Daily Papers of 2024-04-12

  1. Rho-1: Not All Tokens Are What You Need 72 upvotes, #1 of 2024-04-12
  2. ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback 43 upvotes, #2 of 2024-04-12
  3. RecurrentGemma: Moving Past Transformers for Efficient Open Language Models 35 upvotes, #3 of 2024-04-12
  4. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments 35 upvotes, #3 of 2024-04-12
  5. JetMoE: Reaching Llama2 Performance with 0.1M Dollars 30 upvotes, #5 of 2024-04-12
  6. Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models 26 upvotes, #6 of 2024-04-12
  7. Best Practices and Lessons Learned on Synthetic Data for Language Models 23 upvotes, #7 of 2024-04-12
  8. WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents 19 upvotes, #8 of 2024-04-12
  9. HGRN2: Gated Linear RNNs with State Expansion 15 upvotes, #9 of 2024-04-12
  10. From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples 14 upvotes, #10 of 2024-04-12
  11. Audio Dialogues: Dialogues dataset for audio and music understanding 12 upvotes, #11 of 2024-04-12
  12. Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models 10 upvotes, #12 of 2024-04-12
  13. LLoCO: Learning Long Contexts Offline 10 upvotes, #12 of 2024-04-12
  14. Transferable and Principled Efficiency for Open-Vocabulary Segmentation 8 upvotes, #14 of 2024-04-12
  15. Sparse Laneformer 8 upvotes, #14 of 2024-04-12

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.