Español

Explorar

Noticias de IA

21270 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
Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry
arXiv cs.AI Research & Papers
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
arXiv cs.AI Research & Papers
Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for…
arXiv cs.AI Research & Papers
HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
arXiv cs.AI Research & Papers
Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution
arXiv cs.AI Research & Papers
MaskFlow: Precise, Consistent and Seamless Regional Image Editing
arXiv cs.AI Research & Papers
Hidden Gauge Controls Feature Specialization in ReLU Networks
arXiv cs.AI Research & Papers
KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncert…
arXiv cs.AI Research & Papers
Progressive Content Refinement with Decaying Reward Joint LinUCB
arXiv cs.AI Research & Papers
Dueling World Models: Advantage-Style Action Channels for Common-Mode Distractor Rejection
arXiv cs.AI Research & Papers
Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Anal…
arXiv cs.AI Research & Papers
Online Monitoring and Corrective Steering of Programming Agents
arXiv cs.AI Research & Papers
Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Spar…
arXiv cs.AI Research & Papers
SoRoMoX: Fast, Differentiable, and Parallelizable Soft Robot Models
arXiv cs.AI Research & Papers
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lens…
arXiv cs.AI Research & Papers
Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning
arXiv cs.AI Research & Papers
Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separ…
arXiv cs.AI Research & Papers
Characterizing the Quality Profile of AI-Generated C++ in Production
arXiv cs.AI Research & Papers
Flowing Through States: Neural ODE Regularization for Reinforcement Learning
arXiv cs.AI Research & Papers
Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Represen…
arXiv cs.AI Research & Papers
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After…
arXiv cs.AI Research & Papers
SyncSBC: Decentralized Swarm Behavior Prediction for Synchronized Autonomous Control
arXiv cs.AI Research & Papers
CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
arXiv cs.AI Research & Papers
Risk-Aware Decision Policies for Agents Under Noisy Perception
arXiv cs.AI Research & Papers
CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent …
arXiv cs.AI Research & Papers
LyEvO: Lyapunov-Guided Evolutionary Optimization for Safe and Robust Sim-to-Real Policy L…
arXiv cs.AI Research & Papers
Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Languag…
arXiv cs.AI Research & Papers
WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Waterm…
arXiv cs.AI Research & Papers
TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade
arXiv cs.AI Research & Papers
TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation