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
Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
arXiv cs.AI Research & Papers
Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control…
arXiv cs.AI Research & Papers
Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting
arXiv cs.AI Research & Papers
DSL-Topic: Improving Topic Modeling by Distilling Soft Labelsfrom Language Models
arXiv cs.AI Research & Papers
Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower …
arXiv cs.AI Research & Papers
Uncertainty-Aware End-to-End Co-Design of Neural Network Processors: From Training and Ma…
arXiv cs.AI Research & Papers
DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance
arXiv cs.AI Research & Papers
ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling
arXiv cs.AI Policy & Regulation
The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives
arXiv cs.AI Research & Papers
Unlocking Proactivity in Task-Oriented Dialogue
arXiv cs.AI Research & Papers
ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data
arXiv cs.AI Research & Papers
CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face …
arXiv cs.AI Research & Papers
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimiza…
arXiv cs.AI Research & Papers
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learni…
arXiv cs.AI Research & Papers
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retrai…
arXiv cs.AI Research & Papers
Uncertainty Estimation using Variance-Gated Distributions
arXiv cs.AI Research & Papers
ClustRecNet: A Novel End-to-End Deep Learning Framework for Clustering Algorithm Recommen…
arXiv cs.AI Research & Papers
AttnRegDeepLab: A Two-Stage Decoupled Framework for Interpretable Embryo Fragmentation Gr…
arXiv cs.AI Research & Papers
EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation
arXiv cs.AI Research & Papers
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
arXiv cs.AI Research & Papers
Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Mo…
arXiv cs.AI Research & Papers
Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization…
arXiv cs.AI Security & Safety
Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety
arXiv cs.AI Research & Papers
VAMPS: Visual-Assisted Mathematical Problem Solving Benchmark
arXiv cs.AI Research & Papers
ContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipu…
arXiv cs.AI Research & Papers
Revisiting Model Stitching In the Foundation Model Era
arXiv cs.AI Research & Papers
The Digital Apprentice: A Framework for Human-Directed Agentic AI Development
arXiv cs.AI Research & Papers
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
arXiv cs.AI Research & Papers
The Biomimetic Architecture of Software 4.0
arXiv cs.AI Research & Papers
A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and …