Daily Papers of 2024-04-02

  1. Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order 39 upvotes, #1 of 2024-04-02
  2. Getting it Right: Improving Spatial Consistency in Text-to-Image Models 28 upvotes, #2 of 2024-04-02
  3. FlexiDreamer: Single Image-to-3D Generation with FlexiCubes 19 upvotes, #3 of 2024-04-02
  4. MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text 14 upvotes, #4 of 2024-04-02
  5. CosmicMan: A Text-to-Image Foundation Model for Humans 14 upvotes, #4 of 2024-04-02
  6. Measuring Style Similarity in Diffusion Models 13 upvotes, #6 of 2024-04-02
  7. Condition-Aware Neural Network for Controlled Image Generation 10 upvotes, #7 of 2024-04-02
  8. Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward 9 upvotes, #8 of 2024-04-02
  9. Streaming Dense Video Captioning 9 upvotes, #8 of 2024-04-02
  10. Noise-Aware Training of Layout-Aware Language Models 6 upvotes, #10 of 2024-04-02
  11. WavLLM: Towards Robust and Adaptive Speech Large Language Model 5 upvotes, #11 of 2024-04-02
  12. ST-LLM: Large Language Models Are Effective Temporal Learners 4 upvotes, #12 of 2024-04-02

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.