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
Toward Calibrated Mixture-of-Experts Under Distribution Shift
arXiv cs.AI Research & Papers
eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization
arXiv cs.AI Research & Papers
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and …
arXiv cs.AI Research & Papers
What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
arXiv cs.AI Research & Papers
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents
arXiv cs.AI Research & Papers
Analyzing the Narration Gap in LLM-Solver Loops
arXiv cs.AI Research & Papers
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
arXiv cs.AI Research & Papers
Human Universal Grasping
arXiv cs.AI Research & Papers
How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learne…
arXiv cs.AI Research & Papers
RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning
arXiv cs.AI Research & Papers
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
arXiv cs.AI Research & Papers
Information Lattice Learning as Probabilistic Graphical Model Structure Learning
arXiv cs.AI Research & Papers
Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Dis…
arXiv cs.AI Research & Papers
Exit-and-Join Dynamics for Decentralized Coalition Formation
arXiv cs.AI Research & Papers
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
arXiv cs.AI Research & Papers
Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, a…
arXiv cs.AI Research & Papers
Which Pairs to Compare for LLM Post-Training?
arXiv cs.AI Research & Papers
Modularity-Free Conflict-Averse Training for Generalized PINNs
arXiv cs.AI Research & Papers
ProMUSE: Progressive Multi-modal Uncertainty-guided Staged Evidential Alzheimer Disease C…
arXiv cs.AI Research & Papers
Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Re…
arXiv cs.AI Research & Papers
Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
arXiv cs.AI Research & Papers
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
arXiv cs.AI Research & Papers
Process-Verified Reinforcement Learning for Theorem Proving via Lean
arXiv cs.AI Research & Papers
Toten: Knowledge-Based Ontological Tokenization Of Physical Quantities And Technical Nota…
arXiv cs.AI Research & Papers
Ensembles of Large Language Models for Identifying EQ-5D Studies in PubMed Based on Their…
arXiv cs.AI Research & Papers
A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representati…
arXiv cs.AI Research & Papers
Emergent Alignment
arXiv cs.AI Research & Papers
DeXposure-Claw: An Agentic System for DeFi Risk Supervision
arXiv cs.AI Research & Papers
LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model At…
arXiv cs.AI Research & Papers
Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation