Daily Papers of 2024-02-26

  1. MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases 134 upvotes, #1 of 2024-02-26
  2. Genie: Generative Interactive Environments 72 upvotes, #2 of 2024-02-26
  3. Orca-Math: Unlocking the potential of SLMs in Grade School Math 25 upvotes, #3 of 2024-02-26
  4. Watermarking Makes Language Models Radioactive 23 upvotes, #4 of 2024-02-26
  5. Divide-or-Conquer? Which Part Should You Distill Your LLM? 22 upvotes, #5 of 2024-02-26
  6. GPTVQ: The Blessing of Dimensionality for LLM Quantization 21 upvotes, #6 of 2024-02-26
  7. Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition 21 upvotes, #6 of 2024-02-26
  8. ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition 20 upvotes, #8 of 2024-02-26
  9. Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models 18 upvotes, #9 of 2024-02-26
  10. AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning 17 upvotes, #10 of 2024-02-26
  11. API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs 13 upvotes, #11 of 2024-02-26
  12. Seamless Human Motion Composition with Blended Positional Encodings 13 upvotes, #11 of 2024-02-26
  13. CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models 12 upvotes, #13 of 2024-02-26

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.