Related papers: Vector-Vector-Matrix Architecture: A Novel Hardwar…

The rapid advancement of Low-Altitude Economy Networks (LAENets) has enabled a variety of applications, including aerial surveillance, environmental sensing, and semantic data collection. To support these scenarios, unmanned aerial vehicles…

We present paired learning and inference algorithms for significantly reducing computation and increasing speed of the vector dot products in the classifiers that are at the heart of many NLP components. This is accomplished by partitioning…

This paper investigates an important problem of an appropriate variance-covariance matrix estimation in the Modern Portfolio Theory. We propose a novel framework for variancecovariance matrix estimation for purposes of the portfolio…

Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework…

The advent of large vision-language models (LVLMs) represents a remarkable advance in the quest for artificial general intelligence. However, the model's effectiveness in both specialized and general tasks warrants further investigation.…

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

Large language models (LLMs) are both storage-intensive and computation-intensive, posing significant challenges when deployed on resource-constrained hardware. As linear layers in LLMs are mainly resource consuming parts, this paper…

Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models such as Ouro perform reasoning by…

The emergence of heterogeneity and domain-specific architectures targeting deep learning inference show great potential for enabling the deployment of modern CNNs on resource-constrained embedded platforms. A significant development is the…

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose…

Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrices. Recent works such as Tied-LoRA, VeRA, and VB-LoRA push…

Large language models (LLMs) have demonstrated remarkable abilities in natural language processing. However, their deployment on resource-constrained embedded devices remains difficult due to memory and computational demands. In this paper,…

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

This paper presents a novel framework for designing support vector machines (SVMs), which does not impose restriction on the SVM kernel to be positive-definite and allows the user to define memory constraint in terms of fixed template…

Artificial Neural Network computation relies on intensive vector-matrix multiplications. Recently, the emerging nonvolatile memory (NVM) crossbar array showed a feasibility of implementing such operations with high energy efficiency, thus…

The abilities of modern large language models (LLMs) in solving natural language processing, complex reasoning, sentiment analysis and other tasks have been extraordinary which has prompted their extensive adoption. Unfortunately, these…

The prevalent fully-connected tensor network (FCTN) has achieved excellent success to compress data. However, the FCTN decomposition suffers from slow computational speed when facing higher-order and large-scale data. Naturally, there…

Sparse matrix vector multiplication (SpMV) is one of the most common operations in scientific and high-performance applications, and is often responsible for the application performance bottleneck. While the sparse matrix representation has…

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

The increase in open-source availability of Large Language Models (LLMs) has enabled users to deploy them on more and more resource-constrained edge devices to reduce reliance on network connections and provide more privacy. However, the…