Related papers: SAGE: Training-Free Semantic Evidence Composition …

Large language models are unable to continuously adapt and learn from new data during reasoning at inference time. To address this limitation, we propose that complex reasoning tasks be decomposed into atomic subtasks and introduce SAGE, a…

Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications. Particularly supervised hashing has recently received considerable research…

Recent advances in generative networks have enabled new approaches to subsurface velocity model synthesis, offering a compelling alternative to traditional methods such as Full Waveform Inversion. However, these approaches predominantly…

Devices located in remote regions often lack coverage from well-developed terrestrial communication infrastructure. This not only prevents them from experiencing high quality communication services but also hinders the delivery of machine…

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

SAGE (Percipient StorAGe for Exascale Data Centric Computing) is a European Commission funded project towards the era of Exascale computing. Its goal is to design and implement a Big Data/Extreme Computing (BDEC) capable infrastructure with…

Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising yet limited performance. However, most existing LLM agents…

We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of training samples from the trained model. This process, also…

An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes and hyperedges to compact vectors for use in important…

This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint. Since the…

Node importance estimation, a classical problem in network analysis, underpins various web applications. Previous methods either exploit intrinsic topological characteristics, e.g., graph centrality, or leverage additional information,…

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these…

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Large-scale deep learning models impose substantial communication overh ead in distributed training, particularly in bandwidth-constrained or heterogeneous clo ud-edge environments. Conventional synchronous or fixed-compression techniques o…

Engineered image-based biomarkers offer a clinically interpretable alternative to black-box AI in computational pathology, yet their discovery remains largely intuition-driven, guided by fragmented literature rather than rigorous biological…

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse…

The foundation-model ecosystem remains highly centralized because training requires immense compute resources and is therefore largely limited to large cloud operators. Edge-assisted foundation model training that harnesses spare compute on…

Unsupervised Domain Adaptation (UDA) aims to bridge the gap between a source domain, where labelled data are available, and a target domain only represented with unlabelled data. If domain invariant representations have dramatically…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

As a pivotal branch of machine learning, manifold learning uncovers the intrinsic low-dimensional structure within complex nonlinear manifolds in high-dimensional space for visualization, classification, clustering, and gaining key…