Daily Papers of 2023-07-06

  1. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis 94 upvotes, #1 of 2023-07-06
  2. LongNet: Scaling Transformers to 1,000,000,000 Tokens 82 upvotes, #2 of 2023-07-06
  3. DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models 35 upvotes, #3 of 2023-07-06
  4. Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning 23 upvotes, #4 of 2023-07-06
  5. Jailbroken: How Does LLM Safety Training Fail? 16 upvotes, #5 of 2023-07-06
  6. What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? 13 upvotes, #6 of 2023-07-06
  7. Building Cooperative Embodied Agents Modularly with Large Language Models 12 upvotes, #7 of 2023-07-06
  8. Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners 10 upvotes, #8 of 2023-07-06
  9. DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation 8 upvotes, #9 of 2023-07-06
  10. Physics-based Motion Retargeting from Sparse Inputs 7 upvotes, #10 of 2023-07-06
  11. Open-Source Large Language Models Outperform Crowd Workers and Approach ChatGPT in Text-Annotation Tasks 7 upvotes, #10 of 2023-07-06
  12. MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers 7 upvotes, #10 of 2023-07-06
  13. EmoGen: Eliminating Subjective Bias in Emotional Music Generation 5 upvotes, #13 of 2023-07-06
  14. Embodied Task Planning with Large Language Models 5 upvotes, #13 of 2023-07-06
  15. Elastic Decision Transformer 5 upvotes, #13 of 2023-07-06

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.