Found 2,471 document(s)
Page 64 of 165
-
Long-horizon manipulation requires actions whose validity depends on earlier interactions, yet visual progress can conceal missing task prerequisites. We propose RoboLongR, an offline-to-online framework that learns hist...
-
Symbolic regression (SR) seeks to discover mathematical expressions directly from data, without requiring task-specific scientific descriptions. Despite tremendous progress in both conventional search-based methods and r...
-
Interactive world models hold immense potential for high-stakes applications in robotics, game engines, and immersive digital twins, yet existing benchmarks primarily focus on perceptual similarity rather than the physic...
-
LLMs are increasingly being used by users from diverse demographics with pluralistic values and distinct backgrounds. Maintaining safety while respecting value-laden personas is uniquely challenging because persona-condi...
-
Computer-using agents are increasingly capable of performing complex tasks in the digital world. However, high-quality interaction trajectories remain scarce for specialized desktop applications, where limited applicatio...
-
A common strategy for data augmentation is to apply style transfer on training images to enrich appearance variations. Recent approaches have combined style augmentation with random erasing by selectively replacing image...
-
This paper introduces a novel simulation-free framework for learning unbalanced population dynamics on the Riemannian Wasserstein-Fisher-Rao (WFR) manifold, termed Variational Doob-Wasserstein Flow (VDWF), built upon the...
-
We initiate the study of the meta-mathematics of algebraic circuit lower bounds, aiming both to gain insight into the methods sufficient and necessary to prove algebraic circuit lower bounds, and to contribute to the stu...
-
Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge. It is essential for agents learning over long ti...
-
People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by multimodal large language models (MLLMs), egocentric AI assistants on wear...
-
The aim of this reprint is to provide a comprehensive exploration of the latest advancements in forestry through the integration of emerging technologies. This publication delves into several key areas, including the app...
-
World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or visi...
-
Karmazin, KolmaΕ‘, and Qiao-Franco deconstruct the concept of the Indo-Pacific and offer a timely, comparative, and multidimensional exploration of the regionβs international relations. Addressing fundamental academic que...
-
Open access biomedical research article published in Genome Biol....