相关论文: Outlier-Efficient Hopfield Layers for Large Transf…

Transformer-based large language models (LLMs) have achieved great success with the growing model size. LLMs' size grows by $240\times$ every two years, which outpaces the hardware progress and makes model inference increasingly costly.…

This paper explores the improvement of post-training quantization (PTQ) after knowledge distillation in the Whisper speech foundation model family. We address the challenge of outliers in weights and activation tensors, known to impede…

Large language models (LLMs) have made exciting achievements across various domains, yet their deployment on resource-constrained personal devices remains hindered by the prohibitive computational and memory demands of task-specific…

Attention mechanisms and Transformer architectures have revolutionized Natural Language Processing (NLP) by enabling exceptional modeling of long-range dependencies and capturing intricate linguistic patterns. However, their inherent…

Associative Memories like the famous Hopfield Networks are elegant models for describing fully recurrent neural networks whose fundamental job is to store and retrieve information. In the past few years they experienced a surge of interest…

Recently, some hypergraph-based methods have been proposed to deal with the problem of model fitting in computer vision, mainly due to the superior capability of hypergraph to represent the complex relationship between data points. However,…

Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance…

Long-sequence modeling faces a fundamental trade-off between the efficiency of compressive fixed-size memory in RNN-like models and the fidelity of lossless growing memory in attention-based Transformers. Inspired by the Multi-Store Model…

We investigate the functional role of emergent outliers in large language models, specifically attention sinks (a few tokens that consistently receive large attention logits) and residual sinks (a few fixed dimensions with persistently…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Training large language models using 4-bit arithmetic enhances throughput and memory efficiency. Yet, the limited dynamic range of FP4 increases sensitivity to outliers. While NVFP4 mitigates quantization error via hierarchical…

Modern causal language models stack many attention blocks to improve performance, but not all blocks are necessary for every task. We propose Hopscotch, a simple yet effective method that identifies and skips attention blocks with least…

Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Large language models have achieved remarkable success in recent years, primarily due to self-attention. However, traditional Softmax attention suffers from numerical instability and reduced performance as the number of inference tokens…

Out-of-distribution (OOD) detection is a critical task for the safe deployment of machine learning models in the real world. Existing prototype-based representation learning methods have demonstrated exceptional performance. Specifically,…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a…

In this work we propose an energy functional along the lines of Modern Hopfield Networks (MNH), the stationary points of which correspond to the attention due to Vaswani et al. [12], thus unifying both frameworks. The minima of this…

The Hebbian unlearning algorithm, i.e. an unsupervised local procedure used to improve the retrieval properties in Hopfield-like neural networks, is numerically compared to a supervised algorithm to train a linear symmetric perceptron. We…