Daily Papers of 2024-01-05

  1. TinyLlama: An Open-Source Small Language Model 95 upvotes, #1 of 2024-01-05
  2. Understanding LLMs: A Comprehensive Overview from Training to Inference 66 upvotes, #2 of 2024-01-05
  3. LLaMA Pro: Progressive LLaMA with Block Expansion 54 upvotes, #3 of 2024-01-05
  4. LLM Augmented LLMs: Expanding Capabilities through Composition 38 upvotes, #4 of 2024-01-05
  5. Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation 33 upvotes, #5 of 2024-01-05
  6. Instruct-Imagen: Image Generation with Multi-modal Instruction 31 upvotes, #6 of 2024-01-05
  7. LLaVA-φ: Efficient Multi-Modal Assistant with Small Language Model 18 upvotes, #7 of 2024-01-05
  8. What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs 13 upvotes, #8 of 2024-01-05
  9. ODIN: A Single Model for 2D and 3D Perception 12 upvotes, #9 of 2024-01-05
  10. ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers 10 upvotes, #10 of 2024-01-05
  11. Learning the 3D Fauna of the Web 10 upvotes, #10 of 2024-01-05
  12. FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding 7 upvotes, #12 of 2024-01-05
  13. Improving Diffusion-Based Image Synthesis with Context Prediction 7 upvotes, #12 of 2024-01-05
  14. Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers 6 upvotes, #14 of 2024-01-05

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.