Español

Explorar

Noticias de IA

30313 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
Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
arXiv cs.AI Research & Papers
MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
arXiv cs.AI Research & Papers
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendati…
arXiv cs.AI Research & Papers
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
arXiv cs.AI Security & Safety
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
arXiv cs.AI Research & Papers
MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents
arXiv cs.AI Research & Papers
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic V…
arXiv cs.AI Research & Papers
FundaPod: A Multi-Persona Agent Pod Platform with Knowledge Graph Memory for AI-Assisted …
arXiv cs.AI Research & Papers
Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Bette…
arXiv cs.AI Research & Papers
Dr-CiK: A Testbed for Foresight-Driven Agents
arXiv cs.AI Research & Papers
DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation
arXiv cs.AI Research & Papers
The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
arXiv cs.AI Research & Papers
Learning Tangent Bundles and Characteristic Classes with Autoencoder Atlases
arXiv cs.AI Research & Papers
Differential syntactic and semantic encoding in LLMs
arXiv cs.AI Research & Papers
RelaxFlow: Text-Driven Amodal 3D Generation
arXiv cs.AI Research & Papers
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reason…
arXiv cs.AI Research & Papers
Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
arXiv cs.AI Security & Safety
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Dire…
arXiv cs.AI Developer Tooling
BenGER Platform: A Collaborative Web Platform for End-to-End Benchmarking of German Legal…
arXiv cs.AI Research & Papers
Retention Consequence in Lifecycle Memory Control
arXiv cs.AI Research & Papers
C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment…
arXiv cs.AI Research & Papers
Data-Efficient On-Policy Distillation for Automatic Speech Recognition
arXiv cs.AI Research & Papers
The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editing
arXiv cs.AI Research & Papers
Anatomy-Slot: Unsupervised Anatomical Factorization for Homologous Bilateral Reasoning in…
arXiv cs.AI Research & Papers
Voice "Cloning" is Style Transfer
arXiv cs.AI Research & Papers
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex…
arXiv cs.AI Research & Papers
Optimal and Diffusion Transports in Machine Learning
arXiv cs.AI Research & Papers
Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement …
arXiv cs.AI Research & Papers
You Are in Control of Your State: Why Human Outcomes Are Controllable Through Causal Stat…
arXiv cs.AI Research & Papers
Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language…