AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
"自适应推理" 相关文章
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
Fractional Reasoning in LLMs: A New Way to Control Inference Depth
Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
低Token高精度！字节复旦推出自适应推理框架CAR
低Token高精度！字节复旦推出自适应推理框架CAR
Researchers from the National University of Singapore Introduce ‘Thinkless,’ an Adaptive Framework that Reduces Unnecessary Reasoning by up to 90% Using DeGRPO
MatMamba: A New State Space Model that Builds upon Mamba2 by Integrating a Matryoshka-Style Nested Structure
