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
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
arXiv cs.AI Research & Papers
SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recogni…
arXiv cs.AI Research & Papers
Prompt Coverage Adequacy
arXiv cs.AI Research & Papers
Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum D…
arXiv cs.AI Research & Papers
SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses
arXiv cs.AI Research & Papers
Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving
arXiv cs.AI Research & Papers
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
arXiv cs.AI Research & Papers
Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science …
arXiv cs.AI Research & Papers
Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
arXiv cs.AI Research & Papers
PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
arXiv cs.AI Research & Papers
CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery
arXiv cs.AI Research & Papers
AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanati…
arXiv cs.AI Research & Papers
Low-Latency Task-Oriented Image Transmission with Opportunistic Spectrum Access
arXiv cs.AI Research & Papers
TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B
arXiv cs.AI Research & Papers
SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs
arXiv cs.AI Research & Papers
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
arXiv cs.AI Research & Papers
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models
arXiv cs.AI Research & Papers
Has This Checkpoint Been Abliterated? A Two-Signal Audit and Its Failure Map
arXiv cs.AI Research & Papers
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
arXiv cs.AI Research & Papers
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts M…
arXiv cs.AI Research & Papers
Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent…
arXiv cs.AI Research & Papers
Single-Channel EEG-Based Cognitive Load Assessment in Online Learning: A Hybrid Deep Lear…
arXiv cs.AI Research & Papers
Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
arXiv cs.AI Research & Papers
EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning
arXiv cs.AI Research & Papers
ProCal: Inference-Time Proposal Calibration for Open-Vocabulary Object Detection
arXiv cs.AI Research & Papers
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understa…
arXiv cs.AI Research & Papers
Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection f…
arXiv cs.AI Research & Papers
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbr…
arXiv cs.AI Research & Papers
Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cyb…
arXiv cs.AI Research & Papers
AgenticDataBench: A Comprehensive Benchmark for Data Agents