Search: “safety”

Scalable Semantic Steering of Embedding Projections

arXiv:2607.03978v1 Announce Type: cross Abstract: Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with ana

Schedulable Job-Level Dependencies for Cause-Effect Chains via Graph Neural Networks

DGX agent

arXiv:2607.02624v1 Announce Type: cross Abstract: Modern automotive software architectures comprise large sets of mixed-criticality functions executing on shared multi-core platforms with strict real-

safetyarxiv-cs-lg

7 Jul 2026

SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies

arXiv:2607.04609v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies that execute fixed-length action chunks can exhibit multimodal bifurcation: a cross-chunk inconsistency in which a

Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies

arXiv:2607.03423v1 Announce Type: cross Abstract: Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails

Self-Improving Diffusion Classifiers with Minority Preference Optimization

arXiv:2607.03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance. However, their effectiveness is strong

Semantic Video Communication via Multi-Scale Convolution and Dynamic Routing for Next-Generation Networks

arXiv:2607.05093v1 Announce Type: new Abstract: The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generati

Sequential Cohort Selection under Uncertainty

arXiv:2508.16386v2 Announce Type: replace Abstract: We study the problem of fair cohort selection under uncertainty, motivated by university admissions where applicant outcomes are only partially obse

Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization

arXiv:2512.15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multi

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

arXiv:2607.04044v1 Announce Type: new Abstract: Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities

Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning

arXiv:2607.04591v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation by integrating visual perception, language understan

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

arXiv:2510.15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security f

SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction

arXiv:2607.04119v1 Announce Type: cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. H

Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity

arXiv:2607.04739v1 Announce Type: new Abstract: Sampling action chunks via generative models has become a widely adopted methodology for robotic learning from demonstration. However, existing methods

SpecGradFilter: A Spectral Gradient Filtering Framework for Taming Federated Heterogeneity

arXiv:2607.04189v1 Announce Type: new Abstract: Federated Learning (FL) is fundamentally challenged by statistical heterogeneity, where non-identically distributed (non-IID) data induces client drift

Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval

arXiv:2601.22652v2 Announce Type: replace-cross Abstract: Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, a

StageCraft: Execution Aware Mitigation of Distractor and Obstruction Failures in VLA Models

arXiv:2603.20659v2 Announce Type: replace Abstract: Large scale pre-training on text and image data along with diverse robot demonstrations has helped Vision Language Action models (VLAs) to generaliz

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training

arXiv:2607.04963v1 Announce Type: new Abstract: Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed r

States are asking for a $1.4 trillion fine of Meta over addicting kids. Basically they are saying Facebook's business model is a result of c…

States are asking for a $1.4 trillion fine of Meta over addicting kids. Basically they are saying Facebook's business model is a result of crime, and all of Mark Zuckerberg's property should be forfei

safetygary-marcus--x

Model Releases

SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments

model-releasesarxiv-cs-cv

arXiv:2607.05264v1 Announce Type: new Abstract: Existing video benchmarks evaluate action recognition on consumer videos, egocentric recordings, or simulated industrial environments. They do not test

Strategic Buying Agents

arXiv:2607.04708v1 Announce Type: cross Abstract: Agentic AI is shifting online shopping from search toward delegated purchasing, where autonomous buying agents monitor markets and decide when to buy

STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data

arXiv:2607.03501v1 Announce Type: cross Abstract: Copernicus, the European Union's Earth observation program, produces petabytes of Earth observation and climate data, offering immense potential for r

Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection

arXiv:2203.01687v3 Announce Type: replace Abstract: Medical landmark detection usually requires accurate expert annotations, which are laborious and difficult to scale across anatomical regions. In th

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

arXiv:2510.08048v4 Announce Type: replace-cross Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, wh

Teaming Up with AI: Coordination and Cooperation

arXiv:2607.03181v1 Announce Type: cross Abstract: Successful diffusion of AI in the workforce hinges on the economic value that AI brings to human endeavors. Bringing AI into the workforce is more tha

Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability

arXiv:2607.04061v1 Announce Type: cross Abstract: Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge. While LLMs are trained to write lik

Tensor-Train Joint Modeling for Few-Step Discrete Diffusion

arXiv:2607.03788v1 Announce Type: new Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for sequential discrete data, yet its full potential o

Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning

arXiv:2607.03143v1 Announce Type: cross Abstract: Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making sim

Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation

arXiv:2606.22726v2 Announce Type: replace Abstract: Choreographic motion generation poses unique challenges for AI, demanding precise semantic control over complex, temporally structured, and expressi

The agent creates, we validate: A Lightweight Framework for Agentic Artifact Generation

arXiv:2607.02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.g. database queries, threat framework mappings, entity schemas - is relatively straight

The AI boom is just not sustainable; Apollo’s Torsten Slok joins the chorus.

The AI boom is just not sustainable; Apollo’s Torsten Slok joins the chorus. Torsten Slok argues that the AI boom can only be seen in the hyperscalers and semiconductor companies and that this is caus

safetygary-marcus--x

The Foreign Policy AI Evaluation Gap

arXiv:2607.02955v1 Announce Type: cross Abstract: We argue that AI systems used in conducting foreign policy tasks - broadly enacting 'statecraft' - should be a priority test case for technical AI gov

The ‘Ghost’ in the Database: Recovering Active ADFS Signing Keys via Machine DPAPI

Written by: Shebin Mathew Introduction The 'Golden SAML' technique, first described by CyberArk researchers in 2017, and further detailed by Mandiant researchers in 2021, remains one of the most effec

safetygoogle-cloud-ai

The Three Regimes of Offline-to-Online Reinforcement Learning

arXiv:2510.01460v4 Announce Type: replace-cross Abstract: Offline-to-online reinforcement learning (RL) has emerged as a practical paradigm that leverages offline datasets for pretraining and online i

TokAN: Accent Normalization Using Self-Supervised Speech Tokens

arXiv:2607.03928v1 Announce Type: cross Abstract: Accent normalization (AN) seeks to convert non-native (L2) accented speech into standard (L1) speech while preserving speaker identity. The current te

Towards Data-Driven Metrics for Social Robot Navigation Benchmarking

arXiv:2509.01251v3 Announce Type: replace Abstract: This paper presents a joint effort towards the development of a data-driven Social Robot Navigation metric to facilitate benchmarking and policy opt

Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery

arXiv:2607.04745v1 Announce Type: cross Abstract: Modern thermal visual place recognition (TIR-VPR) frontends based on foundation models achieve remarkable closed-set retrieval but suffer from an over

Transformer-Based Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions

arXiv:2511.13103v2 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First,

Trust Region Policy Distillation

arXiv:2607.04751v1 Announce Type: cross Abstract: Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transfo

Turning Off-Policy Tokens On-Policy: A Plug-in Approach for Improving LLM Alignment

arXiv:2607.04728v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of 'rollout then update', which inevitably res

Two Black Boxes, One Solver: Encoder Probing and Decoder Attribution for Neural Multi-Attribute VRP under Hard-Mask and Recourse Decoders

arXiv:2607.04487v1 Announce Type: cross Abstract: Neural autoregressive solvers for the Multi-Attribute Vehicle Routing Problem (MAVRP) reach competitive cost but offer no per-step justification, a pr

UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning

arXiv:2607.04425v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models and agent systems have driven GUI agents from single-platform task execution toward cross-platform int

Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guarantees

arXiv:2607.04430v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in question answering (QA) systems, yet they may generate hallucinated or misaligned responses wi

safetyarxiv-cs-cl

Virtual Category-Guided Continual Generalized Category Discovery

arXiv:2607.04984v1 Announce Type: new Abstract: Continual Generalized Category Discovery (C-GCD) aims to incrementally identify novel categories from sequential unlabeled data while preserving recogni

Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics

arXiv:2607.03589v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal seq

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models

arXiv:2508.08521v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to

VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models

arXiv:2607.04517v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, h

Weak-to-Strong Generalization via Direct On-Policy Distillation

arXiv:2607.05394v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on ev

Who is entitled to benefit from major advances in technology—and on what basis? This new paper with @Dr_Atoosa argues that the benefits of t…

Who is entitled to benefit from major advances in technology—and on what basis? This new paper with @Dr_Atoosa argues that the benefits of technology—including AI—belong to the world in the sense that

safetygary-marcus--x