Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?
arXiv:2505. 13518v3 Announce Type: replace-cross Abstract: Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predictions toward the majority class and degrading classifier performance.
arXiv:2512. 10054v3 Announce Type: replace Abstract: Autoregressive language models expose one causal token frontier, even when the requested document contains sections that could be developed concurrently.
arXiv:2607. 18081v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices.
arXiv:2510. 22228v2 Announce Type: replace-cross Abstract: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).
arXiv:2607. 16248v1 Announce Type: cross Abstract: Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads.
arXiv:2607. 17558v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) offers a promising approach for training large language models without relying on a separate teacher model.
arXiv:2603. 08173v2 Announce Type: replace-cross Abstract: Quantization has become essential for the efficient deployment of speech processing systems.
arXiv:2607. 16930v1 Announce Type: cross Abstract: Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration.
arXiv:2607. 17374v1 Announce Type: cross Abstract: Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings.
arXiv:2607. 16295v1 Announce Type: cross Abstract: Mechanistic interpretability has made significant strides in understanding neural network representations, with sparse dictionary learning (SDL) methods, most prominently sparse autoencoders, as a central paradigm.
arXiv:2607. 17747v1 Announce Type: cross Abstract: The increasing complexity of mobile networks necessitates intelligent and dynamic control strategies for efficient, energy-conserving management.
arXiv:2607. 17790v1 Announce Type: cross Abstract: Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment.
arXiv:2607. 18074v1 Announce Type: new Abstract: Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges.
arXiv:2607. 17668v1 Announce Type: cross Abstract: Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution shifts.
arXiv:2607. 16222v1 Announce Type: cross Abstract: This paper presents ARGO, a smart eyewear platform designed to bridge ergonomic comfort, high computational throughput, and energy efficiency.
arXiv:2607. 17154v1 Announce Type: cross Abstract: Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures.
arXiv:2604. 25693v2 Announce Type: replace Abstract: Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to conduct both retrieval over the full entity set and final link prediction.
arXiv:2511. 05420v2 Announce Type: replace-cross Abstract: As smart grids evolve to meet growing energy demands and modern operational challenges, the ability to accurately predict faults becomes increasingly critical.
arXiv:2607. 16927v1 Announce Type: cross Abstract: We introduce Deep Adaptive Bayesian Screening (DABS), a method for performing adaptive factorial screening in high-dimensional discrete design spaces.