arXiv:2407.10735v3 Announce Type: replace Abstract: This paper investigates the ontological characterization of Large Language Models (LLMs) like ChatGPT. Between inflationary and deflationary accounts, we pay special attention to their status as agents. This requires explaining in detail the architecture, processing, and training procedures that enable LLMs to display their capacities, and the extensions used to […]
Conditioning LLMs to Generate Code-Switched Text
arXiv:2502.12924v3 Announce Type: replace-cross Abstract: Code-switching (CS) is still a critical challenge in Natural Language Processing (NLP), due to the limited availability of large-scale, diverse CS datasets for robust training and evaluation. Despite recent advances, the capabilities and limitations of LLMs in handling CS are still not fully understood. In this work, we investigate the […]
CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
arXiv:2510.13669v2 Announce Type: replace-cross Abstract: Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames, video MAR models often produce highly distorted outputs due to the lack of a structured global prior, especially […]
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
arXiv:2603.06302v1 Announce Type: cross Abstract: As Vision-Language Models (VLMs) become increasingly sophisticated and widely used, it becomes more and more crucial to understand their decision-making process. Traditional explainability methods, designed for classification tasks, struggle with modern autoregressive VLMs due to their complex token-by-token generation process and intricate interactions between visual and textual modalities. We present […]
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
arXiv:2603.05860v1 Announce Type: new Abstract: Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their decisions through a sequence of specialized procedures. While LLM-based agents promise to orchestrate such heterogeneous medical tools, existing systems treat tool sets and invocation strategies as static after deployment. […]
ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code
arXiv:2603.06365v1 Announce Type: cross Abstract: AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review with large language models often suffers from uneven coverage, weak reproducibility, unsupported findings, and the absence of an immutable […]
Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum
arXiv:2603.05614v1 Announce Type: new Abstract: Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governance constraints. This article shows that the structure of service-dependency graphs, modelled as DAGs whose nodes represent compute stages and whose edges […]
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
arXiv:2603.05904v1 Announce Type: cross Abstract: GPU design space exploration (DSE) for modern AI workloads, such as Large-Language Model (LLM) inference, is challenging because of GPUs’ vast, multi-modal design spaces, high simulation costs, and complex design optimization objectives (e.g. performance, power and area trade-offs). Existing automated DSE methods are often prohibitively expensive, either requiring an excessive […]
The Impact of Neglecting Vaccine Unwillingness in Epidemiology Models
arXiv:2603.05626v1 Announce Type: new Abstract: With significant population fractions in many societies who refuse vaccines, it is important to reconsider how vaccination is incorporated into compartmental epidemiology models. It is still most common to apply the vaccination rate to the entire class of susceptibles, rather than to use the more realistic assumption that the vaccination […]
Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
arXiv:2603.05950v1 Announce Type: cross Abstract: Visual token reduction is critical for accelerating Vision-Language Models (VLMs), yet most existing approaches rely on a fixed budget shared across all inputs, overlooking the substantial variation in image information density. We propose E-AdaPrune, an energy-driven adaptive pruning framework that determines the token budget from the singular value spectrum of […]
Behavior-dLDS: A decomposed linear dynamical systems model for neural activity partially constrained by behavior
arXiv:2603.05612v1 Announce Type: new Abstract: Brain-wide recordings of large-scale networks of neurons now provide an unprecedented view into how the brain drives behavior. However, brain activity contains both information directly related to behavior as well as the potential for many internal computations. Moreover, observable behavior is executed not only by the brain, but also by […]
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
arXiv:2603.06001v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies. However, their reliability under Out-of-Distribution (OOD) instructions remains underexplored. In this paper, we reveal a critical failure mode in which VLA policies continue executing visually […]