| Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning | Jul 16, 2025 | DiversityMMLU | —Unverified | 0 |
| Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs | Jul 15, 2025 | DiversityMMLU | CodeCode Available | 0 |
| Lizard: An Efficient Linearization Framework for Large Language Models | Jul 11, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Integrating External Tools with Large Language Models to Improve Accuracy | Jul 9, 2025 | Mathematical ReasoningMMLU | —Unverified | 0 |
| Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate | Jul 8, 2025 | Continual LearningMixture-of-Experts | CodeCode Available | 0 |
| The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains | Jul 8, 2025 | MathMMLU | CodeCode Available | 1 |
| any4: Learned 4-bit Numeric Representation for LLMs | Jul 7, 2025 | GPUGSM8K | CodeCode Available | 2 |
| Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training | Jul 7, 2025 | General KnowledgeMMLU | —Unverified | 0 |
| Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations | Jul 7, 2025 | AttributeMMLU | CodeCode Available | 0 |
| Multi-lingual Functional Evaluation for Large Language Models | Jun 25, 2025 | BelebeleInstruction Following | —Unverified | 0 |