Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知
Published Oct 7
Evaluated models CLIP ViT-B/32 , CLIP ViT-L/14 , Qwen2-VL-7B Abstract 论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。
论证发布时互信息不能认证开源权重抗微调恢复
Published Oct 7
Evaluated models EleutherAI/deep-ignorance-e2e-strong-filter , EleutherAI/deep-ignorance-unfiltered , Google BERT-Tiny and others6 Abstract 作者称零信息仍可一步恢复，表观抗微调可来自参数化。作者研究开源权重模型的篡改抵抗：发布时的互信息是否足以保证微调恢复很慢。
固定有害指令，单轴归因图像到文本越狱的图像属性
Published Oct 4
Evaluated models GPT-4o , Claude Sonnet 4.5 , Qwen3-VL-8B-Instruct and others6 Abstract 固定文本的图像越狱拆解，只在 Qwen 上给出一条有界相关性归因。
分析零训练 LLM+OVOD 流水线中 CAAP 与 SNAP 分离的来源
Published Sep 26
Evaluated models Gemma-3 4B , YOLO-World X , Qwen2.5-VL 7B and others4 提出 SALVE，用文本优化检测蒸馏数据中的潜意识学习效应
Published Sep 15
Evaluated models Qwen2.5-7B-Instruct , OLMo-3-7B-Instruct , Llama-3.1-8B-Instruct and others7 Abstract SALVE 用软提示加 beam search 口头化，把潜意识数据里的教师特质恢复成可读提示。SALVE 是一种文本优化方法，用来在训练学生之前，把潜意识学习数据里读不出来的教师特质说成可读系统提示。
因果审计视觉工具调用，分离观察贡献与动作诱发捷径
Published Aug 7
Evaluated models DeepEyes , Pixel Reasoner , Mini-o3 and others6 Abstract 聚合增益集中在 Calibrated 少数轨迹，作者称之为视觉工具使用的错觉。对六个 thinking-with-images 模型做因果审计，检查 crop-and-zoom 返回的观察是否中介最终答案。
比较越狱微调与权重正交化去对齐对有害协助和有用性的影响
Published Apr 3
Evaluated models Qwen3-4B-Instruct-2507 , Llama-3.1-8B-Instruct , Qwen2.5-14B and others6 量化微调对仅输入侧 PII 的非预期记忆并比较隐私缓解
Published Jan 24
Evaluated models Llama 3.2 1B , Llama 3.2 3B , Llama 3.1 8B and others7 You have reached the end