Español

Explorar

Noticias de IA

29636 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
Hybrid Probabilistic Forecasting of Under-Five Malaria Admissions in Ghana: A Gaussian Pr…
arXiv cs.AI Research & Papers
RefDiffNet: Learning to Expose Subtle PCB Defects Before Detection
arXiv cs.AI Research & Papers
From Cues to Horizons: Dynamic Risk Horizon Profiling for Trajectory Prediction
arXiv cs.AI Research & Papers
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
arXiv cs.AI Research & Papers
Task diversity produces systematic transfer but inhibits continual reinforcement learning
arXiv cs.AI Research & Papers
MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models
arXiv cs.AI Research & Papers
Accuracy, Stability, and Repeated-Run Reliability of Large Language Models on Determinist…
arXiv cs.AI Research & Papers
Detection vs. Execution: Single-Bucket Probes Miss Half the Mamba-2 State Sink
arXiv cs.AI Research & Papers
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-…
arXiv cs.AI Research & Papers
Lodestar: An Online-Learning LLM Inference Router
arXiv cs.AI Research & Papers
Explainable deep reinforcement learning reveals energy-efficient control strategies for t…
arXiv cs.AI Research & Papers
SS-ZKR: Spatial-Semantic Zero-Knowledge Routing for Privacy-Preserving Multi-Agent Collab…
arXiv cs.AI Research & Papers
Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Infe…
arXiv cs.AI Research & Papers
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D …
arXiv cs.AI Research & Papers
AI-IoT-Robotics Integration: Survey of Frameworks, Emerging Trends, and the Path Toward C…
arXiv cs.AI Research & Papers
PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages an…
arXiv cs.AI Research & Papers
Data Collection for Training Quality-Control AI in Carpet Manufacturing
arXiv cs.AI Research & Papers
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
arXiv cs.AI Research & Papers
Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation
arXiv cs.AI Research & Papers
OPD+: Rethinking the Advantage Design for On-Policy Distillation
arXiv cs.AI Research & Papers
3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code
arXiv cs.AI Research & Papers
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Lang…
arXiv cs.AI Research & Papers
Leyline: KV Cache Directives for Agentic Inference
arXiv cs.AI Research & Papers
Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model…
arXiv cs.AI Research & Papers
Strong Stochastic Flow Maps
arXiv cs.AI Research & Papers
A Fiber Criterion for Representation Identifiability in Supervised Learning
arXiv cs.AI Research & Papers
Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA
arXiv cs.AI Research & Papers
MiCU: End-to-End Smart Home Command Understanding with Large Language Model
arXiv cs.AI Research & Papers
HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
arXiv cs.AI Research & Papers
STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing