Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
arXiv cs.AI Research & Papers
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
arXiv cs.AI Research & Papers
Fair Stable Matching: A Nash Social Welfare Approach
arXiv cs.AI Research & Papers
Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization Gap
Hugging Face Blog Research & Papers
Training a coding model to paint watercolours with TRL and OpenEnv
Hugging Face Blog Research & Papers
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
Wired AI Research & Papers
These Russian Mathematicians Taught AI Models How to Talk to Each Other Without Using Wor…
AI News Research & Papers
Motional and MIT AI explains self-driving car decisions
Hacker News (AI filter) Research & Papers
Three sites made 215,128 “best software” pages for AI. Perplexity cites them
arXiv cs.AI Research & Papers
ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback
arXiv cs.AI Research & Papers
Figures as Programs: Recursive Generation of Editable Scientific Figures
arXiv cs.AI Research & Papers
AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, …
arXiv cs.AI Research & Papers
Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs
arXiv cs.AI Research & Papers
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
arXiv cs.AI Research & Papers
One Prompt Is Enough: Watermark Laundering Through Foundation Image Models
arXiv cs.AI Research & Papers
ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation
arXiv cs.AI Research & Papers
Causal Probing for Internal Visual Representations in Multimodal Large Language Models
arXiv cs.AI Research & Papers
SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
arXiv cs.AI Research & Papers
FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satell…
arXiv cs.AI Research & Papers
Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowl…
arXiv cs.AI Research & Papers
LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Result…
arXiv cs.AI Research & Papers
Value Over Language Model: Detecting Original Contribution in Writing
arXiv cs.AI Research & Papers
Compositional Machine Design as Program Synthesis with LLMs
arXiv cs.AI Research & Papers
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Dom…
arXiv cs.AI Research & Papers
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents
arXiv cs.AI Research & Papers
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
arXiv cs.AI Research & Papers
Rethinking Learnability in Offline Data-driven Optimization
arXiv cs.AI Research & Papers
TempCloze: Can Video-LLMs Identify the Missing Middle?
arXiv cs.AI Research & Papers
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
arXiv cs.AI Research & Papers
Provably Safe Sim-to-Real Transfer