5 papers
LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models
Ruilin Yao, Bo Zhang, Jirui Huang +18
Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-wor…
AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
Ruilin Yao, Shegnwu Xiong, Tianyu Zou +2
Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance deg…
Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling
Shengwu. Xiong, Tianyu. Zou, Cong. Wang +1
Evaluating multimodal large language models (MLLMs) is fundamentally challenged by the absence of structured, interpretable, and theoretically grounded benchmarks; current heuristi…
MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
Peng Xu, Shengwu Xiong, Jiajun Zhang +125
This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We…
Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation
Tianyu Zou, Shengwu Xiong, Ruilin Yao +1
This paper studies the few-shot segmentation (FSS) task, which aims to segment objects belonging to unseen categories in a query image by learning a model on a small number of well…