Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Models & Releases
Instella-MoE Technical Report
arXiv cs.AI Research & Papers
From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Unders…
arXiv cs.AI Research & Papers
DualStake: Dual-Path Confidence Calibration in Deep Research Agents
Bloomberg Technology Industry Moves
AI Data Center Spending to Reach $32 Trillion by 2050, PwC Says
arXiv cs.AI Research & Papers
Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Sear…
arXiv cs.AI Research & Papers
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided C…
arXiv cs.AI Research & Papers
Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generati…
arXiv cs.AI Research & Papers
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
arXiv cs.AI Research & Papers
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
arXiv cs.AI Research & Papers
CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training
arXiv cs.AI Research & Papers
Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance
arXiv cs.AI Research & Papers
A Mathematical Theory of Reusable Neural Bases for Network Compression
arXiv cs.AI Security & Safety
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
arXiv cs.AI Security & Safety
The Safeguard Worked. Is the LLM System Safer?
arXiv cs.AI Research & Papers
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Hete…
arXiv cs.AI Research & Papers
Probabilistic Model Checking of Autoregressive Neural Sequence Models
arXiv cs.AI Research & Papers
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
arXiv cs.AI Research & Papers
Intelligent Edge Computing
arXiv cs.AI Research & Papers
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target …
arXiv cs.AI Research & Papers
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation an…
arXiv cs.AI Research & Papers
WiseSpec: Requirements-Driven Agents for Code Generation
arXiv cs.AI Research & Papers
Replacing Training with Memory: Listwise Selection for Text-to-SQL
arXiv cs.AI Research & Papers
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel …
arXiv cs.AI Research & Papers
Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy
arXiv cs.AI Research & Papers
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
arXiv cs.AI Research & Papers
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
arXiv cs.AI Research & Papers
RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
arXiv cs.AI Research & Papers
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Lan…
arXiv cs.AI Research & Papers
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Eviden…
arXiv cs.AI Research & Papers
Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation