AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence

Liyuan Deng, Yunpeng Bai, Yongkang Dai, Xiaoshui Huang, Hongping Gan, Dongshuo Huang, Hao Jiacheng, Yilei Shi

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add Mamba+ block instead of Transformer block in the encoder (ablation)MamTiff-CAD autoencoder · ABC-256 reconstructionparameter accuracy: 63.62 -> 99.93Improved
Add Mamba+ block instead of Transformer block in the encoder (ablation)MamTiff-CAD autoencoder · ABC-256 reconstructionstep ratio: 34.28% -> 93.93%Improved
Add forget gate (Mamba+) to standard Mamba (ablation)MamTiff-CAD autoencoder · ABC-256 reconstructionstep ratio: 92.01% -> 93.93%Improved
Add forget gate (Mamba+) to standard Mamba (ablation)MamTiff-CAD autoencoder · ABC-256 reconstructioninvalid ratio: 10.35% -> 8.50%Improved
Add forget gate (Mamba+) to standard Mamba (ablation)MamTiff-CAD autoencoder · ABC-256 reconstructionMCD: 0.76 -> 0.75No clear effect
Add multi-scale transformer (MST) to the diffusion generator (ablation)MamTiff-CAD generator · Unconditional generationJSD: 4.92 -> 3.19Improved
Add multi-scale transformer (MST) to the diffusion generator (ablation)MamTiff-CAD generator · Unconditional generationstep ratio: 77.05% -> 85.38%Improved
Add multi-scale transformer (MST) to the diffusion generator (ablation)MamTiff-CAD generator · Unconditional generationMMD: 1.47 -> 1.32Improved
Add multi-scale transformer (MST) to the diffusion generator (ablation)MamTiff-CAD generator · Unconditional generationnovelty: 99.6 -> 99.4No clear effect
Use MamTiff-CAD instead of DeepCAD for reconstructionDeepCAD · ABC-256 reconstructionMCD: 41.02 -> 0.75Improved
Use MamTiff-CAD instead of DeepCAD zero-shot on Fusion360DeepCAD · Fusion360 reconstructionparameter accuracy: 77.99 -> 97.99Improved
Use MamTiff-CAD instead of HNC-CAD for generationHNC-CAD · Unconditional generationJSD: 4.25 -> 3.19Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy