safety

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

arXiv:2607.25108v1 Announce Type: cross Abstract: Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, pro

Safety

P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning

DGX agent

arXiv:2607.25541v1 Announce Type: new Abstract: Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a misma

safetyarxiv-cs-ro

29 Jul 2026

Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance

arXiv:2607.25507v1 Announce Type: new Abstract: Transformer language models are usually analyzed through vector geometry, yet ordered context and rotary position encoding introduce explicit phase stru

safetyarxiv-cs-cl

Pictura: Perspective-View Self-Play at Scale for Driving

arXiv:2607.26005v1 Announce Type: cross Abstract: Self-play in simulation produces robust driving policies at scale. Demonstrations of such behavior have been made using privileged vectorized observat

pimathbf{R}^2: Reactive Real-time Flow Policies

arXiv:2607.26055v1 Announce Type: cross Abstract: Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones. Such chunks run open

PLATO: Pointer Learner for Agent and Task Openness

arXiv:2607.25082v1 Announce Type: new Abstract: Open agent systems (OASYS) are increasingly prevalent in real-world domains where the sets of agents and tasks change unpredictably over time. Such open

Predictive Control for Driving under Uncertain Road Geometry Estimated from Onboard Vision

arXiv:2508.02494v2 Announce Type: replace-cross Abstract: Autonomous vehicles driving on unknown roads must estimate the road geometry from onboard sensors and follow the resulting reference while res

Quotient Dynamics, Effective Curvature, and Implicit Bias in Positive Quadratic Networks

arXiv:2607.25624v1 Announce Type: new Abstract: Positive quadratic networks admit the low-rank representation f_U(x)=x^top UU^top x, where Uinmathbb{R}^{dtimes r} is identifiable only up to right orth

Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders

arXiv:2607.24869v1 Announce Type: cross Abstract: Large language models (LLMs) used as listwise rerankers in recommendation systems suffer from position bias when serializing candidate sets into promp

safetyarxiv-cs-cl

Rashomon Alignment

arXiv:2607.25680v1 Announce Type: cross Abstract: We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are dist

Reactive 3D Motion Planning for a Franka Arm via Star-World Workspace Reshaping

arXiv:2607.25138v1 Announce Type: new Abstract: Safety inflation can cause nearby obstacles to overlap, violating the disjoint-obstacle assumptions used by many modulation-based reactive planners. We

Real-Time Driver Safety Scoring Through Inverse Crash Probability Modeling

arXiv:2603.14841v3 Announce Type: replace-cross Abstract: Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer l

Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding

arXiv:2607.24794v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate superior generalization in fundamental video tasks, restricted context windows limit their lo

Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture

arXiv:2607.24817v1 Announce Type: cross Abstract: Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can b

RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning

arXiv:2607.18060v2 Announce Type: replace Abstract: Long-horizon robotic tasks require diverse capabilities that no single policy can reliably provide. Heterogeneous policies offer complementary stren

S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information

arXiv:2607.26047v1 Announce Type: new Abstract: Acoustic information provides rich cues about object location, material properties, and changes caused by contact or motion. This paper introduces a new

Safety-Aware Cascaded Inference for Crop Damage Assessment with Controlled Error Trade-offs

arXiv:2607.25468v1 Announce Type: new Abstract: In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer wh

safetyarxiv-cs-cv

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

arXiv:2607.24850v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning h

Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller

arXiv:2607.25728v1 Announce Type: cross Abstract: This paper presents a cooperative indoor UAV guidance framework that combines a shared voxel-map world model with a multi-agent Soft Actor-Critic (MAS

SONG: A Photorealistic 3D Gaussian Simulation Platform for Benchmarking Social Navigation

arXiv:2607.25219v1 Announce Type: new Abstract: Social navigation has progressed from simplified 2D environments toward a more general vision-based setting, in which a robot needs to achieve socially

Spectral Truncation in Synthetic Control

arXiv:2607.25074v1 Announce Type: cross Abstract: Synthetic control (SC) matches a treated unit's pre-treatment trajectory to a weighted combination of donor units. We study Spectral SC, which instead

Structure-aware Relative Policy Optimization for Ranking

arXiv:2607.25268v1 Announce Type: cross Abstract: Ranking is a fundamental component of modern information access systems. Reinforcement learning (RL) provides a flexible framework for directly optimi

The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play

arXiv:2607.25425v1 Announce Type: new Abstract: Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web explo

The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem

arXiv:2604.14990v2 Announce Type: replace Abstract: The prospect of Artificial General Intelligence (AGI) is increasingly driving institutional decisions, and alignment of AGI is a hard problem. The c

The problem: agent workflows alternate between GPU-heavy reasoning and GPU-idle waiting on tools. Run hundreds concurrently and their KV cac…

The problem: agent workflows alternate between GPU-heavy reasoning and GPU-idle waiting on tools. Run hundreds concurrently and their KV caches fight for memory. Engines evict on a dumb LRU policy, ev

safetytogether-ai--x

The Scaling Properties of Implicit Deductive Reasoning in Transformers

arXiv:2605.04330v2 Announce Type: replace Abstract: We investigate the scaling properties of implicit deductive reasoning over Horn clauses in depth-bounded Transformers. By systematically decorrelati

Time-Frequency Consistency Learning for Robust Speech Deepfake Detection

arXiv:2607.17761v2 Announce Type: replace-cross Abstract: Recently, speech deepfake detection (SDD) has achieved significant progress. However, its robustness evaluation remains largely confined to co

Tri-Manual Visuomotor Imitation Learning of Robot Policies

arXiv:2607.25731v1 Announce Type: new Abstract: Bimanual teleoperation provides an effective way to collect robot demonstrations, but it assumes that the operator and robot have matching numbers of si

Tripody: An Overconstrained 3-SPR-like Parallel Robot for High-Reach Construction Tasks

arXiv:2607.25781v1 Announce Type: new Abstract: Many ceiling construction tasks still rely on heavy serial manipulators that are difficult to deploy in cluttered interiors, motivating lightweight, fie

Unlocking Spatial Grounding in Large Audio-Visual Retrieval models

arXiv:2607.24786v1 Announce Type: cross Abstract: Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The ta

Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization

arXiv:2607.25785v1 Announce Type: cross Abstract: We study stochastic composite nonconvex optimization over a compact convex set when gradient samples arrive along a single trajectory of a fixed ergod

Vector-Valued Distributional Reinforcement Learning Policy Evaluation: A Hilbert Space Embedding Approach

arXiv:2601.18952v2 Announce Type: replace Abstract: We propose an (offline) multi-dimensional distributional reinforcement learning framework (KE-DRL) that leverages Hilbert space mappings to estimate

VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening

arXiv:2607.26042v1 Announce Type: new Abstract: We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing devi

safetyarxiv-cs-cv

We ran a large-scale distillation attack on the Kimi K3 technical report by reading it in parallel at the Hugging Face Journal Club :) https…

We ran a large-scale distillation attack on the Kimi K3 technical report by reading it in parallel at the Hugging Face Journal Club :) https://youtu.be/MW8-kqd2SD8?si=jSKDogcUWbJ8N2k7 Our main takeawa

safetyclem-delangue--x

We’re running out of reasons to ignore AI safety

Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. It put the systems in a sandboxed environment without an internet

safetythe-verge-ai

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops

arXiv:2607.25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation

When Does Legacy Data Start to Help? Emergent Transfer in Cross-Configuration Robot Learning

arXiv:2607.25593v1 Announce Type: new Abstract: Robotic hardware evolves over time, but demonstration data is often tied to a specific sensor and actuator configuration. This raises a practical and un

When Shortest Isn't Safest: A Design Science Approach to Senior-Friendly Pedestrian Routing

arXiv:2607.24795v1 Announce Type: new Abstract: Older adults' independent mobility enables out-of-home participation, well-being and health, yet pedestrian navigation systems still optimize primarily

When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval

arXiv:2607.24800v1 Announce Type: cross Abstract: Adaptive retrieval promises to make knowledge-graph question answering more robust by letting a controller search, inspect neighborhoods, revise actio

Where Steering Signals Come From: Activation Source Selection in Activation Steering

arXiv:2607.25270v1 Announce Type: cross Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steeri

Why Public Service AI Governance Frameworks Risk Failing in the Age of General-Purpose AI: Lessons from Policing

arXiv:2607.25648v1 Announce Type: cross Abstract: Public services face growing pressure to adopt artificial intelligence (AI) to close the gap between rising demand and falling resources. That pressur

A Computational Ethical Framework for Financial Digital Phenotyping for Mental Health

arXiv:2607.24275v1 Announce Type: cross Abstract: Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory r

A Coulomb Particle Model for Learning Kernel Attention in Transformers

arXiv:2607.23869v1 Announce Type: cross Abstract: Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution.

A Cyclic Adaptation-Generalization Framework with Uncertainty-Guided Self-Paced Learning for Long-Term Brain-Machine Interfaces

arXiv:2607.24031v1 Announce Type: new Abstract: Brain-Machine Interfaces (BMIs), which link the brain to external devices, hold great potential in rehabilitation, human performance augmentation, and h

A Multi-stage Constrained Optimization Framework for Data-driven Problems

arXiv:2607.23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more t

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

arXiv:2607.24062v1 Announce Type: cross Abstract: Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and infer

Action-Sufficient Goal Representations

arXiv:2601.22496v2 Announce Type: replace-cross Abstract: In offline goal-conditioned reinforcement learning (GCRL), hierarchical approaches decompose long-horizon tasks into high-level subgoal predic

Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis

arXiv:2601.18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interf