Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 37 papers Another 215 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.
Introduces DistressBench, evaluating models' multidimensional support in crisis conversations
Published Oct 9
Evaluated models Muse Spark 1.2 , Muse Spark 1.3 , Muse Glimmer 30B and others20 Abstract The model is more restrained and acts less.DistressBench uses SSH dialogues written and revised by clinical personnel, and evaluates how much necessary care general chat models deliver according to weighted atomic criteria, rather than whether they refuse. When users disclose suicidal ideation or self-harm to a chat model, the authors consider the expected behavior to be recognizing the crisis, calibrating empathy, de-escalating, and referring to human help. Refusal-based evaluations cannot detect failing to act after recognizing the crisis.
Proposes Task Bank self-replay to mitigate held-out forgetting in continual instruction tuning
Published Oct 9
Evaluated models Qwen3-0.6B , Qwen3-1.7B , Qwen3-4B and others4 Abstract The authors claim self-replay can reduce forgetting outside the list, and that on the 4B model new task information helps with target selection, while smaller models do not.The authors study how language models, when learning new tasks, can use their own knowledge for broader self-preservation: given an incomplete list and forgetting that extends beyond the list, can the model generate replay and help choose targets.
提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤
Published Oct 7
Evaluated models Qwen2.5-3B-Instruct , Qwen2.5-14B-Instruct , gemma-3-4b-it and others8 Abstract 论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。
提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门
Published Oct 7
Evaluated models HuBERT-base , WavLM-base Abstract 论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。
提出 CARE，离线认证 VLA 加速配置的回合级失败风险并选出最快合格候选
Published Oct 7
Evaluated models OpenVLA-OFT , π0.5 , π0 and others5 Abstract CARE 以配对回合认证加速诱发失败，在预算内选最快候选，不足则保留参考。CARE 在部署前从加速配置中选出最快、且加速诱发失败风险能被有限样本认证为低于用户预算的候选。证据不足就保留全计算参考策略。
分析记忆与泛化如何决定机器遗忘的 retain 损伤
Published Oct 6
Evaluated models one-layer ReLU transformer , one-layer transformer (BMA, width doubled) , Hubble-8B-100B perturbed and others6 Abstract 作者称共享规则占比越高，遗忘带来的 retain damage 越大。作者考察学习方式如何左右 unlearning 的 retain damage：训练越依赖跨样本共享的解法，在匹配的遗忘程度上，retain 上的损失越大。
提出 ControlPed 与 HazardPed，生成可控行人危险场景并评测端到端驾驶
Published Oct 5
Evaluated models DiffusionDrive , SSR , VAD and others7 提出轨迹级可迁移对抗攻击，降低深度强化学习策略的期望回报
Published Oct 5
Evaluated models DQN , Double DQN (DDQN) Abstract 轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。这项工作研究 DRL 上的迁移式黑盒观测攻击 ：受害参数不可访问时，在白盒代理上造扰动再迁移。
提出选择性长时程精炼，筛选轨迹以提升终端智能体训练可靠性
Published Oct 5
Evaluated models Qwen/Qwen3-8B Abstract 中间长度的监督更均衡。这项工作研究终端智能体模仿学习里，教师轨迹应保留多少 token。
因果分解自生成反馈如何破坏测试时训练的长时程适应
Published Oct 4
Evaluated models 125M TTT-E2E , 760M TTT-E2E , 3B TTT-E2E and others5 Abstract 自写闭环损害真实文本预测。持久测试时更新若来自模型自己生成的文本，会同时改变模型和后续训练文本。作者在 PG-19 长流上分解这条闭环，并用独立文本决定是否提交更新。
提出 EmoRSS，推理时在拒绝子空间反向抵消情绪激活偏移以缓解过度拒答
Published Oct 4
Evaluated models Llama-3.1-8B-it , Qwen3-8B 提出 Geodesic Unlearning，沿测地线编辑权重以提升缺模态鲁棒性
Published Oct 4
Evaluated models RoBERTa , ResNet50 , Qwen2.5-3B and others6 Abstract GU 用测地线子空间编辑应对部署时缺模态下降，并尽量保住全模态精度。这项工作讨论多模态模型在部署时整段缺一个模态的性能下降，并把校正写成训练后的子空间编辑。
提出 Perturbot 扰动训练，打破 VLA 的模态捷径
Published Oct 3
Evaluated models π0.5 Abstract Perturbot 改训练数据以削弱三类模态捷径，GroundFscore 用来看成功是否来自任务证据。Perturbot 是一套不改推理的 VLA 训练期数据干预，用来削弱模态捷径，并用离线分数区分“任务变好”和“靠捷径变好”。
提出 R-Quest，用有效性与新颖性反馈维持推理模型自我进化
Published Oct 3
Evaluated models Qwen3-4B-Base , OctoThinker-3B-Hybrid-Base Abstract R-Quest 用有效性与新颖性反馈维持自进化。R-Quest 处理的是推理模型自进化中的题目质量：questioner 与 solver 用 GRPO 交替从自生成题目学习时，多轮之后平均成绩会下降。
提出 PowerBench，测量模型对权力转移请求的拒答偏见
Published Oct 2
Evaluated models grok-4.3 , haiku-4.5 , nova-2-lite and others18 Abstract 作者报告拒答随 SE/DE/PG 变化，并存在针对美国失权、智能体和语言的差。
提出 Local Support Learning，把微调适配器限制在当前数据支撑以缓解遗忘
Published Oct 2
Evaluated models Qwen2.5-7B-Instruct , Qwen2.5-3B-Instruct , Qwen2.5-1.5B-Instruct Abstract LSL 用 GMM 门把适配器限制在当前数据支撑内，以减轻多阶段遗忘。LSL 是不访问旧数据、在后训练中保持先前能力的框架。
提出 SAGO，以语义等价变体上的逐例行为稳定性评测大模型泛化
Published Oct 1
Evaluated models Llama-3.2-3B-Instruct , Llama-3.1-8B-Instruct , Gemma-2B-IT and others11 Abstract SAGO 用多轴逐例稳定性替代聚合准确率，十一个模型都未均匀泛化，且排名会随数据集改变。SAGO 把 LLM 泛化改写成同一目标与上下文在语义等价表达下的逐例行为稳定性，而不是单一基准上的聚合准确率。 。
提出 HeadEdit，经冻结 unembedding 做随输入变化的 logit 校正
Published Oct 1
Evaluated models Qwen3-4B , Gemma-3-4B-IT , Llama-3.2-3B-Instruct and others4 Abstract 低秩 unembedding 校正抬高九个设置的总体准确率，并可部分预测 DPO 更新。HeadEdit 是一种不更新参数的行为校准方法，作用点是冻结的 unembedding，而不是中间层残差或新的梯度优化。
提出预训练缩放律，估计野生 AI 网页文本相当于多少人类 token
Published Oct 1
Evaluated models nanochat 19.9M , 35.8M , 86.2M and others7 Abstract wild AI 文本对数据不足的模型先降损失，对高人类预算几乎立刻升损失。作者测量未标注的 wild AI 网页文本对预训练的影响，并提出一个能让 AI token 价值变号的缩放律。
提出 FAIL BANK，用运行时 CBF 反馈自进化更新 VLA 策略
Published Sep 30
Evaluated models π0.5 , π0