Daily Papers of 2024-08-29

  1. Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders 76 upvotes, #1 of 2024-08-29
  2. BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline 51 upvotes, #2 of 2024-08-29
  3. Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models 41 upvotes, #3 of 2024-08-29
  4. LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation 19 upvotes, #4 of 2024-08-29
  5. Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models 19 upvotes, #4 of 2024-08-29
  6. Distribution Backtracking Builds A Faster Convergence Trajectory for One-step Diffusion Distillation 15 upvotes, #6 of 2024-08-29
  7. Efficient LLM Scheduling by Learning to Rank 14 upvotes, #7 of 2024-08-29
  8. Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature 11 upvotes, #8 of 2024-08-29
  9. Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts 10 upvotes, #9 of 2024-08-29
  10. In-Context Imitation Learning via Next-Token Prediction 9 upvotes, #10 of 2024-08-29
  11. ReMamba: Equip Mamba with Effective Long-Sequence Modeling 8 upvotes, #11 of 2024-08-29
  12. Towards Realistic Example-based Modeling via 3D Gaussian Stitching 7 upvotes, #12 of 2024-08-29
  13. TEDRA: Text-based Editing of Dynamic and Photoreal Actors 4 upvotes, #13 of 2024-08-29

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.