Search: “safety”

EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning

arXiv:2511.18242v3 Announce Type: replace Abstract: Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal la

ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies

DGX agent

arXiv:2606.31132v1 Announce Type: new Abstract: Generative control policies (GCPs), such as diffusion policies and flow-based vision-language-action models, enable test-time scaling in robot control.

safetyarxiv-cs-ro

1 Jul 2026

End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions

arXiv:2603.23461v2 Announce Type: replace Abstract: We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying linear Bellman completeness -

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

arXiv:2606.31982v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction prov

Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment

arXiv:2606.31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, l

Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision

arXiv:2606.31800v1 Announce Type: new Abstract: Despite recent progress, the reasoning capabilities of large multimodal language models (MLLMs) remain fundamentally constrained by static supervision,

Explainable Artificial Intelligence For The Detection and Characterisation of Stage B Heart Failure

arXiv:2606.30665v1 Announce Type: cross Abstract: Stage B heart failure is characterized by asymptomatic structural or functional cardiac abnormalities. Identifying individuals at this stage is clinic

ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

arXiv:2606.31201v1 Announce Type: new Abstract: Multi-objective masked image modeling (MIM) combines complementary learning signals (token distillation, CLS alignment, and pixel reconstruction) but ex

FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion

arXiv:2606.31691v1 Announce Type: new Abstract: Scalable reinforcement learning has popularized high-throughput sampling architectures, which significantly compresses the training time for off-policy

safetyarxiv-cs-ro

Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction

arXiv:2603.09930v2 Announce Type: replace Abstract: Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

arXiv:2603.12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning f

From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems

arXiv:2606.31589v1 Announce Type: cross Abstract: Organisations designing, developing, and deploying machine learning systems (MLS) need to be able to check that these systems are trustworthy, and com

From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue

arXiv:2606.30973v1 Announce Type: new Abstract: Frictive Policy Optimization (FPO; Pustejovsky et al., 2025) treats friction in collaborative dialogue -- misalignment, misunderstanding, repair -- as a

safetyarxiv-cs-cl

G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation

arXiv:2601.03510v3 Announce Type: replace Abstract: Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance eviden

GEAR: Guided End-to-End AutoRegression for Image Synthesis

arXiv:2606.32039v1 Announce Type: new Abstract: Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator i

GR2 Technical Report

arXiv:2606.31984v1 Announce Type: cross Abstract: Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

arXiv:2603.26266v3 Announce Type: replace Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction. However, due to i

HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)

arXiv:2606.31325v1 Announce Type: new Abstract: We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the

How Human Feedback Shapes AI-generated Community Notes

arXiv:2606.30905v1 Announce Type: cross Abstract: Community Notes, a bridging-based crowd-sourced fact-checking system, has emerged as a new mechanism for moderating misleading information on social m

Incentive Aware AI Regulations: A Credal Characterisation

arXiv:2603.05175v2 Announce Type: replace Abstract: The rapid proliferation of AI applications has intensified debate on effective regulation of these black-box services. Effective regulation must bal

InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving

arXiv:2606.31109v1 Announce Type: new Abstract: Generating realistic, controllable, and temporally coherent urban environments is a critical yet unresolved challenge in the autonomous driving communit

IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing

arXiv:2606.13368v2 Announce Type: replace Abstract: Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creat

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

arXiv:2606.12634v2 Announce Type: replace-cross Abstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, A

LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior

arXiv:2603.25399v2 Announce Type: replace Abstract: We introduce extbf{LaMP}, a dual-expert Vision-Language-Action framework that embeds dense 3D scene flow as a latent motion prior for robotic manipu

Language-Assisted Super-Resolution from Real-World Low-Resolution Patches

arXiv:2606.31363v1 Announce Type: new Abstract: Single image super-resolution aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Training SR models typically requires pai

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

arXiv:2509.12046v2 Announce Type: replace-cross Abstract: Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned gen

Learning Dexterous Grasping from Sparse Taxonomy Guidance

arXiv:2604.04138v2 Announce Type: replace-cross Abstract: Dexterous manipulation requires planning a grasp configuration suited to the object and task, which is then executed through coordinated multi

Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation

arXiv:2606.31609v1 Announce Type: cross Abstract: Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements mak

Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection

arXiv:2606.30951v1 Announce Type: cross Abstract: Micro-ultrasound (muUS) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspici

Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

arXiv:2606.31411v1 Announce Type: new Abstract: Rapid advancements in generative speech technology have compromised the reliability of voice biometrics. While current spoofing detectors excel when ass

safetyarxiv-cs-cl

LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach

arXiv:2510.10895v2 Announce Type: replace Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-b

Locker-based Truck-Drone Routing with Integrated Considerations of Pickups, Deliveries, and No-Fly Zones

arXiv:2606.30680v1 Announce Type: cross Abstract: Truck-drone delivery is an emerging last-mile logistics mode combining the long-haul capacity of trucks with the flexible service capability of drones

Long-term Traffic Simulation via Structured Autoregressive Modeling

arXiv:2606.31209v1 Announce Type: new Abstract: Interactive traffic simulation is a vital world model for autonomous driving. A central challenge in long-horizon simulation is modeling sustained multi

MNAR-k-means: A k-means Clustering for Data Missing Not at Random with Magnitude-Decaying Probability

arXiv:2606.31253v1 Announce Type: cross Abstract: The classical k-means clustering, based on distances computed from all data features, cannot be directly applied to incomplete data with missing value

Multiple Testing of Linear Forms for Noisy Matrix Completion

arXiv:2312.00305v3 Announce Type: replace-cross Abstract: Many important tasks of large-scale recommender systems can be naturally cast as testing multiple linear forms for noisy matrix completion. Th

Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force

arXiv:2606.30988v1 Announce Type: new Abstract: Robot manipulation often relies on sensory feedback beyond vision, particularly in contact-rich settings where force, tactile, or audio signals reveal i

safetyarxiv-cs-ro

No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation

arXiv:2606.30937v1 Announce Type: new Abstract: LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraini

No country wins a race to superintelligence. An AI vastly smarter than us wouldn't be a weapon we control, we'd be handing control over to i…

No country wins a race to superintelligence. An AI vastly smarter than us wouldn't be a weapon we control, we'd be handing control over to it. ControlAI's US Director Connor Leahy (@NPCollapse) on why

safetyconnor-leahy--x

Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction

arXiv:2606.31025v1 Announce Type: new Abstract: Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. Howeve

PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates

arXiv:2512.06845v2 Announce Type: replace Abstract: Deploying video anomaly detection (VAD) in the real world is often constrained by the scarcity, privacy, and cost of collecting real abnormal footag

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

arXiv:2601.14171v2 Announce Type: replace Abstract: Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer inten

Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace

arXiv:2606.30932v1 Announce Type: new Abstract: Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's expe

PiLoT v2: Pixel-to-Orthogonal Map Alignment for Free-view UAV Geo-localization

arXiv:2606.31098v1 Announce Type: new Abstract: Real-time, drift-free UAV geo-localization is essential for autonomous missions in GNSS-denied environments. The pioneering system, PiLoT, achieves high

Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions

arXiv:2606.31769v1 Announce Type: new Abstract: We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guara

PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines

arXiv:2606.32004v1 Announce Type: new Abstract: Policy-grounded document review requires determining whether a target document complies with organization-specific policies, guidelines, or playbooks. W

Model Releases

Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows

model-releasesarxiv-cs-lg

arXiv:2603.21210v3 Announce Type: replace Abstract: Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but th

Prompting Robot Teams with Natural Language

arXiv:2509.24575v2 Announce Type: replace-cross Abstract: This paper presents a framework to prompt multi-robot teams with high-level tasks using natural language expressions. Our objective is to use

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

arXiv:2606.32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-onl