Daily Papers of 2024-02-19

  1. Linear Transformers with Learnable Kernel Functions are Better In-Context Models 81 upvotes, #1 of 2024-02-19
  2. In Search of Needles in a 10M Haystack: Recurrent Memory Finds What LLMs Miss 42 upvotes, #2 of 2024-02-19
  3. SPAR: Personalized Content-Based Recommendation via Long Engagement Attention 35 upvotes, #3 of 2024-02-19
  4. DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows 31 upvotes, #4 of 2024-02-19
  5. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing 27 upvotes, #5 of 2024-02-19
  6. LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models 23 upvotes, #6 of 2024-02-19
  7. Large Language Models as Zero-shot Dialogue State Tracker through Function Calling 18 upvotes, #7 of 2024-02-19
  8. Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation 17 upvotes, #8 of 2024-02-19
  9. GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting 16 upvotes, #9 of 2024-02-19
  10. PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter 16 upvotes, #9 of 2024-02-19
  11. Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots 15 upvotes, #11 of 2024-02-19
  12. RLVF: Learning from Verbal Feedback without Overgeneralization 11 upvotes, #12 of 2024-02-19

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.