Daily Papers of 2024-03-06

  1. Design2Code: How Far Are We From Automating Front-End Engineering? 85 upvotes, #1 of 2024-03-06
  2. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis 37 upvotes, #2 of 2024-03-06
  3. NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models 28 upvotes, #3 of 2024-03-06
  4. Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters 16 upvotes, #4 of 2024-03-06
  5. Wukong: Towards a Scaling Law for Large-Scale Recommendation 14 upvotes, #5 of 2024-03-06
  6. MathScale: Scaling Instruction Tuning for Mathematical Reasoning 13 upvotes, #6 of 2024-03-06
  7. MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets 10 upvotes, #7 of 2024-03-06
  8. Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use 9 upvotes, #8 of 2024-03-06
  9. EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs 9 upvotes, #8 of 2024-03-06
  10. Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models 7 upvotes, #10 of 2024-03-06
  11. MagicClay: Sculpting Meshes With Generative Neural Fields 6 upvotes, #11 of 2024-03-06
  12. RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches 6 upvotes, #11 of 2024-03-06
  13. Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation 5 upvotes, #13 of 2024-03-06

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.