Researchers have developed EchoCoT, a method that can extract hidden chain-of-thought (CoT) traces from large reasoning models. These CoTs are valuabl...
Researchers have proposed a method to optimize hyperparameters for large-scale Mixture-of-Experts (MoE) models. The approach involves two steps: first...
Researchers have developed a new framework called SABET-QA for answering questions based on temporal knowledge graphs. These graphs contain time-sensi...
Researchers have proposed a framework called Evidence Acquisition and Feasibility Gating (EAFG) to improve the performance of robots executing long-ho...
Researchers have developed an AI framework called AdaPT that enables humanoid robots to learn professional tennis serving and rally styles from broadc...
Researchers have developed a new approach to artificial immune networks (AINs) that can learn from images without needing labels or backpropagation. T...
Researchers have developed a new approach to optimizing the performance of large language models (LLMs) called Task-CoEvolve. The method involves sele...
Researchers have proposed a standardized framework for evaluating the performance of machine learning-based power system protection systems. The frame...
Researchers have developed a framework called Multi-Method Causal Evidence Synthesis (MCES) to analyze observational data and identify potential cause...
Researchers have developed Daedalus-150M, a hybrid AI model that combines convolutional neural networks with attention mechanisms. Designed for CPU in...
Researchers conducted a study on how autonomous coding agents interact with technical documentation. They analyzed two public datasets containing over...
Researchers have developed a new method called Prompt-Conditioned Channel Attention (PCCA) to improve anatomically plausible segmentation in medical i...