← authors · overview

• A Simple Approach to Continual Learning by Transferring Skill Parameters
  2021 · 2 citations
• Fast-SAM3D: 3Dfy Anything in Images but Faster
  2026
• Asymmetric VAE for One-Step Video Super-Resolution Acceleration
  2025
• Quantized Visual Geometry Grounded Transformer
  2025
• QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
  2025
• Asymmetric VAE for One-Step Video Super-Resolution Acceleration
  2025
• BiVM: Accurate Binarized Neural Network for Efficient Video Matting
  2025
• Segment Concealed Objects with Incomplete Supervision
  2025
• CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
  2025
• Freqformer: Image-Demoiréing Transformer via Effective Frequency Decomposition
  2025
• Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)
  2025
• Low-Light Image Enhancement using Event-Based Illumination Estimation
  2025
• NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results
  2025
• GAN Inversion: A Survey
  2021
• Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning
  2021