Daily Papers of 2024-02-21

  1. Neural Network Diffusion 101 upvotes, #1 of 2024-02-21
  2. Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models 52 upvotes, #2 of 2024-02-21
  3. VideoPrism: A Foundational Visual Encoder for Video Understanding 42 upvotes, #3 of 2024-02-21
  4. Video ReCap: Recursive Captioning of Hour-Long Videos 27 upvotes, #4 of 2024-02-21
  5. Instruction-tuned Language Models are Better Knowledge Learners 26 upvotes, #5 of 2024-02-21
  6. The FinBen: An Holistic Financial Benchmark for Large Language Models 24 upvotes, #6 of 2024-02-21
  7. Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields 19 upvotes, #7 of 2024-02-21
  8. MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction 18 upvotes, #8 of 2024-02-21
  9. A Touch, Vision, and Language Dataset for Multimodal Alignment 17 upvotes, #9 of 2024-02-21
  10. How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts 14 upvotes, #10 of 2024-02-21
  11. TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization 14 upvotes, #10 of 2024-02-21
  12. FlashTex: Fast Relightable Mesh Texturing with LightControlNet 14 upvotes, #10 of 2024-02-21
  13. RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models 9 upvotes, #13 of 2024-02-21

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.