| Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning | May 17, 2025 | AllChunking | CodeCode Available | 0 |
| Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO | May 16, 2025 | AllDiversity | —Unverified | 0 |
| Addition is almost all you need: Compressing neural networks with double binary factorization | May 16, 2025 | AllBinarization | CodeCode Available | 0 |
| ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization | May 16, 2025 | AllDeepFake Detection | CodeCode Available | 2 |
| FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks | May 16, 2025 | All | CodeCode Available | 1 |
| What Does Neuro Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs | May 15, 2025 | AllBenchmarking | —Unverified | 0 |
| All You Need Is Synthetic Task Augmentation | May 15, 2025 | AllMolecular Property Prediction | —Unverified | 0 |
| Beyond Pairwise Learning-To-Rank At Airbnb | May 14, 2025 | AllLearning-To-Rank | —Unverified | 0 |
| Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning | May 13, 2025 | AllMachine Unlearning | —Unverified | 0 |
| An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits | May 12, 2025 | AllKnowledge Distillation | —Unverified | 0 |
