most citedGenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?

1 citations · 1 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV20261 cited

GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?

Ruihang Li, Leigang Qu, Jingxu Zhang +6

The rapid advancement of visual generation models has outpaced traditional evaluation approaches, necessitating the adoption of Vision-Language Models as surrogate judges. In this…

cs.CV2026

Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies

Wenjin Hou, Wei Liu, Han Hu +3

Multimodal Large Language Models (MLLMs) have shown remarkable proficiency on general-purpose vision-language benchmarks, reaching or even exceeding human-level performance. Howeve…

cs.CV2026

Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions

Kaiwen Zheng, Junchen Fu, Songpei Xu +4

In this paper, we introduce an underexplored problem in facial analysis: generating and recognizing multi-attribute natural language descriptions, containing facial action units (A…

cs.CV2025

GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

Yikun Wang, Zuyan Liu, Ziyi Wang +3

Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools, leaving a gap toward more general-purpose agen…

cs.CV2025

Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models

Hengzhuang Li, Xinsong Zhang, Qiming Peng +6

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in multimodal tasks. Despite their impressive performance, MLLMs suffer from the modality imbalanc…

cs.CV2025

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training

Xinsong Zhang, Yarong Zeng, Xinting Huang +4

In recent years, the field of vision-language model pre-training has experienced rapid advancements, driven primarily by the continuous enhancement of textual capabilities in large…