Daily Papers of 2024-11-19

  1. Generative World Explorer 65 upvotes, #1 of 2024-11-19
  2. BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices 39 upvotes, #2 of 2024-11-19
  3. AnimateAnything: Consistent and Controllable Animation for Video Generation 20 upvotes, #3 of 2024-11-19
  4. Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering 19 upvotes, #4 of 2024-11-19
  5. Top-nσ: Not All Logits Are You Need 17 upvotes, #5 of 2024-11-19
  6. Drowning in Documents: Consequences of Scaling Reranker Inference 16 upvotes, #6 of 2024-11-19
  7. SlimLM: An Efficient Small Language Model for On-Device Document Assistance 12 upvotes, #7 of 2024-11-19
  8. FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on 12 upvotes, #7 of 2024-11-19
  9. Adaptive Decoding via Latent Preference Optimization 10 upvotes, #9 of 2024-11-19
  10. StableV2V: Stablizing Shape Consistency in Video-to-Video Editing 10 upvotes, #9 of 2024-11-19
  11. Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts 9 upvotes, #11 of 2024-11-19
  12. SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers 8 upvotes, #12 of 2024-11-19
  13. LLäMmlein: Compact and Competitive German-Only Language Models from Scratch 8 upvotes, #12 of 2024-11-19
  14. Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering 6 upvotes, #14 of 2024-11-19
  15. VeGaS: Video Gaussian Splatting 6 upvotes, #14 of 2024-11-19
  16. Evaluating the role of `Constitutions' for learning from AI feedback 5 upvotes, #16 of 2024-11-19

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.