A team of researchers has developed DraftFM, a model for predicting card picks in the popular trading card game Magic: The Gathering. Unlike tradition...
Researchers have created a benchmark called VGI-BENCH to evaluate the visual intelligence of video generation models. The benchmark consists of 27 tas...
Researchers have proposed a new framework called Perception-Enhanced Alignment Direct Preference Optimization (PEA-DPO) to align large language models...
Researchers have developed a method to efficiently estimate uncertainty dynamics in text generation. They found that resampling many reasoning chains ...
Researchers have developed a benchmark called DeltaML-Bench to evaluate machine learning agents on real-world research repositories. The benchmark con...
Computing has accumulated significant technical debt over its 75-year history, exposing businesses and society to substantial risks. The use of AI-ena...
Loreley is a system for evolving programs on a repository scale using quality-diversity search. It retains complete repository states in an archive an...
Researchers have developed a method for improving the perception of underwater robots in degraded visual conditions. They used a pre-trained foundatio...
Researchers have proposed a new method for style transfer in images called SEFS (Style-Encoder-Free Stylization). This approach eliminates the need fo...
Researchers have developed a new method for robust time-series watermarking. The approach uses a generative model called L-VQVAE to encode each data p...
Researchers have developed a method called TempJail to break into large vision-language models (LVLMs) by manipulating subtitles in videos. They found...
Researchers have developed a new method to synthesize full-cycle biventricular motion from a single end-diastolic mesh. This task is challenging due t...