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
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
arXiv cs.AI Research & Papers
An Effective Router for Vision-Language Model Selection
arXiv cs.AI Research & Papers
RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language…
arXiv cs.AI Research & Papers
LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended…
arXiv cs.AI Research & Papers
Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Art…
arXiv cs.AI Research & Papers
REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
arXiv cs.AI Research & Papers
ComplexConstraints and Beyond: Expert Rubrics for RLVR
arXiv cs.AI Research & Papers
DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal S…
arXiv cs.AI Research & Papers
Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language…
arXiv cs.AI Research & Papers
Vision Language Model Helps Private Information De-Identification in Vision Data
arXiv cs.AI Research & Papers
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Act…
arXiv cs.AI Research & Papers
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
arXiv cs.AI Research & Papers
Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal…
arXiv cs.AI Research & Papers
MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation
arXiv cs.AI Research & Papers
TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encode…
arXiv cs.AI Research & Papers
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolvi…
arXiv cs.AI Research & Papers
RunAgent SuperBrowser: A Theory of Autonomous Web Navigation Grounded in Human Browsing B…
arXiv cs.AI Research & Papers
Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
arXiv cs.AI Research & Papers
Capacity, Not Format: Rethinking Structured Reasoning Failures
arXiv cs.AI Research & Papers
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Inte…
arXiv cs.AI Research & Papers
SIFT: Selective-Index For Fast Compute of RAG Prefill by Exploiting Attention Invariance
arXiv cs.AI Research & Papers
AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation…
arXiv cs.AI Research & Papers
Emergent alignment and the projectability of ethical personas
arXiv cs.AI Research & Papers
Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Audita…
arXiv cs.AI Research & Papers
AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Da…
arXiv cs.AI Research & Papers
PRISM: Recovering Instruction Sets from Language Model Activations
arXiv cs.AI Research & Papers
TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs
arXiv cs.AI Research & Papers
From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design
arXiv cs.AI Research & Papers
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-Wor…
arXiv cs.AI Research & Papers
Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery