Daily Papers of 2024-09-25

  1. HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models 39 upvotes, #1 of 2024-09-25
  2. MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling 29 upvotes, #2 of 2024-09-25
  3. Making Text Embedders Few-Shot Learners 27 upvotes, #3 of 2024-09-25
  4. OmniBench: Towards The Future of Universal Omni-Language Models 24 upvotes, #4 of 2024-09-25
  5. Present and Future Generalization of Synthetic Image Detectors 18 upvotes, #5 of 2024-09-25
  6. EuroLLM: Multilingual Language Models for Europe 17 upvotes, #6 of 2024-09-25
  7. MonoFormer: One Transformer for Both Diffusion and Autoregression 17 upvotes, #6 of 2024-09-25
  8. Seeing Faces in Things: A Model and Dataset for Pareidolia 15 upvotes, #8 of 2024-09-25
  9. MaskBit: Embedding-free Image Generation via Bit Tokens 14 upvotes, #9 of 2024-09-25
  10. Improvements to SDXL in NovelAI Diffusion V3 10 upvotes, #10 of 2024-09-25
  11. Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts 9 upvotes, #11 of 2024-09-25
  12. Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation 6 upvotes, #12 of 2024-09-25
  13. DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control 4 upvotes, #13 of 2024-09-25
  14. Reward-Robust RLHF in LLMs 4 upvotes, #13 of 2024-09-25
  15. SLIMER-IT: Zero-Shot NER on Italian Language 4 upvotes, #13 of 2024-09-25
  16. Attention Prompting on Image for Large Vision-Language Models 4 upvotes, #13 of 2024-09-25
  17. RRM: Robust Reward Model Training Mitigates Reward Hacking 3 upvotes, #17 of 2024-09-25
  18. Tabular Data Generation using Binary Diffusion 3 upvotes, #17 of 2024-09-25

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.