| TreeRPO: Tree Relative Policy Optimization | Jun 5, 2025 | Math | CodeCode Available | 0 |
| Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers | Jun 5, 2025 | GSM8KMath | —Unverified | 0 |
| MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning | Jun 5, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning | Jun 5, 2025 | MathVisual Grounding | —Unverified | 0 |
| Guided Speculative Inference for Efficient Test-Time Alignment of LLMs | Jun 4, 2025 | Math | CodeCode Available | 0 |
| OpenThoughts: Data Recipes for Reasoning Models | Jun 4, 2025 | Math | CodeCode Available | 7 |
| Rectified Sparse Attention | Jun 4, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models | Jun 4, 2025 | Math | CodeCode Available | 1 |
| MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching | Jun 3, 2025 | Data AugmentationInstruction Following | —Unverified | 0 |
| Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem | Jun 3, 2025 | GPUMath | —Unverified | 0 |
