Daily Papers of 2025-05-05

1. PixelHacker: Image Inpainting with Structural and Semantic Consistency 40 upvotes, #1 of 2025-05-05
2. Llama-Nemotron: Efficient Reasoning Models 32 upvotes, #2 of 2025-05-05
3. Improving Editability in Image Generation with Layer-wise Memory 27 upvotes, #3 of 2025-05-05
4. Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts 25 upvotes, #4 of 2025-05-05
5. Real-World Gaps in AI Governance Research 11 upvotes, #5 of 2025-05-05
6. CORG: Generating Answers from Complex, Interrelated Contexts 8 upvotes, #6 of 2025-05-05
7. WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation 5 upvotes, #7 of 2025-05-05
8. X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation 3 upvotes, #8 of 2025-05-05
9. TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching 3 upvotes, #8 of 2025-05-05

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.