Daily Papers of 2023-12-19

1. VecFusion: Vector Font Generation with Diffusion 21 upvotes, #1 of 2023-12-19
2. G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model 20 upvotes, #2 of 2023-12-19
3. Rich Human Feedback for Text-to-Image Generation 19 upvotes, #3 of 2023-12-19
4. SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing 19 upvotes, #3 of 2023-12-19
5. GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning 19 upvotes, #3 of 2023-12-19
6. M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts 18 upvotes, #6 of 2023-12-19
7. MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising 14 upvotes, #7 of 2023-12-19
8. Paloma: A Benchmark for Evaluating Language Model Fit 12 upvotes, #8 of 2023-12-19
9. VidToMe: Video Token Merging for Zero-Shot Video Editing 10 upvotes, #9 of 2023-12-19
10. Silkie: Preference Distillation for Large Visual Language Models 10 upvotes, #9 of 2023-12-19
11. MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance 10 upvotes, #9 of 2023-12-19
12. Cascade Speculative Drafting for Even Faster LLM Inference 9 upvotes, #12 of 2023-12-19
13. Catwalk: A Unified Language Model Evaluation Framework for Many Datasets 7 upvotes, #13 of 2023-12-19
14. ProTIP: Progressive Tool Retrieval Improves Planning 7 upvotes, #13 of 2023-12-19
15. Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models 7 upvotes, #13 of 2023-12-19
16. VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder 5 upvotes, #16 of 2023-12-19
17. GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis 4 upvotes, #17 of 2023-12-19

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.