arXiv Computer Vision August 31, 2026 By Zihang Lin, Huaiyuan Qin, Muli Yang, Hongyuan Zhu

SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals

Read the original on arXiv Computer Vision →

SDGBiasBench is a large-scale benchmark suite designed to evaluate and mitigate biases in vision–language models (VLMs) when reasoning about Sustainable Development Goals (SDGs). It contains 500k expert‑involved multiple‑choice questions and 50k regression tasks, allowing assessment of both decision‑level and estimation‑level bias. Experiments show that current VLMs exhibit intrinsic SDG bias, often relying on priors rather than multimodal evidence, and the proposed CADE method significantly reduces this bias, improving accuracy and reducing mean absolute error.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 10

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

arXiv:2512. 11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space.

By Chenrui Fan, Yijun Liang, Shweta Bhardwaj, Kwesi Cobbina, Ming Li, Tianyi Zhou

llms multimodal benchmarks

Hugging Face Trending Papers

Jul 15

SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning

Vision Language Models (VLMs) demonstrate strong perceptual abilities but remain limited in tasks requiring analytical reasoning across multiple visual states, such as multi-image comparison, change detection, and multi-step visual inference. These capabilities are critical for real-world multimodal applications where reasoning must be grounded in systematic differences between visual contexts.

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jul 9

Thinking Ahead: Foresight Intelligence in MLLMs and World Model

arXiv:2511. 18735v3 Announce Type: replace-cross Abstract: In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research.

By Zhantao Gong, Liaoyuan Fan, Qing Guo, Xun Xu, Xulei Yang, Shijie Li

llms agents robotics fine-tuning multimodal benchmarks

arXiv AI

Jun 30

PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science

arXiv:2508. 17117v3 Announce Type: replace-cross Abstract: Existing plant-disease datasets target classification and detection, leaving vision-language models unable to support interactive, reasoning-based diagnosis.

By Syed Nazmus Sakib, Nafiul Haque, Mohammad Zabed Hossain, Shifat E. Arman

llms nlp fine-tuning multimodal benchmarks

arXiv AI

Jun 19

Vero: An Open RL Recipe for General Visual Reasoning

arXiv:2604. 04917v3 Announce Type: replace-cross Abstract: What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks?

By Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu

llms reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Jun 10

Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation

arXiv:2606. 10833v1 Announce Type: new Abstract: Vision-Language Models (VLMs) demonstrate strong performance on general multimodal reasoning benchmarks, yet their ability to perform engineering reasoning remains largely unexplored.

By Syed Wasiq, Syed Mohamad Tawseeq, Yashwant Pravinrao Bangde, Debaditya Roy

llms nlp multimodal benchmarks

One email a morning, machine-written

Related stories

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning

Thinking Ahead: Foresight Intelligence in MLLMs and World Model

PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science

Vero: An Open RL Recipe for General Visual Reasoning

Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation