相关论文: SHARe-KAN: Post-Training Vector Quantization for C…

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address…

Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However, the discrete and non-differentiable nature of spikes leads…

Multi-channel keyword spotting (KWS) has become crucial for voice-based applications in edge environments. However, its substantial computational and energy requirements pose significant challenges. We introduce ASAP-FE (Agile…

Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering…

The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT). While effective for processing long sequences, this paradigm often…

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this end, we propose a gradually shrinking GAN (PPCD-GAN) by…

Post-Training Quantization (PTQ) compresses large language models to low bit-widths using a small calibration set, and its quality depends strongly on which samples are chosen. We identify a failure mode in which calibration samples fail to…

Charge-domain compute-in-memory (CIM) SRAMs have recently become an enticing compromise between computing efficiency and accuracy to process sub-8b convolutional neural networks (CNNs) at the edge. Yet, they commonly make use of a fixed…

This study presents an ensemble technique, SPQ (SVD-Pruning-Quantization), for large language model (LLM) compression that combines variance-retained singular value decomposition (SVD), activation-based pruning, and post-training linear…

Machine learning for scientific discovery is increasingly becoming popular because of its ability to extract and recognize the nonlinear characteristics from the data. The black-box nature of deep learning methods poses difficulties in…

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection…

The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this…

Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines…

Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a…

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning approaches are based on Graph Neural Networks (GNNs). However, these approaches…

The growth in the complexity of Convolutional Neural Networks (CNNs) is increasing interest in partitioning a network across multiple accelerators during training and pipelining the backpropagation computations over the accelerators.…

Deploying Automatic Speech Recognition (ASR) models on memory-constrained edge devices requires aggressive low-bit weight quantization. Layer-wise post-training quantization is practical and effective, but it suffers from cross-layer error…

While joint pruning--quantization is theoretically superior to sequential application, current joint methods rely on auxiliary procedures outside the training loop for finding compression parameters. This reliance adds engineering…