Daily Papers of 2023-06-08

  1. M^3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning 10 upvotes, #1 of 2023-06-08
  2. On the Reliability of Watermarks for Large Language Models 6 upvotes, #2 of 2023-06-08
  3. LLMZip: Lossless Text Compression using Large Language Models 5 upvotes, #3 of 2023-06-08
  4. ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections 4 upvotes, #4 of 2023-06-08
  5. Certified Reasoning with Language Models 3 upvotes, #5 of 2023-06-08
  6. MobileNMT: Enabling Translation in 15MB and 30ms 3 upvotes, #5 of 2023-06-08
  7. PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts 3 upvotes, #5 of 2023-06-08
  8. Designing a Better Asymmetric VQGAN for StableDiffusion 3 upvotes, #5 of 2023-06-08
  9. Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions 2 upvotes, #9 of 2023-06-08
  10. Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks 2 upvotes, #9 of 2023-06-08
  11. Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks 1 upvotes, #11 of 2023-06-08
  12. Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer 1 upvotes, #11 of 2023-06-08

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.