Daily Papers of 2023-11-14

  1. Music ControlNet: Multiple Time-varying Controls for Music Generation 44 upvotes, #1 of 2023-11-14
  2. ChatAnything: Facetime Chat with LLM-Enhanced Personas 35 upvotes, #2 of 2023-11-14
  3. Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text 29 upvotes, #3 of 2023-11-14
  4. Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models 27 upvotes, #4 of 2023-11-14
  5. GOAT: GO to Any Thing 15 upvotes, #5 of 2023-11-14
  6. To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning 15 upvotes, #5 of 2023-11-14
  7. GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation 14 upvotes, #7 of 2023-11-14
  8. SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models 14 upvotes, #7 of 2023-11-14
  9. The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4 13 upvotes, #9 of 2023-11-14
  10. MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks 13 upvotes, #9 of 2023-11-14
  11. LayoutPrompter: Awaken the Design Ability of Large Language Models 11 upvotes, #11 of 2023-11-14
  12. Trusted Source Alignment in Large Language Models 11 upvotes, #11 of 2023-11-14
  13. Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer 8 upvotes, #13 of 2023-11-14
  14. Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data 6 upvotes, #14 of 2023-11-14

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.