Daily Papers of 2023-06-30

  1. OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents 48 upvotes, #1 of 2023-06-30
  2. One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization 41 upvotes, #2 of 2023-06-30
  3. DreamDiffusion: Generating High-Quality Images from Brain EEG Signals 32 upvotes, #3 of 2023-06-30
  4. Generate Anything Anywhere in Any Scene 23 upvotes, #4 of 2023-06-30
  5. Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors 22 upvotes, #5 of 2023-06-30
  6. LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding 12 upvotes, #6 of 2023-06-30
  7. Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation 12 upvotes, #6 of 2023-06-30
  8. Benchmarking Large Language Model Capabilities for Conditional Generation 7 upvotes, #8 of 2023-06-30
  9. Dynamic-Resolution Model Learning for Object Pile Manipulation 6 upvotes, #9 of 2023-06-30
  10. NeuralFuse: Learning to Improve the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes 6 upvotes, #9 of 2023-06-30
  11. BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion 6 upvotes, #9 of 2023-06-30
  12. ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch 5 upvotes, #12 of 2023-06-30
  13. An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs 4 upvotes, #13 of 2023-06-30
  14. Automatic Calibration and Error Correction for Large Language Models via Pareto Optimal Self-Supervision 3 upvotes, #14 of 2023-06-30

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.