Browse and export your curated research paper collection
Julian Kaltheuner, Hannah Dröge, Markus Plack, Patrick Stotko, Reinhard Klein 2/25/2026 arxiv
computer visionTemporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models tha...
Yufei Ye, Jiaman Li, Ryan Rong, C. Karen Liu 2/25/2026 arxiv
computer visionEgocentric manipulation videos are highly challenging due to severe occlusions during interactions and frequent object entries and exits from the camera view as the person moves. Current methods typically focus on recovering either hand or object pose in isolation, but both struggle during interacti...
Georgy Savva, Oscar Michel, Daohan Lu, Suppakit Waiwitlikhit, Timothy Meehan, Dhairya Mishra, Srivats Poddar, Jack Lu, Saining Xie 2/25/2026 arxiv
computer visionExisting action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world environments. We introduce Solaris, a multiplayer video world model that simulates consistent multi-view observations. To e...
Hanna Yukhymenko, Anton Alexandrov, Martin Vechev 2/25/2026 arxiv
machine learningThe reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a full...
Cole Simmons, Richard Diehl Martinez, Dan Jurafsky 2/25/2026 arxiv
machine learningSumerian transliteration is a conventional system for representing a scholar's interpretation of a tablet in the Latin script. Thanks to visionary digital Assyriology projects such as ETCSL, CDLI, and Oracc, a large number of Sumerian transliterations have been published online, and these data are w...
Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde, Peng Gao, Mainack Mondal, Murtuza Jadliwala, Bimal Viswanath 2/25/2026 arxiv
computer visionAdvances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on adding imperceptible protective perturbations to images to thwart misuse such as style mimicry or deepfake manipulations. Although previous ...
Melody Ma, John Hewitt 2/25/2026 arxiv
natural language processingWe study reasoning for accessing world knowledge stored in a language model's parameters. For example, recalling that Canberra is Australia's capital may benefit from thinking through major cities and the concept of purpose-built capitals. While reasoning language models are trained via reinforcemen...
Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng, Huaxiu Yao, Baoling Peng, Huan Zhang, Jianfeng Gao, Tong Zhang 2/25/2026 arxiv
machine learningOpen-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-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI...
Mhd Jawad Al Rahwanji, Sascha Xu, Nils Philipp Walter, Jilles Vreeken 2/25/2026 arxiv
machine learningIn many applications, it is important to identify subpopulations that survive longer or shorter than the rest of the population. In medicine, for example, it allows determining which patients benefit from treatment, and in predictive maintenance, which components are more likely to fail. Existing me...
Eric Zimmermann, Julian Viret, Michal Zelechowski, James Brian Hall, Neil Tenenholtz, Adam Casson, George Shaikovski, Eugene Vorontsov, Siqi Liu, Kristen A Severson 2/25/2026 arxiv
machine learningIn recent years, a standard computational pathology workflow has emerged where whole slide images are cropped into tiles, these tiles are processed using a foundation model, and task-specific models are built using the resulting representations. At least 15 different foundation models have been prop...
Preparing your export...