Daily Papers of 2023-07-25

  1. 3D-LLM: Injecting the 3D World into Large Language Models 40 upvotes, #1 of 2023-07-25
  2. A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis 37 upvotes, #2 of 2023-07-25
  3. Interpolating between Images with Diffusion Models 21 upvotes, #3 of 2023-07-25
  4. Prompting Large Language Models with Speech Recognition Abilities 18 upvotes, #4 of 2023-07-25
  5. Question Decomposition Improves the Faithfulness of Model-Generated Reasoning 15 upvotes, #5 of 2023-07-25
  6. PUMA: Secure Inference of LLaMA-7B in Five Minutes 15 upvotes, #5 of 2023-07-25
  7. Evaluating the Ripple Effects of Knowledge Editing in Language Models 13 upvotes, #7 of 2023-07-25
  8. Optimized Network Architectures for Large Language Model Training with Billions of Parameters 11 upvotes, #8 of 2023-07-25
  9. RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment 11 upvotes, #8 of 2023-07-25
  10. Less is More: Focus Attention for Efficient DETR 7 upvotes, #10 of 2023-07-25
  11. MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features 7 upvotes, #10 of 2023-07-25
  12. Multiscale Video Pretraining for Long-Term Activity Forecasting 6 upvotes, #12 of 2023-07-25

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.