Daily Papers of 2024-09-04

  1. Kvasir-VQA: A Text-Image Pair GI Tract Dataset 68 upvotes, #1 of 2024-09-04
  2. OLMoE: Open Mixture-of-Experts Language Models 67 upvotes, #2 of 2024-09-04
  3. General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model 47 upvotes, #3 of 2024-09-04
  4. LongRecipe: Recipe for Efficient Long Context Generalization in Large Languge Models 37 upvotes, #4 of 2024-09-04
  5. DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos 31 upvotes, #5 of 2024-09-04
  6. FLUX that Plays Music 29 upvotes, #6 of 2024-09-04
  7. LinFusion: 1 GPU, 1 Minute, 16K Image 29 upvotes, #6 of 2024-09-04
  8. VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges 26 upvotes, #8 of 2024-09-04
  9. Diffusion Policy Policy Optimization 19 upvotes, #9 of 2024-09-04
  10. Compositional 3D-aware Video Generation with LLM Director 14 upvotes, #10 of 2024-09-04
  11. ContextCite: Attributing Model Generation to Context 13 upvotes, #11 of 2024-09-04
  12. Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization 10 upvotes, #12 of 2024-09-04
  13. OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model 10 upvotes, #12 of 2024-09-04
  14. GenAgent: Build Collaborative AI Systems with Automated Workflow Generation -- Case Studies on ComfyUI 9 upvotes, #14 of 2024-09-04
  15. Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation 6 upvotes, #15 of 2024-09-04
  16. Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders 4 upvotes, #16 of 2024-09-04
  17. Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain 3 upvotes, #17 of 2024-09-04
  18. The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts 2 upvotes, #18 of 2024-09-04
  19. PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action 1 upvotes, #19 of 2024-09-04

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.