Español

Explorar

Noticias de IA

27413 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
Training-Free Semantic Correction for Autoregressive Visual Models
arXiv cs.AI Research & Papers
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
arXiv cs.AI Research & Papers
Concept-Constrained Prompt Learning for Few-Shot CLIP Adaptation
arXiv cs.AI Research & Papers
Context-Aware Distillation and Ablation for Text2DSL
arXiv cs.AI Research & Papers
GeoRouteNet: Geometry-Enhanced Non-Autoregressive Neural Solver for the Traveling Salesma…
arXiv cs.AI Research & Papers
SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors
arXiv cs.AI Research & Papers
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
arXiv cs.AI Research & Papers
Libretto: Giving LLM Agents a Sense of Musical Structure
arXiv cs.AI Research & Papers
Leakage-Aware Benchmarking of LLM Forecasting: Real-Time Nowcasts as the Decision-Time In…
arXiv cs.AI Research & Papers
Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in…
arXiv cs.AI Research & Papers
When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG
arXiv cs.AI Research & Papers
Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents
arXiv cs.AI Research & Papers
AutoRAS: Learning Robust Agentic Systems with Primitive Representations
arXiv cs.AI Research & Papers
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Ed…
arXiv cs.AI Research & Papers
Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach …
arXiv cs.AI Research & Papers
On the Position Bias of On-Policy Distillation
arXiv cs.AI Research & Papers
Balancing Performance and Diversity in GRPO Autoregressive Text-to-Image Post-Training
arXiv cs.AI Research & Papers
ARCO: Adaptive Rubric with Co-Evolution for Multi-Step LLM-Based Agents
arXiv cs.AI Research & Papers
The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Base…
arXiv cs.AI Research & Papers
Trip+: Benchmarking Agents in Personalized Interactive Travel Planning
arXiv cs.AI Research & Papers
Agent Behavior Mining: Generative AI Agent Governance in Business Processes
arXiv cs.AI Research & Papers
A Quantum-Assisted Agentic Distributed Artificial Intelligence Framework for Deadline-Bou…
arXiv cs.AI Research & Papers
DrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation
arXiv cs.AI Research & Papers
Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier
arXiv cs.AI Research & Papers
From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents
arXiv cs.AI Research & Papers
Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy
arXiv cs.AI Research & Papers
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
arXiv cs.AI Research & Papers
Data Evolution by Wittgenstein's Rule Following
arXiv cs.AI Research & Papers
Skill Coverage: A Test Adequacy Metric for Agent Skills
arXiv cs.AI Research & Papers
Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention