safety

MGMCL: Multi-Granularity Manifold Contrastive Learning With Neural ODEs for Cross-Subject EEG Emotion Recognition

arXiv:2608.08440v1 Announce Type: new Abstract: Cross-subject electroencephalogram (EEG)-based emotion recognition remains challenging due to substantial inter-individual variability and discrete form

Safety

Mismatch Matters: On-Policy Distillation Beyond Token Agreement

DGX agent

arXiv:2608.09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement,

safetyarxiv-cs-ai

11 Aug 2026

Mitigating Gender Bias in English to Romanian Machine Translation

arXiv:2608.08606v1 Announce Type: cross Abstract: Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a

ML-Based Hierarchical Prediction for Practical Energy Scheduling in Dynamic NTN-WPT Systems

arXiv:2608.08804v1 Announce Type: cross Abstract: With advancements in long-distance wireless power transfer (WPT) and space-based energy technologies, integrating WPT into non-terrestrial networks (N

Model-Based Systems Engineering Framework for SysML-Driven Design of Autonomous UAVs

arXiv:2608.09547v1 Announce Type: new Abstract: Autonomous Unmanned Aerial Vehicles (UAVs) are complex cyber-physical systems that require the coordinated integration of flight control, navigation, pe

Model the Edit, Not the Image: Visual Autoregressive Editing from a Source-Centric Perspective

arXiv:2608.09057v1 Announce Type: new Abstract: Next-scale visual autoregressive models (VARs) have emerged as a powerful generative paradigm, producing high-quality images through efficient coarse-to

Motif 3: Technical Report

arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar

MotionCraft: Latent World Modeling with Sparse Attention for Visual Upscaling

arXiv:2608.08553v1 Announce Type: new Abstract: Video super-resolution (VSR) aims to recover high-fidelity high-resolution videos from low-resolution inputs and is central to applications ranging from

Multi-Agent AI Safety as an Institutional Design Problem

arXiv:2608.09828v1 Announce Type: cross Abstract: AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent wo

Multi-Branch Policy Optimization for Multimodal Large Language Models

arXiv:2608.07581v1 Announce Type: cross Abstract: Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a si

Multimodal Model Diffing for Feature Discovery and Control

arXiv:2608.09928v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to

MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model

arXiv:2603.02743v4 Announce Type: replace Abstract: Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and

Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks

arXiv:2608.08567v1 Announce Type: new Abstract: A central obstacle in building graph foundation models is the input heterogeneity in terms of feature space dimensionality, semantics, and structure. Su

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

arXiv:2509.03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. Howev

North Africa's Missing Framework: NLP-Driven Mental Healthcare in Algeria and Implications for Low-resource Settings

arXiv:2608.08607v1 Announce Type: new Abstract: Mental health disorders are a leading cause of disability worldwide, yet Natural Language Processing (NLP) research for mental healthcare has remained c

OD-Gear: Online Decomposition and Group Sampling for Expert-Guided Adversarial Routing in Scalable Capacitated Vehicle Routing

arXiv:2602.00488v3 Announce Type: replace Abstract: Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generaliz

On the use of foundation models in cognitive science

arXiv:2608.07812v1 Announce Type: new Abstract: A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations o

OnEvoMemory: Evolving Memory through Online Robot Rollouts for Pretrained Robot Policies

arXiv:2608.08749v1 Announce Type: new Abstract: Long-horizon robot manipulation requires policies to track completed subtasks and critical interaction events. However, existing memory mechanisms heavi

OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance fo…

OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance for a much cheaper price. Now, it is increasingly an existenti

safetysonya-huang--x

PAM: Training Policy-Aligned Moderation Filters at Scale

arXiv:2505.19766v4 Announce Type: replace Abstract: Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet exi

PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation

arXiv:2608.08726v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) uses a privileged teacher to supervise a reasoning model on prefixes sampled from its own rollouts. Yet each rollou

Penalizing Length: Uncovering Systematic Bias in Quality Estimation Metrics

arXiv:2510.22028v4 Announce Type: replace Abstract: Quality Estimation (QE) metrics are vital in machine translation for reference-free evaluation and increasingly serve as selection criteria in data

Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots

arXiv:2608.09931v1 Announce Type: new Abstract: Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Dist

Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models

arXiv:2608.08199v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in group decision-making with other LLMs and humans. Yet it remains unclear whether their influen

PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention

arXiv:2608.07681v1 Announce Type: new Abstract: Accurate and robust time series forecasting is essential in many applications involving physical processes, such as manufacturing monitoring and astroph

Physics-Informed Policy Iteration for High-Dimensional Hamilton--Jacobi--Bellman Equations: Interior Error Bounds without Boundary Data

arXiv:2508.01718v2 Announce Type: replace Abstract: We develop a physics-informed policy-iteration method for stationary second-order Hamilton--Jacobi--Bellman equations arising in continuous-time sto

PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering

arXiv:2608.07509v1 Announce Type: cross Abstract: LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold

Position Bias in Ordinal Classification: A Systematic Evaluation

arXiv:2608.08869v1 Announce Type: new Abstract: Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predi

PQC in Plaintext: Google Cloud’s post-quantum cryptography roadmap

Securing infrastructure and services against a future cryptographically-relevant quantum computer has been a goal for Google for a decade, and we’ve dedicated ourselves to help developers by advancing

safetygoogle-cloud-ai

Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models

arXiv:2608.09551v1 Announce Type: new Abstract: In the era of large language models (LLMs), attackers often manipulate natural language to elicit unsafe or harmful outputs, creating a new natural lang

Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations

arXiv:2608.08245v1 Announce Type: cross Abstract: LLM applications deployed at scale face a fundamental challenge: privacy constraints prevent direct inspection of user interactions, making it difficu

Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits

arXiv:2608.07913v1 Announce Type: cross Abstract: Selective-risk certificates promise that accepted outputs meet a declared error target. We develop Fed-SRC, a score-agnostic certificate for federated

Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

arXiv:2608.09263v1 Announce Type: new Abstract: Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this g

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation

arXiv:2608.09228v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the

Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update

arXiv:2607.11505v2 Announce Type: replace-cross Abstract: Post-training for large language models typically couples policy exploration with model optimization, hindering the reuse of high-reward behav

Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression

arXiv:2608.08960v1 Announce Type: new Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduce

Real-Time Nonlinear MPC via Sequential Quadratic Programming with Structure-Exploiting ADMM and Interior-Point Methods for Underactuated Double-Pendulum Swing-Up

arXiv:2608.09272v1 Announce Type: cross Abstract: The 4th 'AI Olympics with RealAIGym' competition, to be held at IJCAI-ECAI 2026 in Bremen, challenges participants to develop a global control policy

Reconfigurable Structural Robotic Assembly: Interlocking 3D Aggregations with Self-Aligning Compound Nested Lattice Modules

arXiv:2608.07576v1 Announce Type: new Abstract: Robotic construction systems often treat the material system and the robot as separate design problems, locating intelligence primarily in hardware, sen

Reflex First, Reflect Later: Latency-Aware Embodied LLM Agents for Dynamic Response

arXiv:2506.07223v2 Announce Type: replace Abstract: Large language models (LLMs) have substantially improved the planning capabilities of embodied agents, enabling their deployment in dynamic and safe

Regret of exploratory policy improvement and q-learning

arXiv:2411.01302v2 Announce Type: replace Abstract: We study the convergence of q-learning and related algorithms introduced by Jia and Zhou (J. Mach. Learn. Res., 24 (2023), 161) for controlled diffu

REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

arXiv:2608.07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in

Removing Infrastructure Barriers in Human-Robot Collaboration Through Wireless Reconfigurable Cells

arXiv:2608.09658v1 Announce Type: cross Abstract: Human-Robot Collaboration (HRC) plays a vital role in dynamic, high mix, low volume industrial scenarios such as remanufacturing, which frequently fac

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

arXiv:2508.16406v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature

Retrieval-Augmented Generation-Based Color Restoration for Low-Light Image Enhancement

arXiv:2608.08211v1 Announce Type: cross Abstract: Recent low-light image enhancement (LLIE) methods have driven brightness and structural fidelity close to that of normally-exposed images, yet their o

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

arXiv:2608.09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures ar

RobustDefect-LLM: Explainable and Robustness-Aware Industrial Surface Defect Classification with Decision Support and AI-Assisted Reporting

arXiv:2608.08589v1 Announce Type: new Abstract: This paper presents RobustDefect-LLM, an industrial surface-defect inspection framework integrating deep-learning classification, operator-facing visual

RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance

arXiv:2608.09853v1 Announce Type: cross Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from

SAFE-CHEM: Uncertainty-Aware Policy Switching for Robust Robotic Chemistry

arXiv:2608.09303v1 Announce Type: cross Abstract: The deployment of autonomous robotic systems in chemistry laboratories is accelerating experimental workflows and providing the foundational data for