safety

AI-Assisted Systematization for Evaluating GenAI Systems

arXiv:2605.26001v1 Announce Type: cross Abstract: Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as 'reasoning,' 'fairne

AI-Driven Controlled Environment Agriculture as Resilient Infrastructure for U.S. Fresh-Produce Supply Chains

DGX agent

arXiv:2605.23946v1 Announce Type: cross Abstract: Climate volatility, regional production concentration, labor constraints, cyber risk, and dependence on long-distance fresh-produce supply chains expo

safetyarxiv-cs-ai

26 May 2026

Analogies between Transformer Layers and Power Method

arXiv:2605.25619v1 Announce Type: new Abstract: In the paper we show that there is an analogy between the operations occurring in a layer of a transformer (projections and layer normalizations, disreg

Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation

arXiv:2605.25402v1 Announce Type: cross Abstract: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing meth

and you, through stock index funds, and because of some recent rule changes, will basically be forced to buy this garbage. Elon’s about to t…

and you, through stock index funds, and because of some recent rule changes, will basically be forced to buy this garbage. Elon’s about to take a big chunk of your retirement, and unless you call your

safetygary-marcus--x

Anthropic: fantasy versus reality.

Gary Marcus critiques Anthropic's claims about their AI capabilities, likely contrasting inflated marketing promises with the actual technical limitations and performance of their systems. The post pr

safetygary-marcus--x

AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond

arXiv:2605.26113v1 Announce Type: new Abstract: Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long t

safetyarxiv-cs-ro

Approximating Safety Feedback Without a Safety Oracle via Model Predictive Control

arXiv:2510.20955v2 Announce Type: replace Abstract: Safe decision-making algorithms for control of mobile robots often require the existence of feedback to verify the safety of proposed actions. This

Auditing medical multi-agent AI reveals risks of false consensus

arXiv:2510.10185v2 Announce Type: replace-cross Abstract: Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through sp

Authority Inversion in LLM-Mediated Ubiquitous Systems: When Models Trust Users Over Sensors

arXiv:2605.23938v1 Announce Type: new Abstract: Large language models (LLMs) increasingly fuse heterogeneous inputs in ubiquitous systems. Yet, how LLMs implicitly allocate authority when sensor measu

Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction

arXiv:2512.15605v4 Announce Type: replace Abstract: Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent anoth

AvAtar: Learning to Align via Active Optimal Transport

arXiv:2605.24395v1 Announce Type: new Abstract: Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration.

Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems

arXiv:2605.24458v1 Announce Type: cross Abstract: The integration of fairness and privacy in centralized data-driven applications is critical, especially as these systems increasingly influence sector

Beyond Killer Robots: General AI Attitudes and Public Support for Military AI in Nine Countries

arXiv:2605.25196v1 Announce Type: cross Abstract: AI-enabled military systems are a fixture of modern military conflict. Applications vary from autonomous drones for surveillance and attack to AI-supp

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training

arXiv:2505.20110v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) excel at sampling diverse, high-reward objects. In many practical applications where active reward querie

Beyond the Target: From Imitation to Collaboration in Speculative Decoding

arXiv:2605.24793v1 Announce Type: new Abstract: Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are ver

Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization

arXiv:2605.25129v1 Announce Type: new Abstract: Diffusion models have shown promise in learning to solve constraint optimization problems. However, they are mostly restricted to problems with binary v

Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion

arXiv:2605.24975v1 Announce Type: cross Abstract: Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively

Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei

arXiv:2601.05004v2 Announce Type: replace Abstract: Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to iden

Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models

arXiv:2605.25889v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed on real robots, where each predicted action is executed and each failure carries a safet

Causal methods for LLM development and evaluation

arXiv:2605.25998v1 Announce Type: new Abstract: Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and

Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces

arXiv:2605.25352v1 Announce Type: cross Abstract: Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can ac

Characterizing Linear Alignment Across Language Models

arXiv:2603.18908v4 Announce Type: replace Abstract: Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities

Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems

arXiv:2605.25290v1 Announce Type: cross Abstract: Online experiments in ads, recommendation, and member-experience systems are often planned before the dominant interference mechanism is known. A trea

Clustering as Reasoning: A k-Means Interpretation of Chain-of-Thought Graph Learning

arXiv:2605.24867v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TA

CODESKILL: Learning Self-Evolving Skills for Coding Agents

arXiv:2605.25430v1 Announce Type: new Abstract: Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled in

ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation

arXiv:2605.25553v1 Announce Type: cross Abstract: Category-level object pose estimation aims to predict the pose and size of arbitrary objects in specific categories. Existing methods struggle with th

safetyarxiv-cs-ro

Concept Drift Adaptation Using Self-Supervised and Reinforcement Learning In Android Malware Detection

arXiv:2605.24294v1 Announce Type: cross Abstract: Android malware detectors often degrade after deployment because of concept drift, while full retraining at each maintenance step is costly. We propos

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language mode

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents

arXiv:2605.22634v2 Announce Type: replace-cross Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings

corruption

corruption Elon Musk has used Trump’s war in Iran to quintuple the amount he’s charging the Pentagon for SpaceX services. https://www.thedailybeast.com/elon-musks-spacex-uses-trumps-war-to-squeeze-mor

safetygary-marcus--x

Counterfactually Safe Reinforcement Learning

arXiv:2605.25114v1 Announce Type: cross Abstract: Reinforcement learning algorithms are generally designed to maximize the expected return across a population. However, a policy that is optimal on ave

Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning

arXiv:2605.25977v1 Announce Type: cross Abstract: This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this pa

CROCS: A Two-Stage Clustering Framework for Behaviour-Centric Consumer Segmentation with Smart Meter Data

arXiv:2601.10494v2 Announce Type: replace-cross Abstract: With grid operators confronting rising uncertainty from renewable integration and a broader push toward electrification, Demand-Side Managemen

CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents

arXiv:2605.25511v1 Announce Type: new Abstract: Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning ca

Cultivating Machine Intelligence: The OMEGA Shift from Top-Down Optimization to Autopoietic Cognitive Ecologies

arXiv:2605.25062v1 Announce Type: cross Abstract: The dominant artificial intelligence paradigm trains neural architectures via gradient descent against proxy objectives and reinforcement learning fro

CyBOKClaw: Human-in-the-Loop CyBOK Mapping for Cybersecurity Curriculum

arXiv:2605.24663v1 Announce Type: cross Abstract: This paper presents CyBOKClaw, an interpretable human-in-the-loop retrieval framework for mapping cybersecurity keywords or phrases (KWoPs) to the Cyb

D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation

arXiv:2605.25022v1 Announce Type: cross Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing stud

Dale meets Langevin: A Multiplicative Denoising Diffusion Model

arXiv:2510.02730v2 Announce Type: replace Abstract: Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed sy

Data-Driven Optimization of Tactile Sensor Configurations for Efficient Dexterous Manipulation

arXiv:2409.20473v3 Announce Type: replace Abstract: Tactile sensing is critical for learning-based dexterous manipulation, yet principled guidelines for sensor placement remain largely absent. While d

safetyarxiv-cs-ro

DBPnet: Damper Characteristics-Based Bayesian Physics-Informed Neural Network for Wheel Load Estimation

arXiv:2605.24860v1 Announce Type: cross Abstract: Advanced driver assistance systems (ADAS) play an important role in modern automotive intelligence, significantly enhancing vehicle safety and stabili

DeepEN: A Deep Reinforcement Learning Framework for Personalized Enteral Nutrition in Critical Care

arXiv:2510.08350v3 Announce Type: replace-cross Abstract: Objective: Enteral nutrition (EN) delivery in the ICU remains suboptimal due to limited personalization and uncertainty regarding appropriate

DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading

arXiv:2605.25527v1 Announce Type: new Abstract: This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradien

DeGRe: Dense-supervised Generative Reranking for Recommendation

arXiv:2605.25749v1 Announce Type: cross Abstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lie

Delta Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization

arXiv:2510.11296v3 Announce Type: replace-cross Abstract: Recent approaches for vision-language models (VLMs) have shown remarkable success in achieving fast downstream adaptation. When applied to rea

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

arXiv:2605.24001v1 Announce Type: cross Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement l

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs

arXiv:2605.23975v1 Announce Type: new Abstract: Audio large language models (Audio LLMs) exhibit systematic failures in transcribing code-switching speech despite strong multilingual capabilities. Foc

Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards

arXiv:2603.18444v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilit