Daily Papers of 2024-09-06

1. Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing 93 upvotes, #1 of 2024-09-06
2. Attention Heads of Large Language Models: A Survey 82 upvotes, #2 of 2024-09-06
3. FuzzCoder: Byte-level Fuzzing Test via Large Language Model 44 upvotes, #3 of 2024-09-06
4. From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents 24 upvotes, #4 of 2024-09-06
5. Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation 23 upvotes, #5 of 2024-09-06
6. mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding 22 upvotes, #6 of 2024-09-06
7. CDM: A Reliable Metric for Fair and Accurate Formula Recognition Evaluation 18 upvotes, #7 of 2024-09-06
8. WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild 17 upvotes, #8 of 2024-09-06
9. Building Math Agents with Multi-Turn Iterative Preference Learning 14 upvotes, #9 of 2024-09-06
10. Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries 11 upvotes, #10 of 2024-09-06
11. FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation 11 upvotes, #10 of 2024-09-06
12. Statically Contextualizing Large Language Models with Typed Holes 3 upvotes, #12 of 2024-09-06

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.