Related papers: GRITv2: Efficient and Light-weight Social Relation…

Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as…

The remarkable progress of network embedding has led to state-of-the-art algorithms in recommendation. However, the sparsity of user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users'…

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…

This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in…

Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the…

General-domain large multimodal models (LMMs) have achieved significant advances in various image-text tasks. However, their performance in the Intelligent Traffic Surveillance (ITS) domain remains limited due to the absence of dedicated…

Dynamic graph representation learning strategies are based on different neural architectures to capture the graph evolution over time. However, the underlying neural architectures require a large amount of parameters to train and suffer…

This work explores conditions under which multi-finger grasping algorithms can attain robust sim-to-real transfer. While numerous large datasets facilitate learning generative models for multi-finger grasping at scale, reliable real-world…

Image-Text Retrieval (ITR) systems are central to multimodal information access, with Vision-Language Models (VLMs) showing strong performance on standard benchmarks. However, these benchmarks predominantly rely on coarse-grained…

While transformer architectures have dominated computer vision in recent years, these models cannot easily be deployed on hardware with limited resources for autonomous driving tasks that require real-time-performance. Their computational…

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating…

Neural networks are increasingly used for graph classification in a variety of contexts. Social media is a critical application area in this space, however the characteristics of social media graphs differ from those seen in most popular…

Parameter-efficient fine-tuning (PEFT) is the default way to adapt LLMs, but widely used LoRA and QLoRA are largely geometry-agnostic: they optimize in fixed, randomly oriented low-rank subspaces with first-order descent, mostly ignoring…

This work focuses on developing parameter-efficient and lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Our goal is to set up the new frontier of the 5M magnitude lightweight model on various…

The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe…

Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual…

This paper presents a comprehensive evaluation of lightweight deep learning models for image classification, emphasizing their suitability for deployment in resource-constrained environments such as low-memory devices. Five state-of-the-art…

Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant…

While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation. Drawing from recent studies demonstrating that…

Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing…