Tag: Adaptive Systems
All the articles with the tag "Adaptive Systems".
-
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
Published: at 11:27 AM
92.94 🤔本文提出了一种动态整合框架，通过自适应选择网络和动态加权融合策略从多个LLM中聚合知识，显著提升性能并减少50%的知识干扰，同时保持计算效率。
-
RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
Published: at 11:16 AM 90.48 🤔本文提出RL-of-Thoughts (RLoT) 方法，通过强化学习训练轻量化导航模型，在推理时动态构建任务特定逻辑结构，显著提升大型语言模型在多领域推理任务中的表现，并展现出跨模型和任务的强迁移能力。
-
Thought calibration: Efficient and confident test-time scaling
Published: at 11:22 AM 87.79 🤔本文提出‘思想校准’方法，通过推理树抽象和轻量级探针动态决定语言模型推理终止时机，在分布内数据上减少高达60%的思考token，同时保持性能，并在分布外数据上实现20%的减少。
-
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
Published: at 11:21 AM 87.78 🤔本文提出Route-To-Reason（RTR）框架，通过动态路由机制联合选择最优模型和推理策略，在多个推理任务上实现了更高的准确率和超过60%的token使用量减少，显著优化了性能与成本的权衡。
-
Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
Published: at 11:07 AM 87.75 🤔ASTRA introduces an efficient defense for Vision Language Models by adaptively steering activations away from adversarial directions using image attribution, achieving state-of-the-art performance in mitigating jailbreak attacks with minimal impact on benign utility and high inference efficiency.