Daily Papers of 2023-05-12

  1. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning 7 upvotes, #1 of 2023-05-12
  2. CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model 7 upvotes, #1 of 2023-05-12
  3. Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers 6 upvotes, #3 of 2023-05-12
  4. Exploiting Diffusion Prior for Real-World Image Super-Resolution 6 upvotes, #3 of 2023-05-12
  5. EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention 5 upvotes, #5 of 2023-05-12
  6. An Inverse Scaling Law for CLIP Training 3 upvotes, #6 of 2023-05-12
  7. Bot or Human? Detecting ChatGPT Imposters with A Single Question 2 upvotes, #7 of 2023-05-12
  8. Chain-of-Dictionary Prompting Elicits Translation in Large Language Models 2 upvotes, #7 of 2023-05-12
  9. LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM 1 upvotes, #9 of 2023-05-12
  10. Perpetual Humanoid Control for Real-time Simulated Avatars 1 upvotes, #9 of 2023-05-12
  11. Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction 1 upvotes, #9 of 2023-05-12
  12. Domain Incremental Lifelong Learning in an Open World 1 upvotes, #9 of 2023-05-12
  13. V2Meow: Meowing to the Visual Beat via Music Generation 1 upvotes, #9 of 2023-05-12
  14. Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting 1 upvotes, #9 of 2023-05-12
  15. Simple Token-Level Confidence Improves Caption Correctness 1 upvotes, #9 of 2023-05-12

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.