Daily Papers of 2023-05-18

  1. CoEdIT: Text Editing by Task-Specific Instruction Tuning 10 upvotes, #1 of 2023-05-18
  2. PaLM 2 Technical Report 9 upvotes, #2 of 2023-05-18
  3. SLiC-HF: Sequence Likelihood Calibration with Human Feedback 7 upvotes, #3 of 2023-05-18
  4. DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining 5 upvotes, #4 of 2023-05-18
  5. DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning 4 upvotes, #5 of 2023-05-18
  6. Explaining black box text modules in natural language with language models 3 upvotes, #6 of 2023-05-18
  7. Application-Agnostic Language Modeling for On-Device ASR 2 upvotes, #7 of 2023-05-18
  8. Smart Word Suggestions for Writing Assistance 2 upvotes, #7 of 2023-05-18
  9. What You See is What You Read? Improving Text-Image Alignment Evaluation 2 upvotes, #7 of 2023-05-18
  10. FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention 2 upvotes, #7 of 2023-05-18
  11. A Video Is Worth 4096 Tokens: Verbalize Story Videos To Understand Them In Zero Shot 1 upvotes, #11 of 2023-05-18
  12. NerfBridge: Bringing Real-time, Online Neural Radiance Field Training to Robotics 1 upvotes, #11 of 2023-05-18
  13. Transfer Learning for Fine-grained Classification Using Semi-supervised Learning and Visual Transformers 1 upvotes, #11 of 2023-05-18
  14. Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback 1 upvotes, #11 of 2023-05-18
  15. Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability 1 upvotes, #11 of 2023-05-18
  16. CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo 1 upvotes, #11 of 2023-05-18

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.