Daily Papers of 2024-10-21

  1. UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models 52 upvotes, #1 of 2024-10-21
  2. Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation 39 upvotes, #2 of 2024-10-21
  3. NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples 35 upvotes, #3 of 2024-10-21
  4. MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models 33 upvotes, #4 of 2024-10-21
  5. SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs 24 upvotes, #5 of 2024-10-21
  6. FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model 20 upvotes, #6 of 2024-10-21
  7. Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities 19 upvotes, #7 of 2024-10-21
  8. DPLM-2: A Multimodal Diffusion Protein Language Model 18 upvotes, #8 of 2024-10-21
  9. Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion 13 upvotes, #9 of 2024-10-21
  10. HART: Efficient Visual Generation with Hybrid Autoregressive Transformer 12 upvotes, #10 of 2024-10-21
  11. Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts 9 upvotes, #11 of 2024-10-21
  12. DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation 8 upvotes, #12 of 2024-10-21
  13. BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities 7 upvotes, #13 of 2024-10-21
  14. SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments 5 upvotes, #14 of 2024-10-21
  15. Looking Inward: Language Models Can Learn About Themselves by Introspection 5 upvotes, #14 of 2024-10-21
  16. Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Media 4 upvotes, #16 of 2024-10-21
  17. How Do Training Methods Influence the Utilization of Vision Models? 4 upvotes, #16 of 2024-10-21
  18. A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement 3 upvotes, #18 of 2024-10-21
  19. Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning 2 upvotes, #19 of 2024-10-21
  20. Teaching Models to Balance Resisting and Accepting Persuasion 2 upvotes, #19 of 2024-10-21

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.