12 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…
Beyond Single Object: Learning 3D Relations with Large Language Models
Kohsuke Ide, Ryousuke Yamada, Yue Qiu +4
We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison. We propose a framework for det…
Seeing Red, Thinking Bad: Color Bias in Vision Language Models
Kohsuke Ide, Ryousuke Yamada, Yoshihiro Fukuhara +2
Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation. This motivates careful analysis of how VL…
Image-Space Rule Discovery
Misora Sugiyama, Toya Oyama, Hirokatsu Kataoka
Can image editors solve worksheets while preserving unrelated content? WISP (Worksheet Image-Space Problem Solving) defines 11 tasks and eight information conditions. On 2,200 shar…
Local Brushstroke Quality Assessment via Vision-Language Feedback
Mio Mitamura, Hirokatsu Kataoka
This paper investigates whether multimodal LLMs can evaluate local brushstroke quality in calligraphy and generate educationally useful natural language feedback. We construct an e…
Feed-forward Motion In-betweening for Any 4D
Hiroki Nishizawa, Hubert P. H. Shum, Yoshihiro Fukuhara +2
4D dynamics (3D geometry evolving over time) is a fundamental representation of the physical world and plays a crucial role in world modeling (e.g., animation and games). Owing to…
MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness
Yuto Matsuo, Yoshihiro Fukuhara, Yuki M. Asano +3
Data augmentation is a key technique for improving the robustness of image classification models. However, many recent approaches rely on diffusion-based synthesis or complex featu…
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
Masatoshi Tateno, Gido Kato, Hirokatsu Kataoka +2
Hand-object interaction (HOI) inherently involves dynamics where human manipulations produce distinct spatio-temporal effects on objects. However, existing semantic HOI benchmarks…
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
Masaki Kawamura, Nakamasa Inoue, Rintaro Yanagi +2
Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies have sho…
Approximate Domain Unlearning for Vision-Language Models
Kodai Kawamura, Yuta Goto, Rintaro Yanagi +2
Pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities, enabling them to recognize a wide range of objects across diverse domains without additional t…
CLIP-like Model as a Foundational Density Ratio Estimator
Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi +5
Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weighting, divergence estimation, an…
Simple Visual Artifact Detection in Sora-Generated Videos
Misora Sugiyama, Hirokatsu Kataoka
The December 2024 release of OpenAI's Sora, a powerful video generation model driven by natural language prompts, highlights a growing convergence between large language models (LL…