arXiv:2506.12374v3 Announce Type: replace-cross Abstract: Natural-language manipulation instructions specify the task goal but leave the underlying robot trajectory unspecified. We present AntiGrounding, a visual action-selection framework built…
arXiv:2505.11939v3 Announce Type: replace-cross Abstract: Electrocardiograms (ECGs) are essential non-invasive tools for diagnosing cardiovascular diseases. While recent multimodal ECG-Report contrastive learning methods have shown promise for…
arXiv:2503.15867v4 Announce Type: replace-cross Abstract: Forensic deepfake analysis demands more than binary classification: investigators need region-grounded natural language explanations they can verify against the image. Multimodal large…
arXiv:2502.17003v2 Announce Type: replace-cross Abstract: Transfer-based adversarial attacks rely on surrogate models to craft perturbations, yet often overfit the surrogate's decision boundary. To address this problem, we propose Inverse Knowledge…
arXiv:2502.11153v4 Announce Type: replace-cross Abstract: Kernel selection for regression of physical observables is often heuristic. We investigate a physics-informed strategy in which functional forms and spectral structures associated with…
arXiv:2609.16519v2 Announce Type: replace Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language access to scientific…
arXiv:2609.11286v2 Announce Type: replace Abstract: Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset. This paper describes a generator that has no real…
arXiv:2609.08082v2 Announce Type: replace Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large preference datasets. They also need direct access to the model parameters which are not provided by…
arXiv:2609.06079v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide action generation for robot control. VLMs provide hierarchical visual-semantic representations that…
arXiv:2608.21363v2 Announce Type: replace Abstract: Runtime-governance evidence often collapses materially different events into one audit record: a decision may be made, an instruction dispatched or received, an action may or may not execute, and…
arXiv:2608.17906v4 Announce Type: replace Abstract: Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We…
arXiv:2608.14227v3 Announce Type: replace Abstract: A spectral foundation model should remain useful when laboratories preprocess spectra differently. The standard test trains a classifier under one pipeline and evaluates under another, taking…
arXiv:2608.08736v2 Announce Type: replace Abstract: Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain underexplored…
arXiv:2608.05810v2 Announce Type: replace Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills…
arXiv:2607.09678v2 Announce Type: replace Abstract: When LLM agents hand information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut cost without hurting…
arXiv:2606.29871v2 Announce Type: replace Abstract: We present the AI Training Manager, a bounded LLM-based metacognitive monitoring-and-control layer for machine-learning training. The manager asynchronously observes structured telemetry from an…
arXiv:2606.29251v3 Announce Type: replace Abstract: Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they…
arXiv:2605.22866v2 Announce Type: replace Abstract: Adaptive hierarchical systems accumulate routing state as they learn which components to select. We show that this state already defines a coherent attribution over the hierarchy. A leaf receives…
arXiv:2605.18630v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities across knowledge retrieval, reasoning, code…
arXiv:2604.10513v2 Announce Type: replace Abstract: Ambiguity is an inherent property of natural-language agent specifications. When a system prompt leaves behaviour underdetermined, identical inputs follow divergent execution paths and produce…
arXiv:2603.21925v2 Announce Type: replace Abstract: In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence…
arXiv:2603.06813v3 Announce Type: replace Abstract: Ordinary decentralized multi-agent reinforcement learning presents each focal agent with a continual learning problem: peer updates change its induced rewards and dynamics even when the joint…
arXiv:2603.02540v2 Announce Type: replace Abstract: Large language models (LLMs) display a unified "general factor" of capability across 10 benchmarks (a finding confirmed by our factor analysis of 156 models), yet they still struggle with simple…
arXiv:2602.03128v2 Announce Type: replace Abstract: Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These architectural choices control execution overhead…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.