Tracked topic
Framework is a company that produces modular laptops designed so users can replace components like the motherboard, display, and keyboard.
…A Safety Framework for Mobile GUI Agents via World Model Prediction Published on Jul 17 Submitted by Xue Yu on Jul 21 Authors: Xue Yu , Bo Yuan , , , , Abstract M o b i…
…A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception Published on May 11 Submitted by Yiwei Ou on May 13 University of Auckland Authors: , , , , , , , Abstract Urban-ImageNet presents…
…An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation Published on Jun 3 Submitted by Dong Xie on Jun 4 BAIDU Authors: , , , Dong Xie , , , , , Abstract MapAgent is an industrial…
…An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World Published on Jul 19 Submitted by Jeff on Jul 21 #3 Paper of the day…
…A Multi-Agent Framework for Citation Hallucination Detection Published on May 9 Submitted by Mingzhe Li on May 14 University of Massachusetts Amherst Authors: Mingzhe Li , , Abstract CiteTracer is a multi-agent…
…A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection Published on Jul 22 Submitted by taesiri on Jul 23 Authors: , , , , Abstract T h i s w o…
…A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Published on Jul 22 Submitted by taesiri on Jul 27 #3 Paper of the day NVIDIA Authors: , , , , , , , , , , Abstract A g e n…
…Haoran Zhang , , Boyang Wang , , , , , Abstract A failure detection framework for long-horizon robotic tasks uses action-conditioned world models and functional conformal prediction to monitor manipulation trajectories with only final task labels…
…Sebastian Stapf , , Aram Davtyan , Abstract A scalable framework combines self-distillation and reinforcement learning to transfer task-solving abilities from vision-language models to video diffusion models without requiring labeled task-video…
…Existing benchmarks are poorly aligned with production inference frameworks : they evaluate kernels on a single GPU with synthetic inputs, ignore the surrounding compilation stack , and reward replicating known optimizations rather than discovering…