli.me/publication/dac-2024-fastquery/CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inferencehttps://mengli.me/publication/neurips-2023-copriv/Thu, 14 Dec 2023 00:00:00 +0000https://mengli.me/publication/neurips-2023-copriv/Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inferencehttps://mengli.me/publication/iccad-2023-falcon/Tue, 24 Oct 2023 00:00:00 +0000https://mengli.me/publication/iccad-2023-falcon/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/MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentionhttps://mengli.me/publication/iccv-2023-mpcvit/Tue, 24 Oct 2023 00:00:00 +0000https://mengli.me/publication/iccv-2023-mpcvit/AVATAR: An Aging- and Variation-Aware Dynamic Timing Analyzer for Error-Efficient Computinghttps://mengli.me/publication/tcad-2023-avatar/Fri, 07 Jul 2023 00:00:00 +0000https://mengli.me/publication/tcad-2023-avatar/BiT: Robustly Binarized Multi-distilled Transformerhttps://mengli.me/publication/neurips-2022-bit/Tue, 27 Sep 2022 00:00:00 +0000https://mengli.me/publication/neurips-2022-bit/Depth Shrink: Empowering Hardware-Friendly Shallow Neural Networkshttps://mengli.me/publication/icml-2022-depthshrink/Fri, 10 Jun 2022 00:00:00 +0000https://mengli.me/publication/icml-2022-depthshrink/Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernethttps://mengli.me/publication/icassp-2022-omnisparsity/Sun, 22 May 2022 00:00:00 +0000https://mengli.me/publication/icassp-2022-omnisparsity/Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationhttps://mengli.me/publication/cvpr-2022-hrvit/Sat, 05 Mar 2022 00:00:00 +0000https://mengli.me/publication/cvpr-2022-hrvit/SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systemshttps://mengli.me/publication/cvpr-2022-splitnet/Sat, 05 Mar 2022 00:00:00 +0000https://mengli.me/publication/cvpr-2022-splitnet/NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Traininghttps://mengli.me/publication/iclr-2022-nasvit/Mon, 14 Feb 2022 00:00:00 +0000https://mengli.me/publication/iclr-2022-nasvit/AlphaNet: Improved Training of Supernets with Alpha-Divergencehttps://mengli.me/publication/icml-2021-alphanet/Thu, 10 Jun 2021 00:00:00 +0000https://mengli.me/publication/icml-2021-alphanet/AttentiveNAS: Improving Neural Architecture Search via Attentive Samplinghttps://mengli.me/publication/cvpr-2021-attentivenas/Thu, 01 Apr 2021 00:00:00 +0000https://mengli.me/publication/cvpr-2021-attentivenas/KeepAugment: A Simple Information-Preserving Data Augmentation Approachhttps://mengli.me/publication/cvpr-2021-keepaugment/Mon, 23 Nov 2020 00:00:00 +0000https://mengli.me/publication/cvpr-2021-keepaugment/TimingSAT: Decamouflaging timing-based logic obfuscationhttps://mengli.me/publication/itc-2018-timingsat/Mon, 01 Oct 2018 00:00:00 +0000https://mengli.me/publication/itc-2018-timingsat/Federated Learning with Non-IID Datahttps://mengli.me/publication/arxiv-2018-federated/Sat, 02 Jun 2018 00:00:00 +0000https://mengli.me/publication/arxiv-2018-federated/PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Traininghttps://mengli.me/publication/arxiv-2018-privynet/Fri, 12 Jan 2018 00:00:00 +0000https://mengli.me/publication/arxiv-2018-privynet/Cross-level monte carlo framework for system vulnerability evaluation against fault attackhttps://mengli.me/publication/dac-2017-fault/Sun, 18 Jun 2017 00:00:00 +0000https://mengli.me/publication/dac-2017-fault/AppSAT: Approximately Deobfuscating Integrated Circuitshttps://mengli.me/publication/host-2017-appsat/Mon, 01 May 2017 00:00:00 +0000https://mengli.me/publication/host-2017-appsat/A monte carlo simulation flow for seu analysis of sequential circuitshttps://mengli.me/publication/dac-2016-seu/Sun, 05 Jun 2016 00:00:00 +0000https://mengli.me/publication/dac-2016-seu/