| Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training | May 20, 2025 | AllDomain Generalization | —Unverified | 0 |
| General-Reasoner: Advancing LLM Reasoning Across All Domains | May 20, 2025 | AllMath | CodeCode Available | 3 |
| Not All Correct Answers Are Equal: Why Your Distillation Source Matters | May 20, 2025 | All | —Unverified | 0 |
| Half Search Space is All You Need | May 19, 2025 | AllGPU | —Unverified | 0 |
| Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis | May 19, 2025 | AllMulti-Armed Bandits | —Unverified | 0 |
| Degradation-Aware Feature Perturbation for All-in-One Image Restoration | May 19, 2025 | AllDeblurring | CodeCode Available | 2 |
| Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice | May 19, 2025 | AllHallucination | —Unverified | 0 |
| Synthetic Data RL: Task Definition Is All You Need | May 18, 2025 | AllGSM8K | CodeCode Available | 2 |
| One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models | May 18, 2025 | All | —Unverified | 0 |
| Not All Documents Are What You Need for Extracting Instruction Tuning Data | May 18, 2025 | AllContrastive Learning | —Unverified | 0 |
