Daily Papers of 2024-02-20

  1. FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models 83 upvotes, #1 of 2024-02-20
  2. FiT: Flexible Vision Transformer for Diffusion Model 48 upvotes, #2 of 2024-02-20
  3. AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling 45 upvotes, #3 of 2024-02-20
  4. Speculative Streaming: Fast LLM Inference without Auxiliary Models 42 upvotes, #4 of 2024-02-20
  5. OneBit: Towards Extremely Low-bit Large Language Models 24 upvotes, #5 of 2024-02-20
  6. Learning to Learn Faster from Human Feedback with Language Model Predictive Control 23 upvotes, #6 of 2024-02-20
  7. CoLLaVO: Crayon Large Language and Vision mOdel 21 upvotes, #7 of 2024-02-20
  8. LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration 18 upvotes, #8 of 2024-02-20
  9. Reformatted Alignment 17 upvotes, #9 of 2024-02-20
  10. GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements 11 upvotes, #10 of 2024-02-20
  11. Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning 10 upvotes, #11 of 2024-02-20
  12. DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation 10 upvotes, #11 of 2024-02-20
  13. Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis 10 upvotes, #11 of 2024-02-20
  14. Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability 8 upvotes, #14 of 2024-02-20

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.