Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 47 papers Another 233 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.
Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance
Published Oct 9
Evaluated models PPO Abstract Local closed-loop generation of JSON edge cases.The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.
Proposes EndoRSI, recursively improving endoscopic robot policies with physical evidence
Published Oct 9
Evaluated models Qwen3-VL-4B A survey of risks, defenses, and evaluation in the six-stage lifecycle of world models
Published Oct 9 Abstract Safety is written as a property of the prediction-decision closed loop; claims must be linked to observed consequences and versions.World model safety is organized by the nature of the prediction-decision loop, not by isolated prediction scores.
Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints
Published Oct 9 Abstract FAITH separates safety filtering from reward optimization.FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.
Propose COAP, which uses stateful code to control a robot at test time without a model
Published Oct 9 提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
Published Oct 7
Evaluated models OpenVLA , UniVLA , π0.5 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。
提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉
Published Oct 7
Evaluated models OpenVLA , π0.5 Abstract SOUL 以稀疏特征遗忘 VLA 状态幻觉。SOUL 用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。
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。
提出 VeriFine，用双环协同扩展验证以实现具身推理自我改进
Published Oct 7
Evaluated models Alpamayo 1.5 8B , Qwen3-VL 2B , Claude Opus 5 Abstract VeriFine 用双环协同演化具身推理的策略、课程和评审，驾驶与导航的策略分和评审对齐都上升。VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化，用来处理固定评审跟不上新失败模式的问题。
TAPDreamer 用公开编码器做固定补丁。
Published Oct 6
Evaluated models FastWAM , DreamWAM-uncond , DreamWAM-joint and others4 提出 Inspect Robots，在真实机器人上评测具身模型的能力与拒答
Published Oct 5
Evaluated models Astra（GPT-6 Astra） , GPT-6 Sol , GPT-5.6 Sol and others7 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。
评测文本守卫与激活探针能否拦住机器人隐含伤害指令
Published Oct 5
Evaluated models π0.5 , OpenVLA-OFT , Llama Guard 3 and others10 提出用可逆网络为给定 AI 控制器寻找可证明前向不变集
Published Oct 5
Evaluated models Pendulum AI-controller , Cart pole AI-controller , PVTOL AI-controller Abstract 用潜空间超矩形加解析验证，为事先给定的 AI 控制器寻找 FIS。本文处理的是认证场景：AI 控制器事先给定，不能为了构造 Lyapunov 函数去改控制器，却仍要给出可解析核验的安全依据。
提出 VICS-G 可行未来解码，重排冻结 VLA 策略的动作候选
Published Oct 4
Evaluated models SafeVLA (task-optimized / base) , SafeVLA (safety-aligned / safe) Abstract 作者用可行未来解码重排冻结 VLA 的下一步，并称 VICS-G 降低观测代价且完成率接近策略采样。训练无关解码器 VICS 在冻结 VLA 的推理阶段重排动作块，使当前选择带上该动作仍可能留下的安全完成质量。
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 CrashSim 用真实事故先验引导扩散仿真并构建 nuCrash 评测自动驾驶规划器
Published Oct 3
Evaluated models Lane-graph planner , PDM-closed planner , IL planner and others5 Abstract CrashSim 迁入真实事故先验生成场景。CrashSim 用检索到的真实事故先验引导扩散式多车仿真，为自动驾驶安全评测生成碰撞与近碰撞场景。 。
提出条件特征抑制防御，检出对抗补丁后抑制 VLA 内部特征
Published Oct 2
Evaluated models π0.5 , SmolVLA Abstract 条件抑制与 patch 相关的 SAE 特征，间歇攻击下可提高 SR，持续攻击下则不能。