3 papers
cs.GR2025
3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds
Fan-Yun Sun, Shengguang Wu, Christian Jacobsen +13
Despite large-scale pretraining endowing models with language and vision reasoning capabilities, improving their spatial reasoning capability remains challenging due to the lack of…
cs.CV2025
Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images
Shengguang Wu, Fan-Yun Sun, Kaiyue Wen +1
Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded ta…
cs.CV2024
LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models
Fan-Yun Sun, Weiyu Liu, Siyi Gu +6
Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demon…