| LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning | May 24, 2025 | Computational EfficiencyMMLU | CodeCode Available | 0 |
| INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling | May 22, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Cost-aware LLM-based Online Dataset Annotation | May 21, 2025 | MMLU | —Unverified | 0 |
| Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning | May 20, 2025 | MMLUReinforcement Learning (RL) | —Unverified | 0 |
| Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst | May 20, 2025 | ARCGSM8K | —Unverified | 0 |
| Dual Decomposition of Weights and Singular Value Low Rank Adaptation | May 20, 2025 | GSM8KMMLU | —Unverified | 0 |
| Void in Language Models | May 20, 2025 | MMLUResponse Generation | CodeCode Available | 0 |
| Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings | May 19, 2025 | HumanEvalMath | CodeCode Available | 0 |
| Critique-Guided Distillation: Improving Supervised Fine-tuning via Better Distillation | May 16, 2025 | MathMMLU | —Unverified | 0 |
| Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models | May 16, 2025 | DiversityMMLU | CodeCode Available | 0 |
