Español

Explorar

Noticias de IA

27413 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
Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fi…
arXiv cs.AI Research & Papers
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
arXiv cs.AI Research & Papers
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstr…
arXiv cs.AI Research & Papers
From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning
arXiv cs.AI Research & Papers
IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent…
arXiv cs.AI Research & Papers
NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models…
arXiv cs.AI Research & Papers
The Bioelectrical Information Theory: Investigating the theoretical compression limit of …
arXiv cs.AI Research & Papers
Integrated Real-Time Motion Tracking and AI Analysis for Athletic Performance Optimization
arXiv cs.AI Research & Papers
Aesthetic Perspectives in Information Systems Research: A Hermeneutic Analysis
arXiv cs.AI Research & Papers
$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems
arXiv cs.AI Research & Papers
Pareto-Guided Teacher Alignment for Fair Personalized Text Generation
arXiv cs.AI Research & Papers
FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Project…
arXiv cs.AI Research & Papers
Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Eme…
arXiv cs.AI Research & Papers
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogat…
arXiv cs.AI Research & Papers
Duality for Optimal Multi-Item, Multi-Bidder Auction Design: Revenue Certificates through…
arXiv cs.AI Research & Papers
Benchmarking Knowledge Editing using Logical Rules
arXiv cs.AI Research & Papers
Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
arXiv cs.AI Research & Papers
A Theory on Flow Matching with Neural Networks
arXiv cs.AI Research & Papers
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
arXiv cs.AI Research & Papers
A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchma…
arXiv cs.AI Research & Papers
Interactions Between Crosscoder Features: A Compact Proofs Perspective
arXiv cs.AI Research & Papers
When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff
arXiv cs.AI Research & Papers
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
arXiv cs.AI Research & Papers
A Note on the Strategic Confinement Problem
arXiv cs.AI Research & Papers
Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment
arXiv cs.AI Research & Papers
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid …
arXiv cs.AI Research & Papers
Regimes: An Auditable, Held-Out-Gated Improvement Loop Demonstrated on LongMemEval with A…
arXiv cs.AI Research & Papers
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderatio…
arXiv cs.AI Research & Papers
Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampl…
arXiv cs.AI Research & Papers
Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification i…