Junsong Chen

Venues

Frequent coauthors

Papers

1. Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations
   AAAI 2026 · Junsong Chen
2. DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
   ICCV 2025 ·

   Junyu Chen

   DBLP profile ↗ORCID search ↗
3. DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
   ICCV 2025 ·

   Yecheng Wu

   DBLP profile ↗ORCID search ↗
4. Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
   ICLR 2025 ·

   Junyu Chen

   DBLP profile ↗ORCID search ↗
5. HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
   ICLR 2025 ·

   Haotian Tang

   DBLP profile ↗ORCID search ↗
6. SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
   ICML 2025 ·

   Enze Xie

   DBLP profile ↗ORCID search ↗
7. SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
   ICCV 2025 · Junsong Chen
8. SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers
   ICLR 2025 ·

   Enze Xie

   DBLP profile ↗ORCID search ↗
9. DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving
   AAAI 2024 ·

   Tianqi Wang

   DBLP profile ↗ORCID search ↗
10. Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation
    ECCV 2024 ·

    Shentong Mo

    DBLP profile ↗ORCID search ↗
11. PIXART-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
    ECCV 2024 · Junsong Chen
12. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
    ICLR 2024 · Junsong Chen