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
LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimizat…
arXiv cs.AI Research & Papers
Learning with Boolean threshold functions
arXiv cs.AI Research & Papers
Physics-Knowledge-Guided Hybrid Neural Learning for Arctic Sea Ice Concentration Evolutio…
arXiv cs.AI Research & Papers
Consistency Is Not Coherence: Orientation Search for Certified Alignments Between 4D Defe…
arXiv cs.AI Research & Papers
The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory
arXiv cs.AI Research & Papers
Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints
arXiv cs.AI Research & Papers
Correcting a learned physical invariant improves world-model rollouts
arXiv cs.AI Research & Papers
Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, a…
arXiv cs.AI Research & Papers
AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Metho…
arXiv cs.AI Research & Papers
ParallelWorld: Test-Time Scaling for Embodied Reasoning
arXiv cs.AI Research & Papers
Redteaming Leading Arabic LLMs with ASAS
arXiv cs.AI Research & Papers
Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks
arXiv cs.AI Research & Papers
ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings
arXiv cs.AI Research & Papers
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
arXiv cs.AI Research & Papers
ATHENA: Knowledge-guided agentic neural architecture search for AutoFormer-based electron…
arXiv cs.AI Research & Papers
ReasonEdit: Editing Vision-Language Models using Human Reasoning
arXiv cs.AI Research & Papers
Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric
arXiv cs.AI Research & Papers
Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation
arXiv cs.AI Research & Papers
Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of S…
arXiv cs.AI Research & Papers
Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings
arXiv cs.AI Research & Papers
Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling
arXiv cs.AI Research & Papers
KONTOGRAPH: Verified Point-in-Time Feature Consistency and Amortised Explanation for Real…
arXiv cs.AI Research & Papers
TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimizat…
arXiv cs.AI Research & Papers
Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Bound…
arXiv cs.AI Research & Papers
Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior …
arXiv cs.AI Research & Papers
Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities
arXiv cs.AI Research & Papers
Power-Performance Characterization of TinyML Systems
arXiv cs.AI Research & Papers
MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance
arXiv cs.AI Research & Papers
SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale
arXiv cs.AI Research & Papers
CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance