| SiLVR: A Simple Language-based Video Reasoning Framework | May 30, 2025 | MathMME | CodeCode Available | 1 |
| HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts | May 30, 2025 | ARCGeneral Knowledge | CodeCode Available | 1 |
| Model Unlearning via Sparse Autoencoder Subspace Guided Projections | May 30, 2025 | Adversarial Robustnessfeature selection | —Unverified | 0 |
| Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation | May 30, 2025 | Continual PretrainingFairness | CodeCode Available | 0 |
| Revisiting Uncertainty Estimation and Calibration of Large Language Models | May 29, 2025 | Mixture-of-ExpertsMMLU | —Unverified | 0 |
| Actor-Critic based Online Data Mixing For Language Model Pre-Training | May 29, 2025 | HumanEvalLanguage Modeling | —Unverified | 0 |
| DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors | May 29, 2025 | MMLUMultiple-choice | CodeCode Available | 0 |
| Large Language Models Often Know When They Are Being Evaluated | May 28, 2025 | MMLUMultiple-choice | —Unverified | 0 |
| Reinforcing General Reasoning without Verifiers | May 27, 2025 | MathMathematical Reasoning | CodeCode Available | 2 |
| Capability-Based Scaling Laws for LLM Red-Teaming | May 26, 2025 | MMLUPrompt Engineering | CodeCode Available | 0 |
