activity
20242026
collaborators

10 papers

cs.CV2026

Reliability-Prioritized Fine-Grained Generation in Multimodal Large

Xiaomeng Fan, Wei Wu, Yuwei Wu +9

Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generati…

cs.CV2026

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Pengxiang Li, Zhi Gao, Bofei Zhang +8

Multimodal agents, which integrate a controller e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks.…

cs.CV2026

Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds

Wei Wu, Xiaomeng Fan, Yuwei Wu +4

Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features fro…

cs.CV2026

AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process

Xintong Zhang, Xiaowen Zhang, Jingrong Wu +8

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text…

cs.AI2026

GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks

Chenrui Shi, Zedong Yu, Zhi Gao +7

Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledg…

cs.CV2025

Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spaces

Pengxiang Li, Yuwei Wu, Zhi Gao +5

Learning in hyperbolic spaces has attracted increasing attention due to its superior ability to model hierarchical structures of data. Most existing hyperbolic learning methods use…