Daily Papers of 2024-04-23

1. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone 222 upvotes, #1 of 2024-04-23
2. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions 36 upvotes, #2 of 2024-04-23
3. How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study 36 upvotes, #2 of 2024-04-23
4. FlowMind: Automatic Workflow Generation with LLMs 31 upvotes, #4 of 2024-04-23
5. Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis 25 upvotes, #5 of 2024-04-23
6. A Multimodal Automated Interpretability Agent 17 upvotes, #6 of 2024-04-23
7. SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation 16 upvotes, #7 of 2024-04-23
8. Music Consistency Models 11 upvotes, #8 of 2024-04-23
9. MultiBooth: Towards Generating All Your Concepts in an Image from Text 7 upvotes, #9 of 2024-04-23
10. Learning H-Infinity Locomotion Control 6 upvotes, #10 of 2024-04-23
11. Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer 5 upvotes, #11 of 2024-04-23

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.