Daily Papers of 2024-12-16

  1. Apollo: An Exploration of Video Understanding in Large Multimodal Models 131 upvotes, #1 of 2024-12-16
  2. GenEx: Generating an Explorable World 84 upvotes, #2 of 2024-12-16
  3. SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding 35 upvotes, #3 of 2024-12-16
  4. Large Action Models: From Inception to Implementation 28 upvotes, #4 of 2024-12-16
  5. BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities 26 upvotes, #5 of 2024-12-16
  6. InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption 19 upvotes, #6 of 2024-12-16
  7. FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion 19 upvotes, #6 of 2024-12-16
  8. Efficient Generative Modeling with Residual Vector Quantization-Based Tokens 19 upvotes, #6 of 2024-12-16
  9. FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing 11 upvotes, #9 of 2024-12-16
  10. ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation 11 upvotes, #9 of 2024-12-16
  11. FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers 9 upvotes, #11 of 2024-12-16
  12. LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity 9 upvotes, #11 of 2024-12-16
  13. SCBench: A KV Cache-Centric Analysis of Long-Context Methods 8 upvotes, #13 of 2024-12-16
  14. Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation 7 upvotes, #14 of 2024-12-16
  15. GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers 5 upvotes, #15 of 2024-12-16
  16. SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs 4 upvotes, #16 of 2024-12-16
  17. TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies 2 upvotes, #17 of 2024-12-16
  18. Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images 1 upvotes, #18 of 2024-12-16

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.