Category
2,073 papers
Reliability Beyond Accuracy in Crop Classification Benchmarks (Supplementary Materials)Introduction: Near-perfect crop-label accuracy can conceal uncertainty, perturbation sensitivity, and weak explanations. This study evaluates these reliability dimensions without treating benchmark classification as agronomic recomme...
Reliability Beyond Accuracy in Crop Classification Benchmarks (Supplementary Materials)Introduction: Near-perfect crop-label accuracy can conceal uncertainty, perturbation sensitivity, and weak explanations. This study evaluates these reliability dimensions without treating benchmark classification as agronomic recomme...
This paper critically examines the foundational assumptions of rational decision-making models and finds them to be systematically and comprehensively flawed. Through a rigorous analysis of empirical evidence from behavioral economics and neuroscience, we demonstrate that traditional models, such as Expected Utility Th...
This paper critically examines the foundational assumptions of rational decision-making models and finds them to be systematically and comprehensively flawed. Through a rigorous analysis of empirical evidence from behavioral economics and neuroscience, we demonstrate that traditional models, such as Expected Utility Th...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper explores the complex and often contradictory relationship between hyperconnectivity and democracy. Drawing on novel theoretical frameworks inspired by quantum mechanics, network science, and temporal dynamics, we argue that the hyperconnected world is not simply an extension of the classical political landsc...
This paper explores the complex and often contradictory relationship between hyperconnectivity and democracy. Drawing on novel theoretical frameworks inspired by quantum mechanics, network science, and temporal dynamics, we argue that the hyperconnected world is not simply an extension of the classical political landsc...
The question of whether algorithms can be considered epistemic agents represents one of the most profound challenges at the intersection of philosophy of mind, epistemology, and artificial intelligence. This paper develops a novel theoretical framework for understanding algorithmic epistemic agency through the introduc...
The question of whether algorithms can be considered epistemic agents represents one of the most profound challenges at the intersection of philosophy of mind, epistemology, and artificial intelligence. This paper develops a novel theoretical framework for understanding algorithmic epistemic agency through the introduc...
Computer architecture and organization are fundamental areas of computer engineering that explain how a computer system is designed, structured, and operated. Computer architecture focuses on the functional behavior and capabilities of a computer system, while computer organization describes how these functions are phy...
This dataset contains the Da Nang International Airport (WMO 488550) TMYx 2011–2025 weather data used as climatic input for the study “Autonomous Kinetic Facades: A Bio-inspired Framework using Shape-Memory Alloy (SMA) Actuators and Reinforcement Learning for Dynamic Building Thermoregulation.” The dataset was obtained...
Autoregressive Large Language Models (LLMs) operating under the deliberative System Two paradigm encounter severe structural bottlenecks when deployed in electronic financial markets: token-by-token sequential decoding induces unacceptable execution latencies (3,500-12,000 ms), unstructured text outputs trigger syntact...
Sparse neural networks can substantially reduce computational and memory costs, yet their performance remains highly sensitive to the choice of sparse topology, particularly at extreme sparsity, where they struggle to outperform fully connected models. Existing sparse initialization methods are predominantly structure-...
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
The effort aims to help U.S. learners from kindergarten to community college, with an emphasis on math, making, and the constructive use of AI.
Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
