Search: “safety”

From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution

arXiv:2607.06269v1 Announce Type: new Abstract: Current large language models (LLMs) are fundamentally stateless: their behavior is fully determined by input at inference time, and any higher-order co

Safety

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

DGX agent

arXiv:2607.06080v1 Announce Type: cross Abstract: Putnam's Social Capital Theory is a foundational framework for collective action and community prosperity. However, traditional empirical methods face

safetyarxiv-cs-ai

8 Jul 2026

From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space

arXiv:2607.05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfa

From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications

arXiv:2308.16041v2 Announce Type: replace Abstract: Talking head generation has progressed rapidly from landmark- and GAN-based facial animation to diffusion models, neural rendering, 3D-aware avatars

GaussFusion: Towards Multimodal 3D Gaussian Pretraining

arXiv:2607.05906v1 Announce Type: new Abstract: 3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D represent

GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation

arXiv:2607.05869v1 Announce Type: cross Abstract: Robust robotic grasping of novel objects requires datasets that simultaneously provide photorealistic RGB-D observations, physically validated grasp q

Heckman-Corrected Epistemic Uncertainty: Selection on Unobservables Defeats Importance Weighting

arXiv:2607.05806v1 Announce Type: new Abstract: Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes on

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

arXiv:2607.06223v1 Announce Type: new Abstract: Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent mus

Intercepting an Agile Target with Net-Carrying Drones using Competitive Multi-Agent Reinforcement Learning

arXiv:2607.05939v1 Announce Type: new Abstract: This article presents a solution to intercept an agile drone by a team of agile drone carrying catching nets. We formulate the problem as a competitive

Is Domain Adaptation Always Helpful? A Frozen-Backbone Study of Cross-Domain Sentiment Transfer

arXiv:2607.05937v1 Announce Type: new Abstract: Sentiment analysis with frozen pre-trained language model (PLM) backbones has become a common paradigm, yet the practical benefit of explicit domain ada

safetyarxiv-cs-cl

IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction

arXiv:2606.18181v2 Announce Type: replace-cross Abstract: Illegal, unreported, and unregulated fishing (IUU) traditionally refers to fishing activities that violate applicable laws or occur in areas t

K-ABENA: K-Adaptive Backpropagation with Error-based N-exclusion Algorithm : (Compensated Loss-Based Sample Exclusion with Unbiased Gradient Estimation)

arXiv:2607.05903v1 Announce Type: cross Abstract: We present K-ABENA (K-Adaptive Backpropagation with Error-based N-exclusion Algorithm), a selective gradient computation framework that reduces per-it

KAT-Coder-V2.5 Technical Report

arXiv:2607.05471v1 Announce Type: cross Abstract: We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-tur

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

arXiv:2512.23236v4 Announce Type: replace-cross Abstract: Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key syst

KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning

arXiv:2607.06019v1 Announce Type: new Abstract: Non-invasive prediction of Gleason Grade Group (GGG) in prostate cancer using multiparametric MRI (mpMRI) is clinically vital for reducing unnecessary b

LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation

arXiv:2607.06323v1 Announce Type: new Abstract: Real-world learning for dexterous hands remains brittle because high-dimensional hand actions amplify imitation errors and make reinforcement-learning e

„Language models model language“ is going to be my quote of the week … maybe I print a T shirt for the next conference.

„Language models model language“ is going to be my quote of the week … maybe I print a T shirt for the next conference. super interesting - and a reminder that language models model language and not i

safetygary-marcus--x

Learning to Throw Objects Safely in Multi-Obstacle Environments

arXiv:2607.06388v1 Announce Type: cross Abstract: Robotic throwing enables fast and efficient object placement beyond the robot's immediate workspace, but reliable throwing in cluttered environments r

Learning When to Automate: Queue Control in Human-AI Service Systems

arXiv:2607.06017v1 Announce Type: new Abstract: We study a human-AI service system in which tasks arrive sequentially and are processed through a two-stage architecture: an automated chatbot followed,

Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents

arXiv:2606.22504v1 Announce Type: cross Abstract: Coding agents often receive broad tool access for an entire task, even when a resource is needed only for one subgoal. We call this gap lingering auth

MAC-XA: Multi-view Anatomy-Correspondence Fusion for Coronary Stenosis Reporting from X-ray Angiography

arXiv:2607.06268v1 Announce Type: new Abstract: Multi-view reasoning in coronary X-ray angiography is inherently a cross-projection geometric problem, yet automated report generation in this setting r

MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback

arXiv:2503.13212v3 Announce Type: replace Abstract: Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely ado

MASCA: LLM based-Multi Agents System for Credit Assessment

arXiv:2507.22758v2 Announce Type: replace Abstract: Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling

safetyarxiv-cs-cl

// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it's discusses the use of a learned…

// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it's discusses the use of a learned policy for using memory at the right granularity. Most memo

safetydair-ai--x

Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?

arXiv:2603.28553v2 Announce Type: replace-cross Abstract: Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationa

O3N: Omnidirectional Open-Vocabulary Occupancy Prediction

arXiv:2603.12144v2 Announce Type: replace Abstract: Understanding and reconstructing the 3D world through omnidirectional perception is becoming increasingly important for autonomous agents and embodi

OBBSeg: Irregular Lesion Segmentation under Oriented Bounding Box Annotations

arXiv:2607.06007v1 Announce Type: new Abstract: Pixel-level annotation remains a major bottleneck in medical image segmentation, making weak supervision an attractive yet under-constrained alternative

Optimal Transport Q-Learning for Flow Policy Steering and Acceleration

arXiv:2607.06262v1 Announce Type: new Abstract: Diffusion and flow policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajector

Our approach to government and national security partnerships

OpenAI outlines its strategy for collaborating with government agencies and national security institutions, likely covering principles for responsible AI deployment in defense and security contexts. T

safetyopenai

Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?

arXiv:2508.01109v3 Announce Type: replace Abstract: We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturin

PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models

arXiv:2607.05441v1 Announce Type: cross Abstract: Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still str

Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferences

arXiv:2506.03218v2 Announce Type: replace-cross Abstract: The EU has become one of the vanguards in regulating the digital age. A particularly important regulation in the Artificial Intelligence (AI)

Quantifying Retriever-Generator Alignment in RAG with Local Explanations

arXiv:2601.21803v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground their outputs in external documents. However, th

safetyarxiv-cs-cl

Realistic Compound-Lens Defocus Blur Synthesis

arXiv:2607.05837v1 Announce Type: new Abstract: Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learn

Recovering Cloud Microstructures with Cascaded Diffusion Inversion

arXiv:2607.05637v1 Announce Type: new Abstract: High-resolution satellite imagery is critical for observing fine-scale cloud structures that inform weather modification strategies like cloud seeding f

RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures

arXiv:2607.06018v1 Announce Type: new Abstract: Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not r

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

arXiv:2607.06559v1 Announce Type: new Abstract: Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under int

SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

arXiv:2607.05943v1 Announce Type: new Abstract: Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines cons

Securing Amazon Bedrock AgentCore Runtime with AWS WAF

This post shows you two architecture patterns that address this problem. Both use an internet-facing ALB with AWS WAF and route traffic through a VPC Interface Endpoint to AgentCore Runtime. Pattern 1

safetyaws-ml-blog

SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation

arXiv:2603.21046v2 Announce Type: replace-cross Abstract: UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN

Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data

arXiv:2607.06013v1 Announce Type: new Abstract: Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventuall

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

arXiv:2607.05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision

Straight-Path Flow Matching for Incomplete Multi-View Clustering

arXiv:2607.06281v1 Announce Type: new Abstract: Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative appro

Structured-Condensed Prompt Tuning in Vision-Language Models for Fine-grained Image Recognition

arXiv:2607.06185v1 Announce Type: new Abstract: Fine-grained image recognition poses a significant challenge due to the substantial expertise and effort required for manual annotation. Vision-language

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

arXiv:2602.02401v2 Announce Type: replace Abstract: Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vi

The Jagged Global Economy: Frontier AI Unevenly Exposes National Economies

arXiv:2607.05404v1 Announce Type: cross Abstract: Frontier AI's labor-market effects matter to workers, firms, and policymakers, but current evidence generally comes from a handful of high-income econ

To Retain or to Adapt? Generalizing Continual Learning

arXiv:2607.05609v1 Announce Type: cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, of

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

arXiv:2607.05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework fo