8 papers · 1 filter
RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning
Ruoxuan Zhang, Qiyun Zheng, Siyu Wu +13
Vision-Language Models (VLMs) are widely used for visual understanding, yet current evaluation protocols fail to assess whether these capabilities are grounded in physical reasonin…
Seeing Time: Benchmarking Chronological Reasoning and Shortcut Biases in Vision-Language Models
Haoyu Zhou, Qing Qing, Caichong Li +6
Recent advancements in Vision-Language Models (VLMs) have significantly enhanced their ability to interpret complex visual semantics, yet their capacity for chronological reasoning…
Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction
Juncheng Hu, Jiawei Du, Xin Zhang +1
Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expressed in textual reasoning or draw…
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
Guotao Liang, Zhangcheng Wang, Chuang Wang +6
Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains c…
Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
Yogachandran Rahulamathavan, Nasir Iqbal, Juncheng Hu +1
Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting b…
ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation
Yuan Shui, Yandong Guan, Zhanwei Zhang +4
Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models from high-level descriptions…
AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
Juncheng Hu, Ziteng Xue, Guotao Liang +5
We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Exis…
Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback
Guotao Liang, Zhangcheng Wang, Juncheng Hu +5
Multimodal Large Language Models (MLLMs) have shown promising capabilities in generating Scalable Vector Graphics (SVG) via direct code synthesis. However, existing paradigms typic…