Posts
All the articles I've posted.
-
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。
-
Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs
Published: at 11:14 AM 87.75 🤔本文提出了一种动态自适应的混合训练框架 SASR，通过基于梯度范数和 KL 散度的动态调整机制结合 SFT 和 RL，在数学推理和逻辑推理任务上显著提升了大语言模型的性能，优于传统 SFT、RL 和静态混合方法。
-
Sparse-Group Boosting with Balanced Selection Frequencies: A Simulation-Based Approach and R Implementation
Published: at 10:25 AM 87.75 🤔This paper introduces sparse-group boosting and a simulation-based group balancing algorithm within the 'sgboost' R package to mitigate variable selection bias in high-dimensional grouped data, demonstrating improved fairness and interpretability through simulations and ecological data analysis.
-
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.