Daily Papers of 2024-01-09

  1. Mixtral of Experts 161 upvotes, #1 of 2024-01-09
  2. MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts 74 upvotes, #2 of 2024-01-09
  3. Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM 52 upvotes, #3 of 2024-01-09
  4. Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon 30 upvotes, #4 of 2024-01-09
  5. GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation 21 upvotes, #5 of 2024-01-09
  6. DiarizationLM: Speaker Diarization Post-Processing with Large Language Models 17 upvotes, #6 of 2024-01-09
  7. AST-T5: Structure-Aware Pretraining for Code Generation and Understanding 14 upvotes, #7 of 2024-01-09
  8. CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution 11 upvotes, #8 of 2024-01-09
  9. Has Your Pretrained Model Improved? A Multi-head Posterior Based Approach 10 upvotes, #9 of 2024-01-09
  10. AGG: Amortized Generative 3D Gaussians for Single Image to 3D 10 upvotes, #9 of 2024-01-09
  11. TeleChat Technical Report 8 upvotes, #11 of 2024-01-09

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.