safety

3SPO: State-Score-Supervised Policy Optimization for LLM Agents

arXiv:2606.09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performan

A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications

DGX agent

arXiv:2410.15595v4 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct P

safetyarxiv-cs-ai

10 Jun 2026

A fine-grained attention and geometric correspondence model for musculoskeletal risk classification in athletes using multimodal visual and skeletal features

arXiv:2509.05913v3 Announce Type: replace Abstract: Musculoskeletal disorders pose significant risks to athletes, and early risk assessment is essential for prevention. However, most existing methods

A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation

arXiv:2606.10366v1 Announce Type: cross Abstract: Simulation has become an essential tool for evaluating and improving vision-language-action (VLA) policies, offering scalable, reproducible, and contr

A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis

arXiv:2606.10500v1 Announce Type: new Abstract: In equipment operation, the implementation of fault diagnosis is essential to ensure the continuity and safety of production equipment, improve operatio

A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly Detection via Semantic Alignment and Optimal Transport

arXiv:2606.10216v1 Announce Type: cross Abstract: Advanced Persistent Threats (APTs) are stealthy, multi-stage cyberattacks whose detection is difficult due to scarce labeled traces, severe class imba

A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis

arXiv:2606.10412v1 Announce Type: new Abstract: The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple

Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models

arXiv:2606.10495v1 Announce Type: new Abstract: Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretraine

safetyarxiv-cs-ro

Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study

arXiv:2601.16700v2 Announce Type: replace-cross Abstract: Generative artificial intelligence (GenAI) tools have seen rapid adoption among software developers. While adoption rates in the industry are

AI oligarchs are trying to buy elections (again)

AI oligarchs are trying to buy elections (again) AI titans are spending 1.3M to shape Utah primaries. Defending Our Values, run by Chris Stewart, spent 880K to support Rep. Celeste Maloy. DOV operates

Alignment Defends LLMs from Property Inference Attacks

arXiv:2606.10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work h

Alongside it, Anthropic is releasing a proposal for how governments can address the risks posed by frontier AI and a policy framework for jo…

Alongside it, Anthropic is releasing a proposal for how governments can address the risks posed by frontier AI and a policy framework for job displacement, for which we intend to provide substantial f

safetydario-amodei--x

An essay on policy responses to AI's exponential progress across regulation and public safety, macroeconomics and taxes, science, civil liberties, geopolitics (Dario Amodei)

Dario Amodei: An essay on policy responses to AI's exponential progress across regulation and public safety, macroeconomics and taxes, science, civil liberties, geopolitics — In one of the side plots

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

arXiv:2606.09843v1 Announce Type: cross Abstract: Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior. Whether

and see for deeper analysis https://open.substack.com/pub/garymarcus/p/breaking-news-and-how-the-end-might?r=8tdk6&utm_medium=ios

Gary Marcus discusses breaking news and potential existential risks or significant developments related to AI systems, likely examining how current AI capabilities and limitations might lead to critic

AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects

arXiv:2606.10988v1 Announce Type: new Abstract: While recent advancements in generative AI have substantially accelerated static 3D model creation workflows, the synthesis of category-agnostic 3D anim

Anthropic and OpenAI did not call for a pause. Read the wording: 'good for the world to have the option', 'possible' to slow down 'when need…

Anthropic and OpenAI did not call for a pause. Read the wording: 'good for the world to have the option', 'possible' to slow down 'when needed'. This is how they signal safety to one audience, acceler

safetyconnor-leahy--x

Anthropic has long advocated for transparency requirements for frontier AI, because the risks weren't yet clear enough to regulate precisely…

Anthropic's leadership, through CEO Dario Amodei, has advocated for transparency requirements in frontier AI development as a regulatory approach, arguing that the risks were insufficiently understood

safetydario-amodei--x

Anthropic, if they really believe what they say, should show some leadership:

Anthropic, if they really believe what they say, should show some leadership: 🔔 IF Anthropic is for real about safety, the should pause, for one month, and show leadership. If they won’t pause, even b

Anthropic releases two policy proposals on how governments should address catastrophic risks and manage labor market disruption from advanced AI systems (Anthropic)

Anthropic: Anthropic releases two policy proposals on how governments should address catastrophic risks and manage labor market disruption from advanced AI systems — AI is advancing at exponential spe

Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans

arXiv:2606.10953v1 Announce Type: new Abstract: Furnished floor plans are fundamental to real estate visualization, interior design, and architectural workflows. However, progress in automatic furnitu

are you kidding me

are you kidding me Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I

safetyjeremy-howard--x

ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations

arXiv:2606.11188v1 Announce Type: new Abstract: This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-

As vertically integrated platforms start to dominate they lock out third party access to the most valuable portions of the platform. Of cour…

As vertically integrated platforms start to dominate they lock out third party access to the most valuable portions of the platform. Of course, Anthropic is has the right to implement whatever policy

safetytogether-ai--x

AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents

arXiv:2606.05597v2 Announce Type: replace Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, a

Automated Alignment between Elicitation Interviews and Requirements

arXiv:2510.08622v2 Announce Type: replace Abstract: Software requirements are derived from a variety of elicitation techniques, many of which have a conversational nature, like interviews. However, ev

safetyarxiv-cs-cl

Automated Scoring of Arabic Text Using Large Language Models: A Literature Review

arXiv:2606.09830v1 Announce Type: new Abstract: In modern educational systems, Automatic Text Scoring (ATS) plays a central role by enabling scalable and consistent evaluation of learner responses wit

safetyarxiv-cs-cl

Automatic Labelling for Low-Light Pedestrian Detection

arXiv:2507.02513v4 Announce Type: replace Abstract: Pedestrian detection in RGB images is a key task in pedestrian safety, as the most common sensor in autonomous vehicles and advanced driver assistan

Banger post from @testdrivenzen There is no good outcome for the world unless countries coordinate to stop ASI development.

Banger post from @testdrivenzen There is no good outcome for the world unless countries coordinate to stop ASI development. Any plan for surviving superintelligent AI that doesn't go through strong in

safetyconnor-leahy--x

Baseline-Free Policy Optimization for Neural Combinatorial Optimization

arXiv:2606.10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems. The standard training algorithm, REINFORCE with a ro

Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets

arXiv:2606.10979v1 Announce Type: new Abstract: Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operationa

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

arXiv:2606.10968v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechan

🚨Breaking news that could be huge, and enormously bad for GenAI, if other countries make similar decisions. https://the-decoder.com/landmar…

🚨Breaking news that could be huge, and enormously bad for GenAI, if other countries make similar decisions. https://the-decoder.com/landmark-german-ruling-declares-googles-ai-overviews-are-googles-own

BREAKING! This may well be the beginning of the end.

BREAKING! This may well be the beginning of the end. 🚨BREAKING: SoftBank tried to borrow 6 billion against its 13% OpenAI stock… to keep funding OpenAI Banks said NO They don’t believe OpenAI is worth

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization

arXiv:2606.09909v1 Announce Type: cross Abstract: With the growing concerns over copyright infringement in diffusion-based customization, adversarial attacks have emerged as a prominent defense strate

CameraMatics, which uses AI to help fleet operators improve safety, reduce operational risk, and lower carbon emissions, raised €49M (Joe Brennan/The Irish Times)

Joe Brennan / The Irish Times: CameraMatics, which uses AI to help fleet operators improve safety, reduce operational risk, and lower carbon emissions, raised €49M — Tech focuses on accident preventio

Canada introduces the Safe Social Media Act, a bill that would ban social media for children under 16 and establish safety standards for AI chatbots (Maria Cheng/Reuters)

Maria Cheng / Reuters: Canada introduces the Safe Social Media Act, a bill that would ban social media for children under 16 and establish safety standards for AI chatbots — The Canadian government in

Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting

arXiv:2606.10607v1 Announce Type: cross Abstract: Causal discovery aims to uncover causal structures from observational data, which is crucial for real-world decision-making. However, different causal

Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data

arXiv:2606.10789v1 Announce Type: new Abstract: Zero-shot learning (ZSL) for inertial measurement unit (IMU)-based human activity recognition (HAR) faces a central challenge: bridging the gap between

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs

arXiv:2411.02817v2 Announce Type: replace-cross Abstract: Generative models guided by text prompts are widely evaluated for fidelity and prompt alignment, yet their ability to produce outputs remains

Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation

arXiv:2606.09923v1 Announce Type: cross Abstract: Neural operators such as the Fourier Neural Operator (FNO) have emerged as powerful surrogates for solving partial differential equations (PDEs), achi

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

arXiv:2601.19210v2 Announce Type: replace Abstract: Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial exampl

Convergence of Monte Carlo Optimistic Policy Iteration: Beyond Uniform State-Action Updates

arXiv:2606.10580v1 Announce Type: cross Abstract: The asymptotic behaviour of Monte Carlo optimistic policy iteration (MC-O-PI) is a long-standing open question. When the model of the environment is u

Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm

arXiv:2606.10504v1 Announce Type: new Abstract: Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student m

Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising

arXiv:2606.10187v1 Announce Type: cross Abstract: We develop a decision-calibrated conformal framework for pacing decisions in streaming advertising. Pacing depends on uncertain future inventory, dema

Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation

arXiv:2606.10475v1 Announce Type: cross Abstract: Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks, but they are currently optimized in a w

DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment

arXiv:2606.10010v1 Announce Type: cross Abstract: Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion score

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

arXiv:2606.10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting po