Español

Explorar

Noticias de IA

22318 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
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
arXiv cs.AI Research & Papers
Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders
arXiv cs.AI Research & Papers
Which Algorithm Specification Formats Help Language Models Implement Machine Learning Alg…
arXiv cs.AI Research & Papers
The Role of Prompt Language and Translation-Theory-Driven Prompts in Large Language Model…
arXiv cs.AI Research & Papers
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
arXiv cs.AI Research & Papers
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
arXiv cs.AI Research & Papers
Generative wave propagator
arXiv cs.AI Research & Papers
AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Ac…
arXiv cs.AI Research & Papers
Scalable Maximal Frequent Episode Mining with Desbordante
arXiv cs.AI Research & Papers
Robustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier
arXiv cs.AI Research & Papers
Graph Neural Networks are Heuristics
arXiv cs.AI Research & Papers
Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Att…
arXiv cs.AI Research & Papers
A Bayesian Framework for Evaluating Scenario Compatibility in Generative Population Synth…
arXiv cs.AI Research & Papers
SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Ma…
arXiv cs.AI Research & Papers
Efficient Perception in Automotive Detection and Tracking Using Neuromorphic Computing
arXiv cs.AI Research & Papers
Joint Velocity Slope Diffusion Prior for Structurally Constrained Velocity Model Building
arXiv cs.AI Research & Papers
Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensit…
arXiv cs.AI Research & Papers
Self-Specializing Vision-Language Transmon Chip Calibration in a Physics-Grounded Environ…
arXiv cs.AI Research & Papers
CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillat…
arXiv cs.AI Research & Papers
Failures and Successes to Learn a Core Conceptual Distinction from the Statistics of Lang…
arXiv cs.AI Research & Papers
Lyapunov-Guided Training for Hardware-Safe Neural Networks Under Fixed-Point Arithmetic
arXiv cs.AI Research & Papers
Mask2Real-WM: Segmentation Masks as a Sim-to-Real Bridge for Controllable Dexterous World…
arXiv cs.AI Research & Papers
EEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection
arXiv cs.AI Research & Papers
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual…
arXiv cs.AI Research & Papers
Mask-based Predictive Representations for Reinforcement Learning
arXiv cs.AI Research & Papers
RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba…
arXiv cs.AI Research & Papers
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent P…
arXiv cs.AI Research & Papers
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
arXiv cs.AI Research & Papers
Builder, Defender, Breaker: The Case Against Removing the Human from the AI-Driven Securi…
arXiv cs.AI Research & Papers
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-…