10 papers
Visual General Intelligence: A White Paper
Hirokatsu Kataoka, Yoshihiro Fukuhara, Yonglong Tian +18
This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning may provide a pathway toward A…
WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark
Yida Yin, Harish Krishnakumar, Chung Peng Lee +9
In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual…
VLM3: Vision Language Models Are Native 3D Learners
Zhipeng Cai, Zhuang Liu, Yunyang Xiong +3
Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D u…
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
Kaichen Zhou, Yuzhen Chen, Fangneng Zhan +8
Video world models can generate realistic futures from a single instruction, but they often fail to track the same physical points consistently across time. As a result, the genera…
VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Guanyu Zhou, Yida Yin, Wenhao Chai +3
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition, largely because natural image datasets provide li…
Vero: An Open RL Recipe for General Visual Reasoning
Gabriel Sarch, Linrong Cai, Qunzhong Wang +3
What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) suggest tha…
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Shuming Liu, Mingchen Zhuge, Changsheng Zhao +20
Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct…
DepthLM: Metric Depth From Vision Language Models
Zhipeng Cai, Ching-Feng Yeh, Hu Xu +7
Vision language models (VLMs) can flexibly address various vision tasks through text interactions. Although successful in semantic understanding, state-of-the-art VLMs including GP…
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
Shengbang Tong, David Fan, Jiachen Zhu +7
In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph…
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao +14
Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge…