PPaperPicks

Joonseok Lee

17 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. SCALE: Upscaled Continual Learning of Large Language Models
  2. GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting
  3. Graph Spectral Filtering with Chebyshev Interpolation for Recommendation
  4. Latent Diffusion Models With Masked Autoencoders
  5. Latent Expression Generation for Referring Image Segmentation and Grounding
  6. Local Large Language Models for Recommendation
  7. SummDiff: Generative Modeling of Video Summarization with Diffusion
  8. Towards Scalable Human-aligned Benchmark for Text-guided Image Editing
  9. A Revisit to the Decoder for Camouflaged Object Detection
  10. Content-based Graph Reconstruction for Cold-start Item Recommendation
  11. Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
  12. Finding NeMo: Negative-Mined Mosaic Augmentation for Referring Image Segmentation
  13. Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
  14. Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space
  15. Self-Guided Masked Autoencoder
  16. Towards a Complete Benchmark on Video Moment Localization
  17. V2Meow: Meowing to the Visual Beat via Video-to-Music Generation