Daily Papers of 2025-01-17

1. Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps 65 upvotes, #1 of 2025-01-17
2. OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking 46 upvotes, #2 of 2025-01-17
3. Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models 35 upvotes, #3 of 2025-01-17
4. Learnings from Scaling Visual Tokenizers for Reconstruction and Generation 33 upvotes, #4 of 2025-01-17
5. Do generative video models learn physical principles from watching videos? 30 upvotes, #5 of 2025-01-17
6. FAST: Efficient Action Tokenization for Vision-Language-Action Models 22 upvotes, #6 of 2025-01-17
7. Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators 19 upvotes, #7 of 2025-01-17
8. SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces 18 upvotes, #8 of 2025-01-17
9. CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation 17 upvotes, #9 of 2025-01-17
10. AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation 12 upvotes, #10 of 2025-01-17
11. The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models 12 upvotes, #10 of 2025-01-17
12. RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation 10 upvotes, #12 of 2025-01-17

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.