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
Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Disti…
arXiv cs.AI Research & Papers
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
arXiv cs.AI Research & Papers
Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHi…
arXiv cs.AI Research & Papers
Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipu…
arXiv cs.AI Research & Papers
NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
arXiv cs.AI Research & Papers
Back to the Future: A workbook time machine for spread sheet creation benchmarks
arXiv cs.AI Research & Papers
DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task L…
arXiv cs.AI Research & Papers
Scale-to-Dialogue: Low-Burden Elicitation of Daily Premenstrual Symptom Ratings with Smal…
arXiv cs.AI Research & Papers
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
arXiv cs.AI Research & Papers
Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction
arXiv cs.AI Research & Papers
FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Mo…
arXiv cs.AI Research & Papers
Improving Generalization Robustness of Multimodal RLVR
arXiv cs.AI Research & Papers
Open-World Hierarchical Perception: Taxonomic Abstraction over Class-Agnostic Proposals f…
arXiv cs.AI Research & Papers
LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models
arXiv cs.AI Research & Papers
Evidence-RL: Towards Evidence-intensive Visual Reasoning
arXiv cs.AI Research & Papers
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questi…
arXiv cs.AI Research & Papers
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States
arXiv cs.AI Research & Papers
EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
arXiv cs.AI Research & Papers
Second Order Drifting Models
arXiv cs.AI Research & Papers
BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusio…
arXiv cs.AI Research & Papers
Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safe…
arXiv cs.AI Research & Papers
Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Ch…
arXiv cs.AI Research & Papers
FSTC-Encoder: Feature--Spatial--Temporal Correlation Learning for Generalizable RF Sensing
arXiv cs.AI Research & Papers
Full-bandwidth transformer
arXiv cs.AI Research & Papers
Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression
arXiv cs.AI Research & Papers
Abstracted Away: Resisting Alienation and Ungrounded Abstraction in AI Research Communiti…
arXiv cs.AI Research & Papers
SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills
arXiv cs.AI Research & Papers
Guixu: Valuation-Driven Data Discovery for Autonomous AI Agents with On-Chain Attestation
arXiv cs.AI Research & Papers
LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Langu…
arXiv cs.AI Research & Papers
An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadr…