| Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers | May 7, 2025 | MathReinforcement Learning (RL) | —Unverified | 0 |
| SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning | May 5, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| RM-R1: Reward Modeling as Reasoning | May 5, 2025 | MathReinforcement Learning (RL) | CodeCode Available | 2 |
| Rewriting Pre-Training Data Boosts LLM Performance in Math and Code | May 5, 2025 | Code GenerationGSM8K | CodeCode Available | 1 |
| Generating Narrated Lecture Videos from Slides with Synchronized Highlights | May 5, 2025 | Mathtext-to-speech | —Unverified | 0 |
| A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law | May 5, 2025 | MathMedical Diagnosis | —Unverified | 0 |
| LookAlike: Consistent Distractor Generation in Math MCQs | May 3, 2025 | Distractor GenerationMath | —Unverified | 0 |
| TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students | May 2, 2025 | GSM8KIn-Context Learning | CodeCode Available | 0 |
| NeMo-Inspector: A Visualization Tool for LLM Generation Analysis | May 1, 2025 | GSM8KMath | CodeCode Available | 1 |
| DeepCritic: Deliberate Critique with Large Language Models | May 1, 2025 | Math | CodeCode Available | 1 |
