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
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
arXiv cs.AI Research & Papers
A geometric and deep learning reproducible pipeline for monitoring floating anthropogenic…
arXiv cs.AI Research & Papers
EngTrace: A Symbolic Benchmark for Verifiable Process Supervision of Engineering Reasoning
arXiv cs.AI Research & Papers
EmoFSM: A Finite State Machine for Emotional Support Conversation
arXiv cs.AI Research & Papers
SSIL: Self-Supervised Imitation Learning for End-to-End Driving
arXiv cs.AI Research & Papers
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
arXiv cs.AI Policy & Regulation
Retrofitters, pragmatists and activists: Public interest litigation for accountable autom…
arXiv cs.AI Research & Papers
First, do NOHARM: towards clinically safe large language models
arXiv cs.AI Research & Papers
When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval
arXiv cs.AI Research & Papers
Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
arXiv cs.AI Research & Papers
Mordal: Automated Pretrained Model Selection for Vision Language Models
arXiv cs.AI Research & Papers
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
arXiv cs.AI Research & Papers
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
arXiv cs.AI Research & Papers
Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Rein…
arXiv cs.AI Research & Papers
Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search
arXiv cs.AI Research & Papers
m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning
arXiv cs.AI Research & Papers
LVLMs and Humans Ground Differently in Referential Communication
arXiv cs.AI Research & Papers
Non-negative Elastic Net Decoding for Information Retrieval
arXiv cs.AI Research & Papers
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Langu…
arXiv cs.AI Research & Papers
PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
arXiv cs.AI Research & Papers
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
arXiv cs.AI Research & Papers
Optimism Stabilizes Thompson Sampling for Adaptive Inference
arXiv cs.AI Research & Papers
The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
arXiv cs.AI Research & Papers
FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Valid…
arXiv cs.AI Research & Papers
A homotopy-type-theoretic generalization of neurosymbolic inference
arXiv cs.AI Research & Papers
Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers
arXiv cs.AI Research & Papers
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow
arXiv cs.AI Research & Papers
GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Join…
arXiv cs.AI Research & Papers
Position: Modular Memory is the Key to Continual Learning Agents
arXiv cs.AI Research & Papers
Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion