Daily Papers of 2025-05-02

1. DeepCritic: Deliberate Critique with Large Language Models 48 upvotes, #1 of 2025-05-02
2. A Survey of Interactive Generative Video 43 upvotes, #2 of 2025-05-02
3. T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT 39 upvotes, #3 of 2025-05-02
4. Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks 21 upvotes, #4 of 2025-05-02
5. LLMs for Engineering: Teaching Models to Design High Powered Rockets 13 upvotes, #5 of 2025-05-02
6. TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models 13 upvotes, #5 of 2025-05-02
7. KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution 13 upvotes, #5 of 2025-05-02
8. AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization 11 upvotes, #8 of 2025-05-02
9. Spatial Speech Translation: Translating Across Space With Binaural Hearables 7 upvotes, #9 of 2025-05-02
10. MediAug: Exploring Visual Augmentation in Medical Imaging 6 upvotes, #10 of 2025-05-02
11. Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs 6 upvotes, #10 of 2025-05-02
12. A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic 2 upvotes, #12 of 2025-05-02

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.