5 papers
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
Xiang Li, Xueheng Li, Yu Wang +4
Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior human preference alignment in Image Quality Assessment (IQA). However, existi…
Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
Runzhou Liu, Hailey Weingord, Sejal Mittal +18
Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important…
Reliable and Responsible Foundation Models: A Comprehensive Survey
Xinyu Yang, Junlin Han, Rishi Bommasani +49
Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), a…
He-Mg compounds and helium-driven nonmetal transition in metallic magnesium
Y. S. Huang, H. X. Song, Q. D. Hao +6
The polymorphism and mechanism of helium compounds is crucial for understanding the physical and chemical nature of He-bearing materials under pressures. Here, we predict two new t…
Probabilistic Prompt Distribution Learning for Animal Pose Estimation
Jiyong Rao, Brian Nlong Zhao, Yu Wang
Multi-species animal pose estimation has emerged as a challenging yet critical task, hindered by substantial visual diversity and uncertainty. This paper challenges the problem by…