Neuromorphic/In-Memory Computing
Our research focuses on memory-based deep learning techniques, including SRAM/ReRAM-based deep learning processing-in-memory (PIM) and Flash memory based robust deep learning inference techniques.
Our research focuses on memory-based deep learning techniques, including SRAM/ReRAM-based deep learning processing-in-memory (PIM) and Flash memory based robust deep learning inference techniques.
![[J39] Multi-Centroid Hyperdimensional Computing for Compact IMC Arrays via Dimension Pruning](/publication/j39_ieee_iot_2026/featured_huf9402f40fe754b8b006fc6aa19638b45_203624_150x0_resize_q75_h2_lanczos.webp)
![[C101] HyperSPACE: Sparse-Adder-Compatible Encoding for Efficient Hyperdimensional Computing on Digital CIM Arrays](/publication/c101_islped_2026/featured_hu32cf67a1a20437b056372b0c40906524_444055_150x0_resize_q75_h2_lanczos_3.webp)
![[C100] Dataflow-Preserving, Overhead-Free Weight Remapping for Fault-Tolerant ReRAM-Based In-Memory Computing](/publication/c100_islped_2026/featured_hub4cd0d8ae94e62ca11d6c9a133e62296_861223_150x0_resize_q75_h2_lanczos_3.webp)
![[C97] RangeGuard: Efficient, Bounded Approximate Error Correction for Reliable DNNs](/publication/c97_isca_2026/featured_hu637b7fedd1c1f1c47334034fe7dcd094_541770_150x0_resize_q75_h2_lanczos_3.webp)
![[C94] REFLEX: Rewrite-Free Row-Aligned Sparse Attention for Efficient LLM Execution on PIM](/publication/c94_dac_2026/featured_hu5796ab5899401798ab8f5476d3af2495_887135_150x0_resize_q75_h2_lanczos_3.webp)
![[J36] RUnQuant: High-Resolution Weight Quantization via Unanchored Weight Decomposition in Column-wise Granularity for CIM Accelerators](/publication/j36_jsa_2026/featured_hu60bb86e2e8db2d4c628955a528e5811f_325175_150x0_resize_q75_h2_lanczos_3.webp)
![[C86] Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling](/publication/c86_neurips_2025/featured_hu299bd38a0615c712f9b133008803e6f4_428189_150x0_resize_q75_h2_lanczos_3.webp)
![[C84] Learnable Center-Based Quantization for Efficient Analog PIM with Reduced ADC Precision](/publication/c84_asp_dac_2026/featured_hu5cb801bdc1f08f678921e48c60b09955_453146_150x0_resize_q75_h2_lanczos_3.webp)
![[C83] Data Flow-Aware Weight Remapping for Efficient Fault Tolerance in ReRAM-Based Accelerators](/publication/c83_asp_dac_2026/featured_huc5dbf7a933210caf5a1e2ed2f44c8c1f_276949_150x0_resize_q75_h2_lanczos_3.webp)
![[C82] ETA: Efficient Transformer Attention Mapping for ReRAM-based Compute-In-Memory Architectures](/publication/c82_apccas_2025/featured_hu47d3bbf26e9d24e2ae430e15b57a5415_203039_150x0_resize_q75_h2_lanczos_3.webp)
![[C81] Weight Sharing for Array-Efficient CNN Inference in Compute-In-Memory Architectures](/publication/c81_isocc_2025/featured_hu83a83bbba365e930d36bbbf54a76bce6_125013_150x0_resize_q75_h2_lanczos_3.webp)
![[C80] Efficient and Robust SNN Decoder Training for Closed-Loop Brain-Machine Interfaces](/publication/c80_biocas_2025/featured_huac977f42b07c0cf0395f002987c59050_324932_150x0_resize_q75_h2_lanczos_3.webp)
![[J34] Mixed Binary Supporting Electrolyte Approach for Enhanced Synaptic Functionality in One-shot Integrable Electropolymerized Synaptic Transistors](/publication/j34_materials_2025/featured_hu507862b18a20787f8af3fac319568729_1707009_150x0_resize_q75_h2_lanczos_3.webp)
![[J33] GAROS: Genetic Algorithm-Aided Row-Skipping for Shift and Duplicate Kernel Mapping in Processing-In-Memory Architectures](/publication/j33_jsa_2025/featured_hub14b0595e0e7a8a9b00bb7acb2d07647_244090_150x0_resize_q75_h2_lanczos_3.webp)
![[C73] Event-based Neural Spike Detection Using Spiking Neural Networks for Neuromorphic iBMI System](/publication/c73_iscas_2025/featured_hue7d03aca5a8a74861c0dbc86832498de_558336_150x0_resize_q75_h2_lanczos.webp)
![[J32] Input/Mapping Precision Controllable Digital CIM with Adaptive Adder Tree Architecture for Flexible DNN Inference](/publication/j32_jsa_2025/featured_hu6e280091d42ae0bb3191279fe85e76bd_376233_150x0_resize_q75_h2_lanczos.webp)
![[C72] MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures](/publication/c72_date_2025/featured_huba2f590ec7c4175d15ee23e2222b09f4_365984_150x0_resize_q75_h2_lanczos.webp)
![[C71] Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators](/publication/c71_date_2025/featured_hu77cf7c405e8e73a3f45ca5006471d9a2_471051_150x0_resize_q75_h2_lanczos.webp)
![[C70] Low-Rank Compression for IMC Arrays](/publication/c70_date_2025/featured_hu5fe43a200eb0ef87d24f5ee03c6a1386_425114_150x0_resize_q75_h2_lanczos.webp)
![[J31] An FPGA-Based Energy-Efficient Real-Time Hand Pose Estimation System with an Integrated Image Signal Processor for Indirect 3D Time-of-Flight Sensors](/publication/j31_ieee_iot_2024/featured_hue5717bd1ba3636cf0edc5b1e0c1e4f98_18804_150x0_resize_q75_h2_lanczos.webp)
![[C65] Continuous Memory Representation for Anomaly Detection](/publication/c65_eccv_2024_memory/featured_huc1405457563e2fe2bcb5178e5675cc30_276005_150x0_resize_q75_h2_lanczos.webp)
![[J30] Reconfigurable Resistive Switching Memory for Telegraph Code Sensing and Recognizing Reservoir Computing Systems](/publication/j30_small_2024/featured_hu392797ac6560e6acaf420b973e8dac8a_104021_150x0_resize_q75_h2_lanczos_3.webp){kind=small}
![[C64] C-AFA: A Conditionally Approximate Full Adder for Efficient DNN Inference in CIM Arrays](/publication/c64_isocc_2024_cim/featured_hu6dcc38f40e51f7b608819649e28410a0_94430_150x0_resize_q75_h2_lanczos_3.webp)
![[C62] Row-Efficient Pruning for In-Memory Convolutional Weight Mapping](/publication/c62_isocc_2024_inmemory/featured_hu1a48ff11825d6800e0d4b8e5718e630b_63812_150x0_resize_q75_h2_lanczos_3.webp)
![[J29] One-Shot Remote Integration of Macromolecular Synaptic Elements on a Chip for Ultrathin Flexible Neural Network System](/publication/j29_adma_2024/featured_hu1beb12e38334fc14a663d962fa3d891c_108785_150x0_resize_q75_h2_lanczos_3.webp)
![[C59] ConvMapSim: Modeling and Simulating Convolutional Weight Mapping for PIM Arrays](/publication/c59_aicas_2024_pim/featured_hu7841e356fe03916c86dab30f71208452_213922_150x0_resize_q75_h2_lanczos_3.webp)
![[C56] TraiNDSim: A Simulation Framework for Comprehensive Performance Evaluation of Neuromorphic Devices for On-Chip Training](/publication/c56_dac_2024/featured_hue7f50756159e4563e731f906898f5e95_159630_150x0_resize_q75_h2_lanczos_3.webp)
![[J28] KERNTROL: Kernel Shape Control Toward Ultimate Memory Utilization for In-Memory Convolutional Weight Mapping](/publication/j28_tcas1_2024/featured_hu805487e99ad06f6fbcaef7b20a0cb065_48999_150x0_resize_q75_h2_lanczos.webp)
![[C55]KARS: Kernel-Grouping Aided Row-Skipping for SDK-based Weight Compression in PIM Arrays](/publication/c55_iscas_2024/featured_hucd18a576234a102f6750bbdb1d150af7_1255458_150x0_resize_q75_h2_lanczos_3.webp)
![[J26] Highly Reliable 3D Channel Memory and Its Application in a Neuromorphic Sensory System for Finger Motion Tracking](/publication/j26_acs_nano_2023/featured_hufa32657bfa793801b399e1667b883191_615630_150x0_resize_q75_h2_lanczos_3.webp)
![[C51] DCR: Decomposition-Aware Column Re-Mapping for Stuck-At-Fault Tolerance in ReRAM Arrays](/publication/c51_iccd_2023/featured_hu955d12e6bf3401e2d14bc5bdf00f703d_492171_150x0_resize_q75_h2_lanczos_3.webp)
![[C47] Kernel Shape Control for Row-Efficient Convolution on Processing-In-Memory Arrays](/publication/c47_iccad_2023/featured_hu1621c99a28d0c8fc51a5ddb8808ca2ed_1230598_150x0_resize_q75_h2_lanczos_3.webp)
![[C45] PAIRS: Pruning-AIded Row-Skipping for Convolutional Weight Mapping in Processing-In-Memory Architectures](/publication/c45_islped_2023/featured_hu5474c00338c99e9bb1e7062de2916f94_1427630_150x0_resize_q75_h2_lanczos_3.webp)
![[C44] Weight-Aware Activation Mapping for Energy-Efficient Convolution on PIM Arrays](/publication/c44_islped_2023/featured_hu055ae0625da78932d12bea10c1b4ed00_233470_150x0_resize_q75_h2_lanczos_3.webp)
![[J24] Room-Temperature-Processable Highly Reliable Resistive Switching Memory with Reconfigurability for Neuromorphic Computing and Ultrasonic Tissue Classification](/publication/j24_afm_2023/featured_hu5a7757ac07928a16d8ffe56aa7f6a65d_841063_150x0_resize_q75_h2_lanczos_3.webp)
![[J18] Multi-Prediction Compression: An Efficient and Scalable Memory Compression Framework for GP-GPU](/publication/j18_cal_2022/featured_hu6aef2193e6bece41bd2a0e680fa624e7_174230_150x0_resize_q75_h2_lanczos.webp)
![[J17] VWC-SDK: Convolutional Weight Mapping Using Shifted and Duplicated Kernel with Variable Windows and Channels](/publication/j17_jetcas_2022/featured_hu1a6fa2935aa5e48aeb8d0d301ce445c0_367892_150x0_resize_q75_h2_lanczos.webp)
![[C32] VW-SDK: Efficient Convolutional Weight Mapping Using Variable Windows for Processing-In-Memory Architectures](/publication/c32_date_2022/Featured_hu6aef2193e6bece41bd2a0e680fa624e7_188891_150x0_resize_q75_h2_lanczos.webp)
![[J15] Adaptive Weight-bit Inversion for State Error Reduction for Robust and Efficient Deep Neural Network Inference Using MLC NAND Flash](/publication/j15_jsa_2022/featured_hu6aef2193e6bece41bd2a0e680fa624e7_64901_150x0_resize_q75_h2_lanczos.webp)
![[C29] A Charge-Domain Computation-in-Memory Macro with Versatile All-Around-Wire-Capacitor for Variable-Precision Computation and Array-Embedded DA/AD Conversions](/publication/c29_esscirc_2021/featured_hu5297bb3ee09acbdf121b1dade851a80c_308541_150x0_resize_q75_h2_lanczos_3.webp){kind=small}
![[J11] A Charge-Domain Scalable-Weight In-Memory Computing Macro with Dual-SRAM Architecture for Precision-Scalable DNN Accelerators](/publication/j11_tcas1_2021/featured_hu6aef2193e6bece41bd2a0e680fa624e7_293978_150x0_resize_q75_h2_lanczos.webp)
![[C26] WISER: Deep Neural Network Weight-bit Inversion for State Error Reduction in MLC NAND Flash](/publication/c26_date_2021/Featured_hu5ad8c31e59524e7f9eeb09f5c1bf4c2c_183210_150x0_resize_q75_h2_lanczos.webp)