Daily Papers of 2023-10-06

  1. Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion 79 upvotes, #1 of 2023-10-06
  2. Improved Baselines with Visual Instruction Tuning 39 upvotes, #2 of 2023-10-06
  3. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines 37 upvotes, #3 of 2023-10-06
  4. How FaR Are Large Language Models From Agents with Theory-of-Mind? 34 upvotes, #4 of 2023-10-06
  5. MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning 30 upvotes, #5 of 2023-10-06
  6. Aligning Text-to-Image Diffusion Models with Reward Backpropagation 22 upvotes, #6 of 2023-10-06
  7. UniAudio: An Audio Foundation Model Toward Universal Audio Generation 20 upvotes, #7 of 2023-10-06
  8. FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation 20 upvotes, #7 of 2023-10-06
  9. Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency 15 upvotes, #9 of 2023-10-06
  10. Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning 13 upvotes, #10 of 2023-10-06
  11. A Long Way to Go: Investigating Length Correlations in RLHF 10 upvotes, #11 of 2023-10-06
  12. Drag View: Generalizable Novel View Synthesis with Unposed Imagery 8 upvotes, #12 of 2023-10-06
  13. HeaP: Hierarchical Policies for Web Actions using LLMs 8 upvotes, #12 of 2023-10-06
  14. EcoAssistant: Using LLM Assistant More Affordably and Accurately 6 upvotes, #14 of 2023-10-06

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.