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
Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models vi…
arXiv cs.AI Research & Papers
StandardE2E: A Unified Framework for End-to-End Autonomous Driving Datasets
arXiv cs.AI Research & Papers
Self-Evolving Deep Research via Joint Generation and Evaluation
arXiv cs.AI Research & Papers
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectori…
arXiv cs.AI Research & Papers
Stochastic Sparse Attention for Memory-Bound Inference
arXiv cs.AI Research & Papers
A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks
arXiv cs.AI Security & Safety
A Systematic Investigation of RL-Jailbreaking in LLMs
arXiv cs.AI Research & Papers
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
arXiv cs.AI Research & Papers
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-…
arXiv cs.AI Research & Papers
BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
arXiv cs.AI Research & Papers
DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Mode…
arXiv cs.AI Research & Papers
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
arXiv cs.AI Security & Safety
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in A…
arXiv cs.AI Research & Papers
CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capab…
arXiv cs.AI Research & Papers
ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction i…
arXiv cs.AI Research & Papers
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
arXiv cs.AI Research & Papers
Real-Time Automatic License Plate Recognition Using YOLOv8, SORT Tracking, and Temporal D…
arXiv cs.AI Research & Papers
Treat Traffic Like Trees: A Semantic-Preserving Hierarchical Graph-Based Expert Framework…
arXiv cs.AI Research & Papers
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language M…
arXiv cs.AI Research & Papers
Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare R…
arXiv cs.AI Research & Papers
Multi-SPIN: Multi-Access Speculative Inference for Cooperative Token Generation at the Ed…
arXiv cs.AI Research & Papers
QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Ap…
arXiv cs.AI Research & Papers
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs w…
arXiv cs.AI Research & Papers
Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers
arXiv cs.AI Research & Papers
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
arXiv cs.AI Research & Papers
Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation
arXiv cs.AI Research & Papers
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
arXiv cs.AI Research & Papers
Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control
arXiv cs.AI Opinion & Editorial
Thinking Through Signs: PEEL as a Semiotic Scaffolding for Epistemically Accountable AI-E…
arXiv cs.AI Research & Papers
GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes