42 articles mentioning Llama-4-Scout-17B-16E-Instruct
arXiv:2610.23796v1 Announce Type: new Abstract: Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads. We present FUTRANSFORMER, a CUDA implementatio
arXiv:2610.20632v1 Announce Type: new Abstract: Modern healthcare generates increasingly complex medical reports that challenge clinical professionals in terms of time and interpretive burden. Manual review processes are slow, error-prone, and difficult to scale. This paper presents MeddeX, a Medica
arXiv:2610.19210v1 Announce Type: new Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingly large KV caches. Efficient recurrent alternatives reduce the asymptotic complexi
arXiv:2608.21134v2 Announce Type: replace-cross Abstract: Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute requirements. We present a framework for quantizing VLMs for efficient inference on resource-constrained hardware. Our approa
arXiv:2609.14864v1 Announce Type: new Abstract: We predict single-sequence model throughput from GGUF metadata using roofline-shaped predictors with quantization-specific scale factors fitted on reference models. The scored cohort comprises 318 phase-depth measurements from 53 host-file configuratio
arXiv:2601.18685v5 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Research syntheses remain scarce and risk being outdated by the time of publication. We present a Living
arXiv:2607.22545v1 Announce Type: new Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single
arXiv:2607.12079v1 Announce Type: new Abstract: Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expande
arXiv:2606.15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-interpretability platform, to examine LLaMA 3.1-8B-Instruct on 54 moral promp
arXiv:2512.22671v3 Announce Type: replace-cross Abstract: Structured width pruning of GLU-MLP layers in Llama-3.2 models, guided by the Peak-to-Peak Magnitude (PPM) criterion, reveals a systematic dichotomy in how reducing the expansion ratio affects different model capabilities. While performance o
arXiv:2606.13370v1 Announce Type: new Abstract: This study examines training dynamics in a small Llama-style language model trained under a fixed, compute-constrained token budget. Rather than evaluating efficiency solely through endpoint performance, the study uses a quantitative experimental repea
arXiv:2606.10327v1 Announce Type: new Abstract: Automated Essay Scoring (AES) systems must judge interdependent discourse elements (e.g., lead, claim, evidence, conclusion), yet most approaches treat these in isolation, harming coherence and generalization. We investigate task-aware fine-tuning of L
arXiv:2605.18860v1 Announce Type: new Abstract: This paper proposes a neuron pruning framework based on neuron-level spectral structural importance evaluation. Given a trained neural network, we record the hidden states of each hidden layer during inference and model neurons as graph nodes, with hid
arXiv:2605.01148v1 Announce Type: new Abstract: Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., "what month is six months after August?"). Even though Llama-3.1-8B's representations for these concepts are circularly stru
arXiv:2409.06624v4 Announce Type: replace-cross Abstract: Large Language Models (LLM) often need to be Continual Pre-Trained (CPT) to obtain unfamiliar language skills or adapt to new domains. The huge training cost of CPT often asks for cautious choice of key hyper-parameters such as the mixture ra
arXiv:2506.03178v2 Announce Type: replace-cross Abstract: Automated radiology report generation holds significant potential to reduce radiologists' workload and enhance diagnostic accuracy. However, generating precise and clinically meaningful reports from chest radiographs remains challenging due t
arXiv:2604.14171v1 Announce Type: new Abstract: Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains critically underresourced in the landscape of Large Language Models (LLMs). This study presents a sy
arXiv:2604.12168v1 Announce Type: cross Abstract: The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low
arXiv:2512.12812v2 Announce Type: replace-cross Abstract: Prompt engineering has emerged as a critical factor influencing large language model (LLM) performance, yet the impact of pragmatic elements such as linguistic tone and politeness remains underexplored, particularly across different model fam
arXiv:2607.22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units. Prior attempts, including our own, failed or pro
arXiv:2602.11534v3 Announce Type: replace-cross Abstract: Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that favor
arXiv:2506.11067v3 Announce Type: replace Abstract: Objective: Develop a cost-effective, large language model (LLM)-based pipeline for automatically extracting Review of Systems (ROS) entities from clinical notes. Materials and Methods: The pipeline extracts ROS section from the clinical note using
arXiv:2604.13077v1 Announce Type: new Abstract: Coronary angiography (CAG) reports contain clinically relevant physiological measurements, yet this information is typically in the form of unstructured natural language, limiting its use in research. We investigate the use of Large Language Models (LL
arXiv:2604.07663v1 Announce Type: new Abstract: The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's size. Although light-state optimizers like SinkGD attempt to address this issue, we identify the embedd
arXiv:2603.27006v1 Announce Type: cross Abstract: Large language models produce em dashes at varying rates, and the observation that some models "overuse" them has become one of the most widely discussed markers of AI-generated text. Yet no mechanistic account of this pattern exists, and the paralle