Rui Ma

16

Papers

94

Total Citations

Papers (16)

3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation

P(all-atom) Is Unlocking New Path For Protein Design

OmniStyle: Filtering High Quality Style Transfer Data at Scale

B-spine: Learning B-spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation

DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction

SigStyle: Signature Style Transfer via Personalized Text-to-Image Models

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition

BOOTPLACE: Bootstrapped Object Placement with Detection Transformers

FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

ELIC: Efficient Learned Image Compression With Unevenly Grouped Space-Channel Contextual Adaptive Coding

PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion

Practical Learned Lossless JPEG Recompression With Multi-Level Cross-Channel Entropy Model in the DCT Domain