[Paper] SumTablets: A Transliteration Dataset of Sumerian Tablets
Sumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script. Thanks to visionary digital Assyr...
Sumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script. Thanks to visionary digital Assyr...
Advances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on ...
Sybil resistance is a key requirement of decentralized consensus protocols. It is achieved by introducing a scarce resource (such as computational power, moneta...
We study reasoning for accessing world knowledge stored in a language model's parameters. For example, recalling that Canberra is Australia's capital may benefi...
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-q...
Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid wi...
Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems. However, addressing complex questi...
In many applications, it is important to identify subpopulations that survive longer or shorter than the rest of the population. In medicine, for example, it al...
In recent years, a standard computational pathology workflow has emerged where whole slide images are cropped into tiles, these tiles are processed using a foun...
Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windo...
Mixed-Integer Programs (MIPs) are NP-hard optimization models that arise in a broad range of decision-making applications, including finance, logistics, energy ...
Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and...