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
CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs
arXiv cs.AI Research & Papers
Can Interpretation Predict Behavior on Unseen Data?
arXiv cs.AI Research & Papers
SEER: Supervised Learning to Control Energetic Reasoning
arXiv cs.AI Research & Papers
Expected Free Energy as Belief-Dependent Utility for rho-POMDPs
arXiv cs.AI Research & Papers
Capacity and Redundancy Trade-offs in Multi-Task Learning
arXiv cs.AI Research & Papers
DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance…
arXiv cs.AI Research & Papers
PriorProof: A Point-in-Time Measure of Technique Novelty for Formal Proofs
arXiv cs.AI Research & Papers
Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Aut…
arXiv cs.AI Research & Papers
Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking
arXiv cs.AI Research & Papers
Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation D…
arXiv cs.AI Research & Papers
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode …
arXiv cs.AI Research & Papers
When LLMs Over-Answer: Measuring and Mitigating Quality Issues in LLM-Based Hardware Desc…
arXiv cs.AI Research & Papers
Nonuniformity Principle in Human-AI Coworking
arXiv cs.AI Research & Papers
From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence
arXiv cs.AI Research & Papers
ETAS: An Effect-Typed Language for Agent Systems
arXiv cs.AI Research & Papers
SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift
arXiv cs.AI Research & Papers
Generalised Bellman recurrence and three dualities in sequential decision-making
arXiv cs.AI Research & Papers
Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning
arXiv cs.AI Research & Papers
OpenMHC: Accelerating the Science of Wearable Foundation Models
arXiv cs.AI Research & Papers
The Failures of Marginal Influence-Based Attribution Methods for Global Time Series Expla…
arXiv cs.AI Research & Papers
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation…
arXiv cs.AI Research & Papers
Agent psychometrics: Task-level performance prediction in agentic coding benchmarks
arXiv cs.AI Research & Papers
From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?
arXiv cs.AI Research & Papers
Some Large Language Models Exhibit Consistent Risk Attitudes
arXiv cs.AI Research & Papers
A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges
arXiv cs.AI Research & Papers
DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection fo…
arXiv cs.AI Research & Papers
VideoSEMA: a scalable and efficient Mamba-like attention for video understanding
arXiv cs.AI Research & Papers
COLIP-2: Olfaction-Vision-Language Embeddings
arXiv cs.AI Research & Papers
Mobile Network Control with a World Model
arXiv cs.AI Research & Papers
PEARL: Auditable Repair for Scientific Reasoning Graph Extraction