safety

Designing Safety-Constrained LLM Systems for Public Health Information Access

arXiv:2607.13038v1 Announce Type: cross Abstract: We present the design and implementation of a safety constrained large language model (LLM) system for public health information access, focusing on m

Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance

DGX agent

arXiv:2607.13260v1 Announce Type: cross Abstract: Policy documents shape governance outcomes, but their reasoning is often implicit. Participatory commitments and managerial control routinely coexist

safetyarxiv-cs-ai

16 Jul 2026

Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing

arXiv:2607.13103v1 Announce Type: cross Abstract: Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing

Distributionally Robust and Safe Imitation Learning

arXiv:2607.13436v1 Announce Type: new Abstract: Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution s

Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education

arXiv:2607.14046v1 Announce Type: new Abstract: This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a

Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition

arXiv:2607.13347v1 Announce Type: cross Abstract: LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We

Explaining Reinforcement Learning Agents via Inductive Logic Programming

arXiv:2607.13655v1 Announce Type: new Abstract: Explainable Reinforcement Learning (XRL) seeks to make Reinforcement Learning (RL) policies more transparent and interpretable, a key requirement in saf

Final Authority in AI Governance: Frontier-Provider Sovereignty and Action-Centered Deployer Governance

arXiv:2607.13040v1 Announce Type: cross Abstract: This paper examines where final authority should sit once capable AI systems are embedded in organizational workflows. It compares two governance mode

Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding

arXiv:2607.13892v1 Announce Type: new Abstract: Computed tomography (CT) vision-language pretraining from paired volumes and radiology reports is a scalable yet challenging task. Existing methods comm

FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion

arXiv:2607.13656v1 Announce Type: new Abstract: Image-based indoor scene relighting remains challenging due to the complex interplay between cluttered geometry and local illumination, requiring precis

Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

arXiv:2607.13429v1 Announce Type: cross Abstract: Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the standard recipe for vision-langua

GNN-DIP: Neural Corridor Selection for Decomposition-Based Motion Planning

arXiv:2603.12361v2 Announce Type: replace Abstract: Motion planning through narrow passages remains a core challenge: sampling-based planners rarely place samples inside these narrow but critical regi

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

arXiv:2607.13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, c

HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation

arXiv:2607.09776v2 Announce Type: replace-cross Abstract: When adapting Vision Language Action (VLA) models to downstream tasks, multiple rounds of post-training are often required to progressively ad

Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction

arXiv:2607.13646v1 Announce Type: cross Abstract: Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenari

Introducing Human-Centeredness in AI-Assisted Lexicography

arXiv:2607.11808v2 Announce Type: replace-cross Abstract: This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers signifi

Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping

arXiv:2508.12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting vi

Joint On-and-Off Policy Learning for Vision-and-Language Navigation

arXiv:2607.13461v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Rece

LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning

arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and har

Layered Risk Mapping for Autonomous Patient Transport in Expeditionary Medical Facilities

arXiv:2607.13497v1 Announce Type: new Abstract: In expeditionary medical facilities, routine patient transport imposes a compounding burden of personal protective equipment consumption, staff diversio

Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents

arXiv:2606.18223v2 Announce Type: replace-cross Abstract: With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown a

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

arXiv:2604.00830v3 Announce Type: replace-cross Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at

Marker-free deformable registration and fusion for augmented reality-guided positive margin localization during tumor resection surgery

arXiv:2607.13343v1 Announce Type: new Abstract: Positive margins in head and neck oncologic surgery require mapping specimen-side pathology findings to the patient resection bed. This is challenging b

MASPRM: Multi-Agent System Process Reward Model

arXiv:2510.24803v3 Announce Type: replace-cross Abstract: Inference-time search over multi-agent systems (MAS) wastes compute when it cannot identify which agent's intermediate message advanced progre

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

arXiv:2607.13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approach

Mind the Gap: Action Rebinding Attacks against Android GUI Agents

arXiv:2601.12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content a

Music-to-Dance Generation via Atomic Movements

arXiv:2607.13978v1 Announce Type: cross Abstract: Music-driven dance generation aims to produce human motion that is both rhythmically synchronized and semantically consistent with music. While recent

Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration

arXiv:2607.13414v1 Announce Type: cross Abstract: Non-expansive two-time-scale stochastic approximation is governed by a slow stochastic Krasnoselskii--Mann fixed-point iteration rather than by contra

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

arXiv:2505.18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to th

On the Sublinear Regret of Continuous K-Max Bandits

arXiv:2502.13467v2 Announce Type: replace Abstract: The K-Max combinatorial multi-armed bandit problem arises in applications such as recommendation and distributed decision making, where the reward i

Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows

arXiv:2607.13078v1 Announce Type: cross Abstract: LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature

Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation

arXiv:2607.13686v1 Announce Type: new Abstract: We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a conte

OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations

arXiv:2607.13420v1 Announce Type: new Abstract: Clicks on homepage marketing blocks are driven by a dual-mechanism of content interest and access habits. However, habitual clicks often create Pseudo-P

PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner

arXiv:2603.10330v2 Announce Type: replace-cross Abstract: Autonomous driving in complex traffic requires planners that generalize beyond hand-crafted rules, motivating data-driven approaches that lear

PhysClaw-0: A Symbiotic Agentic System for Robot Autonomy via Language Corrections

arXiv:2607.14047v1 Announce Type: new Abstract: Autonomous data collection governs the volume and quality of real-world trajectories for manipulation policy learning. Existing pipelines reduce human e

Pretraining in Actor-Critic Reinforcement Learning for Locomotion

arXiv:2510.12363v4 Announce Type: replace-cross Abstract: The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years.

Price of Fairness in Bandits: A Tight Minimax Characterization

arXiv:2607.13402v1 Announce Type: cross Abstract: In bandit problems, standard regret-minimizing algorithms treat exploration as an amortized cost, which can expose early participants to unfair ex-ant

Privacy Preserving Recommender Systems Balancing Personalization with Privacy

arXiv:2607.13328v1 Announce Type: cross Abstract: Personalized recommendation systems are central to modern e-commerce and retail platforms, but they typically rely on centralized storage of detailed

Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities

arXiv:2607.13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledgi

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

arXiv:2607.13428v1 Announce Type: new Abstract: Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones.

RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset

arXiv:2603.11811v2 Announce Type: replace-cross Abstract: The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the p

Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks

arXiv:2607.13455v1 Announce Type: new Abstract: High-quality teleoperation datasets are costly to collect, particularly for hard tasks. We observe that many tasks exhibit directional asymmetry: comple

SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing

arXiv:2607.13594v1 Announce Type: new Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a gua

SARFA: Segment Anything with Radiomic Feature Alignment

arXiv:2607.13323v1 Announce Type: new Abstract: The Segment Anything Model (SAM) has demonstrated strong generalizability across a variety of segmentation tasks. However, SAM often struggles in situat

SCOPE-RL: Optimizing Reasoning Paths Before and After Success

arXiv:2607.11506v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards. This sparse anchor reliably verif

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

arXiv:2607.13124v1 Announce Type: cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compre

SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning

arXiv:2607.13931v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-languag