DeadPool: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Lea…
Online Segment 3D Gaussians via Launching Virtual Drones
Profit-Based Counterfactual Explanations for Product Improvement: A Case Study of Manga S…
SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Int…
SemHash-LLM: A Multi-Granularity Semantic Hashing Framework for Document Deduplication
MVFusion-GS: Motion-Variance Guided Temporal Attention for High-Quality Dynamic Gaussian …
Boosting Infrared Small Target Detection via Logit-Domain Contrast and Adaptive Shape Ref…
Evolutionary Feature Engineering for Structured Data
Autoresearch: The feedback loop behind self-improving agents
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Expl…
Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of…
Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes
Risk Architecture for AI-Native Engineering Teams: An Organizational Framework for Agenti…
The Wiola Architecture for Efficient Small Language Models
Multi-Objective Exploration and Preference Optimization via Mutual Information
Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Lev…
HippoRAG: Neurobiologically inspired RAG using Amazon Bedrock, Amazon Neptune, and person…
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Acti…
Accelerate protein design with BoltzGen on Amazon SageMaker AI
Quantum vs. Classical Machine Learning: A Unified Empirical Comparison
Optimal Resource Utilization for Autonomous Laboratory Orchestrators
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling
Why Three AI Labs Suddenly Started Building Scientific Infrastructure
How AI agents can train their own skills
EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization