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
From Collaboration to Capability: Internalizing Routed LLM Experts into Compact Reasoners
arXiv cs.AI Research & Papers
Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geom…
arXiv cs.AI Research & Papers
MPT: Missing Prototype Tracking via Barycentric Reconstruction in Vehicular Federated Lea…
arXiv cs.AI Research & Papers
Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf
arXiv cs.AI Research & Papers
How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and…
arXiv cs.AI Research & Papers
Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterpr…
arXiv cs.AI Research & Papers
Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references,…
arXiv cs.AI Research & Papers
Niching Agents in The Core
arXiv cs.AI Research & Papers
Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers
arXiv cs.AI Research & Papers
BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI…
arXiv cs.AI Research & Papers
Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis
arXiv cs.AI Research & Papers
TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspectio…
arXiv cs.AI Research & Papers
Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Mu…
arXiv cs.AI Research & Papers
Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble …
arXiv cs.AI Research & Papers
TripPattern: A Pattern-based Text Watermarking Method for Large Language Models
arXiv cs.AI Research & Papers
Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of …
arXiv cs.AI Research & Papers
When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
arXiv cs.AI Security & Safety
SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical C…
arXiv cs.AI Research & Papers
Assisted Spatial Cognition Through Vision-Language Models
arXiv cs.AI Research & Papers
Diffusion Models and Concept Formation
arXiv cs.AI Research & Papers
Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
arXiv cs.AI Research & Papers
GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecast…
arXiv cs.AI Research & Papers
WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation
arXiv cs.AI Research & Papers
MInTRL: Off-policy Intervention can boost On-policy RL
arXiv cs.AI Research & Papers
Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach
arXiv cs.AI Research & Papers
Debiasing as a Measurement Intervention: Calibrated Ties and Resolution Loss in LLM-as-a-…
arXiv cs.AI Research & Papers
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Con…
arXiv cs.AI Research & Papers
DU-NO: A Parameter-Efficient Double U-Shaped Neural Operator for Phase-Resolving Wave Mod…
arXiv cs.AI Research & Papers
Automated Detection and Structuring of Social Tipping Point Evidence in Climate related D…
arXiv cs.AI Research & Papers
DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense P…