I code or AI code: A comparative evaluation of AI-rated scores in classroom observations
研究使用GPT-5模型对幼儿课堂师生互动进行评分,并与人工评分比较,发现AI在情感支持领域表现较好,但在组织和教学支持方面差异较大。
研究使用GPT-5模型对幼儿课堂师生互动进行评分,并与人工评分比较,发现AI在情感支持领域表现较好,但在组织和教学支持方面差异较大。
为解决粤语书面数据稀缺问题,通过CPT、chat-vector合并等方法训练CantoneseLLM v2模型,提高粤语推理能力。
研究提出了一种利用光学黑像素的轻量级方法来检测针对图像传感器的电磁信号注入攻击,该方法在不同攻击条件下表现出高达99.6%的ROC-AUC值和低至0.027的EER。
本文提出Reflection Steering框架,通过在激活空间中分离反射与推理,减少大型推理模型中的冗余反思,从而节省推理令牌并提高效率。
This work addresses the dilemma faced by current large language models, where safety alignment either distorts semantic representations through fine-tuning or incurs high inference costs. The authors propose a training-free geometric safety mechanism that freezes the pretrained encoder and maps text embeddings onto the unit hypersphere. Leveraging a precomputed library of topological anchor points, the method performs zero-shot safety judgments via Gibbs–Boltzmann free energy and a dual-timescale exponential moving average, effectively decoupling representation learning from inference. Requiring only a few fixed hyperparameters, the approach significantly enhances robustness against high-frequency perturbations and achieves state-of-the-art performance across eight benchmarks—e.g., AuthenHallu AUC = 1.0000 and HarmBench AUC = 0.9802—while offering sub-millisecond latency, zero cold-start overhead, and strong cross-lingual transferability, as demonstrated by CHIFRAUD AUC = 0.9758 on Chinese data.
研究使用GPT-5模型对幼儿课堂师生互动进行评分,并与人工评分比较,发现AI在情感支持领域表现较好,但在组织和教学支持方面差异较大。
为解决粤语书面数据稀缺问题,通过CPT、chat-vector合并等方法训练CantoneseLLM v2模型,提高粤语推理能力。
研究提出了一种利用光学黑像素的轻量级方法来检测针对图像传感器的电磁信号注入攻击,该方法在不同攻击条件下表现出高达99.6%的ROC-AUC值和低至0.027的EER。
本文提出Reflection Steering框架,通过在激活空间中分离反射与推理,减少大型推理模型中的冗余反思,从而节省推理令牌并提高效率。
This work addresses the dilemma faced by current large language models, where safety alignment either distorts semantic representations through fine-tuning or incurs high inference costs. The authors propose a training-free geometric safety mechanism that freezes the pretrained encoder and maps text embeddings onto the unit hypersphere. Leveraging a precomputed library of topological anchor points, the method performs zero-shot safety judgments via Gibbs–Boltzmann free energy and a dual-timescale exponential moving average, effectively decoupling representation learning from inference. Requiring only a few fixed hyperparameters, the approach significantly enhances robustness against high-frequency perturbations and achieves state-of-the-art performance across eight benchmarks—e.g., AuthenHallu AUC = 1.0000 and HarmBench AUC = 0.9802—while offering sub-millisecond latency, zero cold-start overhead, and strong cross-lingual transferability, as demonstrated by CHIFRAUD AUC = 0.9758 on Chinese data.