Daily Papers of 2023-11-21

  1. Exponentially Faster Language Modelling 119 upvotes, #1 of 2023-11-21
  2. Orca 2: Teaching Small Language Models How to Reason 77 upvotes, #2 of 2023-11-21
  3. Make Pixels Dance: High-Dynamic Video Generation 67 upvotes, #3 of 2023-11-21
  4. System 2 Attention (is something you might need too) 43 upvotes, #4 of 2023-11-21
  5. GPQA: A Graduate-Level Google-Proof Q&A Benchmark 38 upvotes, #5 of 2023-11-21
  6. MultiLoRA: Democratizing LoRA for Better Multi-Task Learning 36 upvotes, #6 of 2023-11-21
  7. Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning 28 upvotes, #7 of 2023-11-21
  8. Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression 27 upvotes, #8 of 2023-11-21
  9. LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching 20 upvotes, #9 of 2023-11-21
  10. Memory Augmented Language Models through Mixture of Word Experts 18 upvotes, #10 of 2023-11-21
  11. AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort 16 upvotes, #11 of 2023-11-21
  12. ToolTalk: Evaluating Tool-Usage in a Conversational Setting 9 upvotes, #12 of 2023-11-21
  13. ProAgent: From Robotic Process Automation to Agentic Process Automation 8 upvotes, #13 of 2023-11-21
  14. TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems 7 upvotes, #14 of 2023-11-21
  15. M^{2}UGen: Multi-modal Music Understanding and Generation with the Power of Large Language Models 5 upvotes, #15 of 2023-11-21
  16. GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration 5 upvotes, #15 of 2023-11-21

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.