Junsong Chen

14 papers · 2023–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+4 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🧭 Keyword Pioneer

🤝 Dynamic Duo (12) 🗃️ Keyword Collector (54) 💎 Century Club · Bronze ⚡ Prolific Year · Productive

Venues

ICCV (4) ICLR (4) AAAI (2) ECCV (2) CVPR (1) ICML (1)

Top co-authors

Enze Xie (12) Junyu Chen (7) Han Cai (7) Song Han (7) Zhenguo Li (5) Chongjian GE (4) Jincheng Yu (4) Huchuan Lu (4) Ping Luo (4) Zhongdao Wang (3)

Research topics

Computer Vision (12) Deep Learning (9) Generation (9) Models (9) Architectures (6) Machine Learning (5) Application Areas (5) Artificial Intelligence (4) Core AI (4) Analysis (3) Domain-Specific (2) Learning Paradigms (2) Learning Types (1) Optimization & Theory (1) Techniques (1)

Keywords

image generation (6) diffusion model (5) latent diffusion (3) 3d object detection (2) multimodal learning (2) diffusion transformer (2) text-to-image generation (2) object tracking (1) model distillation (1) autoregressive transformer (1) video understanding (1) bird's eye view (1) image reconstruction (1) 3d vision (1) knowledge distillation (1) depth estimation (1) flow matching (1) sensor fusion (1) multi-view perception (1) autonomous driving (1)

Papers

Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal Representations AAAI 2026 DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space ICCV 2025 DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer ICCV 2025 Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models ICLR 2025 HART: Efficient Visual Generation with Hybrid Autoregressive Transformer ICLR 2025 SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer ICML 2025 SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers ICLR 2025 SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation ICCV 2025 DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving AAAI 2024 Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation ECCV 2024 PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis ICLR 2024 PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation ECCV 2024 ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data CVPR 2023 MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation ICCV 2023