Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
An Uncertainty-Aware Resilience Micro-Agent for Causal Observability in the Computing Con…
Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experim…
Teaching Through Analogies: A Modular Pipeline for Educational Analogy Generation
Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Appl…
Unlocking Apple's Private Cloud Compute: An Analysis of Privacy-Preserving Artificial Int…
GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Ge…
Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Cl…
An Interactive Paradigm for Deep Research
CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Represe…
Side-by-side Comparison Amplifies Dialect Bias in Language Models
Assessing the Operational Viability of Foundation Models for Time Series Forecasting
Generative OOD-regularized Model-based Policy Optimization
Robust Fuzzy Multi-view Learning under View Conflict
Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centrali…
Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems
Prism: Spectral-Aware Block-Sparse Attention
Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Mod…
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Fo…
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point
How Well Do Models Follow Their Constitutions?
Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmar…
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to …
Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Ad…
StakeBench: Evaluating Language Understanding Grounded in Market Commitment
Inference Time Context Sparsity: Illusion or Opportunity?