Daily Papers of 2023-11-16

1. Drivable 3D Gaussian Avatars 47 upvotes, #1 of 2023-11-16
2. DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model 22 upvotes, #2 of 2023-11-16
3. Single-Image 3D Human Digitization with Shape-Guided Diffusion 22 upvotes, #2 of 2023-11-16
4. EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis 18 upvotes, #4 of 2023-11-16
5. Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models 13 upvotes, #5 of 2023-11-16
6. GRIM: GRaph-based Interactive narrative visualization for gaMes 13 upvotes, #5 of 2023-11-16
7. UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations 11 upvotes, #7 of 2023-11-16
8. SiRA: Sparse Mixture of Low Rank Adaptation 9 upvotes, #8 of 2023-11-16
9. UT5: Pretraining Non autoregressive T5 with unrolled denoising 8 upvotes, #9 of 2023-11-16
10. PEARL: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers 8 upvotes, #9 of 2023-11-16
11. Thread of Thought Unraveling Chaotic Contexts 7 upvotes, #11 of 2023-11-16
12. Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation 7 upvotes, #11 of 2023-11-16
13. Fusion-Eval: Integrating Evaluators with LLMs 6 upvotes, #13 of 2023-11-16

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.