Daily Papers of 2023-11-13

  1. Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks 98 upvotes, #1 of 2023-11-13
  2. JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models 37 upvotes, #2 of 2023-11-13
  3. Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model 33 upvotes, #3 of 2023-11-13
  4. FinGPT: Large Generative Models for a Small Language 28 upvotes, #4 of 2023-11-13
  5. Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs 28 upvotes, #4 of 2023-11-13
  6. Prompt Engineering a Prompt Engineer 22 upvotes, #6 of 2023-11-13
  7. Language Models can be Logical Solvers 19 upvotes, #7 of 2023-11-13
  8. Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization 18 upvotes, #8 of 2023-11-13
  9. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores 14 upvotes, #9 of 2023-11-13
  10. ADaPT: As-Needed Decomposition and Planning with Language Models 11 upvotes, #10 of 2023-11-13
  11. Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities 10 upvotes, #11 of 2023-11-13
  12. PolyMaX: General Dense Prediction with Mask Transformer 7 upvotes, #12 of 2023-11-13
  13. Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems 7 upvotes, #12 of 2023-11-13
  14. FMViT: A multiple-frequency mixing Vision Transformer 6 upvotes, #14 of 2023-11-13

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.