The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Learning Moral Diversity: Modelling Individual Perspectives in Moral Classification of Te…
Error Highways: Scaling Predictive Coding to Very Deep Networks
GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation
Generative Relightable Avatars
Confident but Conflicted: Internal Uncertainty and Cognitive Dissonance Resolution in LLMs
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach …
Automated sign detection across the Electronic Babylonian Library: A large-scale dataset …
Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on Gener…
Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in S…
Grounded Scaling: Why Agentic AI Needs Deterministic Environments
FetSelect: Task-Specific Architectures and Self-Supervised Learning for Automated Fetal U…
ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models
Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form G…
Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubi…
Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Time…
Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
Multi-cancer detection using a computationally efficient CNN with transfer learning
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Rein…
Large Language Model-Assisted Cleaning of Report-Derived Labels in a Large-Scale Chest CT…
ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation
Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance
How Does Research Evolve? Tracing Cross-Domain Trajectories in NLP, ML, and CV with Claim…
Null-Calibrated Conformal Selection via Target-Membership Scores
Building reliable agentic AI systems
Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribu…
Active Sensing and Deferred-Decision Trajectory Optimization for Robust Target Identifica…
Learning a Normal World Model for Few-Shot Boundary-Calibrated Abnormality Detection