Daily Papers of 2024-07-15

  1. SpreadsheetLLM: Encoding Spreadsheets for Large Language Models 106 upvotes, #1 of 2024-07-15
  2. Human-like Episodic Memory for Infinite Context LLMs 51 upvotes, #2 of 2024-07-15
  3. Toto: Time Series Optimized Transformer for Observability 27 upvotes, #3 of 2024-07-15
  4. MUSCLE: A Model Update Strategy for Compatible LLM Evolution 19 upvotes, #4 of 2024-07-15
  5. H2O-Danube3 Technical Report 18 upvotes, #5 of 2024-07-15
  6. Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing 16 upvotes, #6 of 2024-07-15
  7. Transformer Layers as Painters 12 upvotes, #7 of 2024-07-15
  8. GAVEL: Generating Games Via Evolution and Language Models 12 upvotes, #7 of 2024-07-15
  9. StyleSplat: 3D Object Style Transfer with Gaussian Splatting 10 upvotes, #9 of 2024-07-15
  10. SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers 9 upvotes, #10 of 2024-07-15
  11. TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models 8 upvotes, #11 of 2024-07-15
  12. Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis 8 upvotes, #11 of 2024-07-15
  13. New Desiderata for Direct Preference Optimization 6 upvotes, #13 of 2024-07-15
  14. Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning 5 upvotes, #14 of 2024-07-15
  15. Characterizing Prompt Compression Methods for Long Context Inference 5 upvotes, #14 of 2024-07-15
  16. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training 5 upvotes, #14 of 2024-07-15
  17. RRM: Relightable assets using Radiance guided Material extraction 4 upvotes, #17 of 2024-07-15

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.