Daily Papers of 2024-10-02

  1. Law of the Weakest Link: Cross Capabilities of Large Language Models 50 upvotes, #1 of 2024-10-02
  2. TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices 28 upvotes, #2 of 2024-10-02
  3. Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect 20 upvotes, #3 of 2024-10-02
  4. One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos 17 upvotes, #4 of 2024-10-02
  5. Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation 16 upvotes, #5 of 2024-10-02
  6. Illustrious: an Open Advanced Illustration Model 10 upvotes, #6 of 2024-10-02
  7. ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer 10 upvotes, #6 of 2024-10-02
  8. SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs 10 upvotes, #6 of 2024-10-02
  9. Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration 9 upvotes, #9 of 2024-10-02
  10. Visual Context Window Extension: A New Perspective for Long Video Understanding 7 upvotes, #10 of 2024-10-02
  11. DressRecon: Freeform 4D Human Reconstruction from Monocular Video 7 upvotes, #10 of 2024-10-02
  12. Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models 6 upvotes, #12 of 2024-10-02
  13. What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study 4 upvotes, #13 of 2024-10-02
  14. Embodied-RAG: General non-parametric Embodied Memory for Retrieval and Generation 3 upvotes, #14 of 2024-10-02

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.