Researchers have found that large language models (LLMs) struggle to integrate information across long-form texts, despite growing context lengths. To...
Researchers have proposed a new framework called VISOR to improve the performance of vision-language models in tasks that require multi-step reasoning...
Researchers have developed a new method for medical image segmentation called SegWithU. It's designed to estimate the uncertainty of automated contour...
Researchers have developed a framework to recover performance in Large Language Models (LLMs) that have been degraded due to factors like catastrophic...
Researchers have developed FairNVT, a lightweight debiasing framework for transformer-based encoders. It aims to improve prediction fairness by reduci...
Researchers have found that different language models, such as Transformers and Linear RNNs, learn to represent numbers in a similar way despite being...
Researchers have developed a new AI model that can detect gaseous microemboli in real-time during cardiac surgery. The model uses a 2.5D U-Net archite...
Researchers have developed a new method called eXplainable DFT (XDFT) to identify physical mechanisms behind experiment-simulation mismatches in chemi...
Researchers have proposed a new method called SOD (Step-wise On-policy Distillation) to improve the performance of small language models in tasks that...
Researchers have proposed a framework for dynamically splitting neural network layers across edge devices and cloud infrastructure. Their approach tak...
Researchers have developed SurgicalMamba, an algorithm for online surgical phase recognition. It uses a dual-path SSD approach with two mechanisms: st...
Researchers have developed a system called EXPO-FT for fine-tuning pre-trained Vision-Language-Action (VLA) models using reinforcement learning. This ...