Daily Papers of 2023-09-21

1. LMDX: Language Model-based Document Information Extraction and Localization 67 upvotes, #1 of 2023-09-21
2. FreeU: Free Lunch in Diffusion U-Net 66 upvotes, #2 of 2023-09-21
3. DreamLLM: Synergistic Multimodal Comprehension and Creation 60 upvotes, #3 of 2023-09-21
4. Kosmos-2.5: A Multimodal Literate Model 56 upvotes, #4 of 2023-09-21
5. Chain-of-Verification Reduces Hallucination in Large Language Models 39 upvotes, #5 of 2023-09-21
6. End-to-End Speech Recognition Contextualization with Large Language Models 9 upvotes, #6 of 2023-09-21
7. A Large-scale Dataset for Audio-Language Representation Learning 9 upvotes, #6 of 2023-09-21
8. The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute 4 upvotes, #8 of 2023-09-21
9. Controllable Dynamic Appearance for Neural 3D Portraits 2 upvotes, #9 of 2023-09-21

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.