safety

CROP: Conservative Reward for Model-based Offline Policy Optimization

arXiv:2310.17245v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are par

Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music

DGX agent

arXiv:2604.10503v1 Announce Type: cross Abstract: Modern audio systems universally employ mel-scale representations derived from 1940s Western psychoacoustic studies, potentially encoding cultural bia

safetyarxiv-cs-ai

14 Apr 2026

Cross-Cultural Value Awareness in Large Vision-Language Models

arXiv:2604.09945v1 Announce Type: cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity t

CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation

arXiv:2604.10918v1 Announce Type: new Abstract: Tables contain rich structured information, yet when stored as images their contents remain 'locked' within pixels. Converting table images into LaTeX c

Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor

arXiv:2501.18490v3 Announce Type: replace-cross Abstract: This article introduces a novel sample-efficient curriculum learning (CL) approach for training an end-to-end reinforcement learning (RL) poli

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

arXiv:2503.11892v3 Announce Type: replace Abstract: Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intri

Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN

arXiv:2604.09682v1 Announce Type: cross Abstract: Autonomous network management in Open Radio Access Networks requires intelligent decision making across conflicting objectives, yet existing LLM based

Deep deterministic policy gradient with symmetric data augmentation for lateral attitude tracking control of a fixed-wing aircraft

arXiv:2407.11077v3 Announce Type: replace-cross Abstract: The symmetry of dynamical systems can be exploited for state-transition prediction and to facilitate control policy optimization. This paper l

DeepFleet: Multi-Agent Foundation Models for Mobile Robots

arXiv:2508.08574v3 Announce Type: replace Abstract: We introduce DeepFleet, a suite of foundation models designed to support coordination and planning for large-scale mobile robot fleets. These models

safetyarxiv-cs-ro

Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model

arXiv:2604.09665v1 Announce Type: cross Abstract: While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted

Demographic and Linguistic Bias Evaluation in Omnimodal Language Models

arXiv:2604.10014v1 Announce Type: cross Abstract: This paper provides a comprehensive evaluation of demographic and linguistic biases in omnimodal language models that process text, images, audio, and

Descriptor-Injected Cross-Modal Learning: A Systematic Exploration of Audio-MIDI Alignment via Spectral and Melodic Features

arXiv:2604.10283v1 Announce Type: cross Abstract: Cross-modal retrieval between audio recordings and symbolic music representations (MIDI) remains challenging because continuous waveforms and discrete

Design Experiments to Compare Multi-armed Bandit Algorithms

arXiv:2603.05919v2 Announce Type: replace Abstract: Online platforms routinely compare multi-armed bandit algorithms, such as UCB and Thompson Sampling, to select the best-performing policy. Unlike st

Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning

arXiv:2604.11206v1 Announce Type: cross Abstract: Digital nudging systems lack architectural guidance for translating behavioral science into software design. While research identifies nudge strategie

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

arXiv:2603.18280v2 Announce Type: replace-cross Abstract: Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the

Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation

arXiv:2604.10170v1 Announce Type: cross Abstract: The growing complexity of visuomotor policies poses significant challenges for deployment with heterogeneous robotic hardware constraints. However, mo

Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate

arXiv:2604.11258v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, pote

safetyarxiv-cs-cl

Dialogue based Interactive Explanations for Safety Decisions in Human Robot Collaboration

arXiv:2604.05896v2 Announce Type: replace Abstract: As robots increasingly operate in shared, safety critical environments, acting safely is no longer sufficient robots must also make their safety dec

safetyarxiv-cs-ro

Differentiable free energy surface: a variational approach to directly observing rare events using generative deep-learning models

arXiv:2604.09769v1 Announce Type: cross Abstract: Rare events are central to the evolution of complex many-body systems, characterized as key transitional configurations on the free energy surface (FE

Diffusion-Based Generative Priors for Efficient Beam Alignment in Directional Networks

arXiv:2604.09653v1 Announce Type: cross Abstract: Beam alignment is a key challenge in directional mmWave and THz systems, where narrow beams require accurate yet low-overhead training. Existing learn

Discrete Flow Maps

arXiv:2604.09784v1 Announce Type: cross Abstract: The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models

DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

arXiv:2510.24574v2 Announce Type: replace-cross Abstract: Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The

Distributionally Robust PAC-Bayesian Control

arXiv:2604.10588v1 Announce Type: new Abstract: We present a distributionally robust PAC-Bayesian framework for certifying the performance of learning-based finite-horizon controllers. While existing

Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations

arXiv:2604.11322v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to to

Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment

arXiv:2603.07462v2 Announce Type: replace Abstract: Determining whether AI systems process information similarly to humans is central to cognitive science and trustworthy AI. While modern AI models ca

DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping

arXiv:2604.03402v2 Announce Type: replace-cross Abstract: Smartphone cameras have gained immense popularity with the adoption of high-resolution and high-dynamic range imaging. As a result, high-perfo

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

arXiv:2603.18806v2 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them wi

Dual-Exposure Imaging with Events

arXiv:2604.10273v1 Announce Type: new Abstract: By combining complementary benefits of short- and long-exposure images, Dual-Exposure Imaging (DEI) enhances image quality in low-light scenarios. Howev

Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

arXiv:2604.10567v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel

EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning

arXiv:2604.09815v1 Announce Type: new Abstract: Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tas

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

arXiv:2510.05837v2 Announce Type: replace Abstract: Balancing exploration and exploitation remains a central challenge in reinforcement learning with verifiable rewards (RLVR) for large language model

safetyarxiv-cs-cl

Efficient Disruption of Criminal Networks through Multi-Objective Genetic Algorithms

arXiv:2604.09647v1 Announce Type: cross Abstract: Criminal networks, such as the Sicilian Mafia, pose substantial threats to public safety, national security, and economic stability. Outdated disrupti

Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation

arXiv:2604.11775v1 Announce Type: cross Abstract: Perturbation-based explainability methods such as KernelSHAP provide model-agnostic attributions but are typically impractical for patch-based 3D medi

Efficient Training for Cross-lingual Speech Language Models

arXiv:2604.11096v1 Announce Type: cross Abstract: Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emergin

Elon Musk’s AI software, Grok, continues to generate sexualized images of people without their consent, despite his company’s pledge months …

Elon Musk’s AI software, Grok, continues to generate sexualized images of people without their consent, despite his company’s pledge months ago to halt abusive deepfakes after a public backlash and go

safetygary-marcus--x

EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models

arXiv:2604.11043v1 Announce Type: new Abstract: Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, h

Empowering Video Translation using Multimodal Large Language Models

arXiv:2604.11283v1 Announce Type: new Abstract: Recent developments in video translation have further enhanced cross-lingual access to video content, with multimodal large language models (MLLMs) play

Enabling and Inhibitory Pathways of Students' AI Use Concealment Intention in Higher Education: Evidence from SEM and fsQCA

arXiv:2604.10978v1 Announce Type: cross Abstract: This study investigates students' AI use concealment intention in higher education by integrating the cognition-affect-conation (CAC) framework with a

End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering

arXiv:2511.09282v3 Announce Type: replace-cross Abstract: Significant progress has been made in spoken question answering (SQA) in recent years. However, many existing methods, including large audio l

safetyarxiv-cs-cl

Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design

arXiv:2604.11733v1 Announce Type: cross Abstract: We study routing games in which travelers optimize over routes that are remembered or surfaced, rather than over a fixed exogenous action set. The pap

Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance

arXiv:2604.10437v1 Announce Type: new Abstract: Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potent

Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance

arXiv:2604.10904v1 Announce Type: cross Abstract: AI-based image reconstruction models are increasingly deployed in clinical workflows to improve image quality from noisy data, such as low-dose X-rays

Evolutionary Token-Level Prompt Optimization for Diffusion Models

arXiv:2604.09861v1 Announce Type: new Abstract: Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual

EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation

arXiv:2604.10911v1 Announce Type: new Abstract: Medium-to-long-horizon stock allocation presents significant challenges due toveak predictive structures, non-stadonary market regimes, and the degradat

Examining EAP Students' AI Disclosure Intention: A Cognition-Affect-Conation Perspective

arXiv:2604.10991v1 Announce Type: cross Abstract: The growing use of generative artificial intelligence (AI) in academic writing has raised increasing concerns regarding transparency and academic inte

Exciting news! @theaidocfilm is now available to rent or buy on Apple TV, Prime Video, or wherever you get your movies on demand. If you mis…

Exciting news! @theaidocfilm is now available to rent or buy on Apple TV, Prime Video, or wherever you get your movies on demand. If you missed the theatrical release, you can now watch this urgent fi

safetyconnor-leahy--x

Explainability and Certification of AI-Generated Educational Assessments

arXiv:2604.09622v1 Announce Type: cross Abstract: The rapid adoption of generative artificial intelligence (AI) in educational assessment has created new opportunities for scalable item creation, pers

Explainable Planning for Hybrid Systems

arXiv:2604.09578v1 Announce Type: new Abstract: The recent advancement in artificial intelligence (AI) technologies facilitates a paradigm shift toward automation. Autonomous systems are fully or part