Español

Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attent…
arXiv cs.AI Research & Papers
CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision
arXiv cs.AI Security & Safety
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
arXiv cs.AI Security & Safety
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
arXiv cs.AI Research & Papers
Pretrained self-supervised speech models can recognize unseen consonants
arXiv cs.AI Research & Papers
Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices
arXiv cs.AI Research & Papers
LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems
arXiv cs.AI Research & Papers
Model-Based and Data-Driven Hierarchical Control and Topology Co-Design for Robust Networ…
arXiv cs.AI Research & Papers
Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs
arXiv cs.AI Research & Papers
Artificial Intelligence in Ship Finance: Applications, Opportunities, and a Case Study in…
arXiv cs.AI Research & Papers
Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LL…
arXiv cs.AI Research & Papers
EKF-Based Depth Camera and Deep Learning Fusion for UAV-Person Distance Estimation and Fo…
arXiv cs.AI Research & Papers
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded…
arXiv cs.AI Research & Papers
PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Sp…
arXiv cs.AI Research & Papers
OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins
arXiv cs.AI Security & Safety
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranki…
arXiv cs.AI Research & Papers
Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation
arXiv cs.AI Research & Papers
Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Be…
arXiv cs.AI Research & Papers
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
arXiv cs.AI Research & Papers
The Standard Interpretable Model: A general theory of interpretable machine learning to d…
arXiv cs.AI Research & Papers
Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark …
arXiv cs.AI Research & Papers
Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Brid…
arXiv cs.AI Research & Papers
Harness In-Context Operator Learning with Chain of Operators
arXiv cs.AI Research & Papers
StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery
arXiv cs.AI Research & Papers
ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories
arXiv cs.AI Research & Papers
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Mo…
arXiv cs.AI Research & Papers
From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Mul…
arXiv cs.AI Research & Papers
Information-Theoretic Decomposition for Multimodal Interaction Learning
arXiv cs.AI Research & Papers
When Context Returns: Toward Robust Internalization in On-Policy Distillation
arXiv cs.AI Research & Papers
LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scal…