safety

Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs

arXiv:2606.29092v1 Announce Type: cross Abstract: In a changing decision problem, standard dynamic-regret analyses have often equated the cost of non-stationarity to how far loss moves. However, it is

Safety

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners

DGX agent

arXiv:2606.29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervis

safetyarxiv-cs-ai

30 Jun 2026

PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning

arXiv:2606.30291v1 Announce Type: new Abstract: Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion meth

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

arXiv:2603.05786v2 Announce Type: replace-cross Abstract: As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which int

Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification

arXiv:2606.30105v1 Announce Type: new Abstract: Quantitative verification of neural networks requires reasoning about probabilities under substantial uncertainty in both input distributions and their

ProSpec RL: Plan Ahead, then Execute

arXiv:2407.21359v2 Announce Type: replace-cross Abstract: Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental

PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF

arXiv:2606.29758v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) for Large Language Models increasingly relies on critic-free methods as a practical alternative to a

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

arXiv:2606.29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently trai

ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control

arXiv:2606.30362v1 Announce Type: cross Abstract: While current Behavior Foundation Models (BFMs) provide robust control priors for humanoids, they only execute pre-defined reference motions. As a res

REAR: Test-time Preference Realignment through Reward Decomposition

arXiv:2606.30339v1 Announce Type: new Abstract: Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to

Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts

arXiv:2606.30518v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves language models by grounding generation in external context. However, it can be fragile when the retrieved

ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies

arXiv:2606.28939v1 Announce Type: new Abstract: Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into

ReMAP-PET: Beyond Visual Understanding -- Learning Region-Guided Metabolic Alignment Semantics from Brain PET

arXiv:2606.29577v1 Announce Type: cross Abstract: Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain f

RePer-360: Releasing Perspective Priors for 360^irc Depth Estimation via Self-Modulation

arXiv:2603.05999v2 Announce Type: replace Abstract: Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360^irc images due to the substan

Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair

arXiv:2606.28620v1 Announce Type: cross Abstract: Fayyazi et al. (2025) recently proposed FACTER, a model-agnostic framework designed to jointly enforce fairness and statistical coverage in LLM-based

Resolution Thresholds in VLM Detection of Harmful ASCII Art Across Construction Modes and Languages

arXiv:2606.29649v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) are increasingly deployed as content moderation tools, yet they remain vulnerable to jailbreak attacks in which harm

RetrDex: Efficient Object Retrieval in Cluttered Scenes with a Dexterous Hand

arXiv:2502.18423v3 Announce Type: replace Abstract: Retrieving objects buried beneath clutter is both challenging and time-consuming, as complex support relationships make manipulation particularly di

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

arXiv:2602.09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (

Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation

arXiv:2606.29997v1 Announce Type: new Abstract: Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited a

RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation

arXiv:2606.29934v1 Announce Type: new Abstract: Image-goal navigation is a key challenge in embodied robotics, where an agent must reach a target specified solely by a goal image. While existing reinf

RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought

arXiv:2606.15753v2 Announce Type: replace Abstract: Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding th

Robotic Arm-Based Spectral Sensing for Strawberry Positioning and Non-Destructive Sweetness Measurement

arXiv:2606.28555v1 Announce Type: new Abstract: Accurate assessment of sweetness is essential for quality control in agriculture, yet conventional methods rely on destructive sampling and are difficul

Robust Extended Kalman Filter for Land Navigation Using Massive Array of MEMS IMUs

arXiv:2606.29271v1 Announce Type: cross Abstract: We propose a robust Extended Kalman Filter (EKF) architecture for land navigation using an array of hundreds of low-cost micro-electromechanical syste

Robust Strategic Classification under Decision-Dependent Cost Uncertainty

arXiv:2606.30136v1 Announce Type: new Abstract: Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably chang

Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets

arXiv:2606.29837v1 Announce Type: new Abstract: Dataset distillation (DD) condenses large corpora into compact, information-rich subsets for efficient training and reuse. However, under noisy supervis

Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

arXiv:2606.29428v1 Announce Type: new Abstract: Zero-shot anomaly detection aims to identify defects in arbitrary novel domains; however, existing models assume that the auxiliary data contains a rich

Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

arXiv:2410.01244v2 Announce Type: replace-cross Abstract: We introduce a novel Wasserstein-1 (W_1) path-space divergence for stochastic and deterministic dynamics and establish a Wasserstein Uncertain

SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance

arXiv:2606.30113v1 Announce Type: cross Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from dis

SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers

arXiv:2606.29360v1 Announce Type: new Abstract: High-resolution Diffusion Transformer (DiT) inference contains substantial spatial redundancy, but many spatially adaptive implementations encode region

Safety from Honesty in a Disinterested AI Predictor

arXiv:2606.29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior th

SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm

arXiv:2606.20523v2 Announce Type: replace-cross Abstract: Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

arXiv:2606.28562v1 Announce Type: new Abstract: On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent

Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation

arXiv:2606.29941v1 Announce Type: cross Abstract: Visuo-Tactile policies leveraging optical tactile sensors have shown great promise in contact-rich manipulation. These sensors achieve high spatial re

Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery

arXiv:2606.29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in s

Sequential Fairness Auditing with Limited Output Access

arXiv:2606.30338v1 Announce Type: new Abstract: External evaluations are becoming increasingly central to the governance of AI systems. In practice, however, independent auditors often have limited ac

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

arXiv:2606.30444v1 Announce Type: cross Abstract: Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut

SIR: Structured Image Representations for Explainable Robot Learning

arXiv:2606.30101v1 Announce Type: cross Abstract: Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations

“Sometimes I wonder, maybe everything is conscious, or nothing is conscious. I prefer the former; it just seems more fun.” – Elon Musk

“Sometimes I wonder, maybe everything is conscious, or nothing is conscious. I prefer the former; it just seems more fun.” – Elon Musk Media Neuralink has solved through-dura electrode implantation! T

safetyelon-musk--x

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

arXiv:2602.23353v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model

SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning

arXiv:2606.29322v1 Announce Type: new Abstract: Collaborative learning is sustainable only when it benefits each participant. Standard federated learning optimizes a global average objective, which ca

SPACE: Swarm Pheromone Fields for Adaptive Collision-Aware Exploration

arXiv:2606.29372v1 Announce Type: new Abstract: Massive robot swarms can explore unknown environments quickly, but adding robots eventually stops helping. Doorways and dense traffic create congestion,

SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence

arXiv:2412.04739v2 Announce Type: replace Abstract: Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing attempts to

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-

SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference

arXiv:2602.20610v3 Announce Type: replace-cross Abstract: Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large lang

Spectral phase transitions and trainability in neural network learning dynamics

arXiv:2606.28486v1 Announce Type: cross Abstract: The emergence of low-dimensional structures in the spectra of neural network weight matrices is a common empirical feature of trained models, but the

Sphere-VIO: Fast and Robust Visual-Inertial Odometry via Unified Spherical Representation for Heterogeneous Multi-Camera Systems

arXiv:2606.29910v1 Announce Type: new Abstract: Multi-camera visual-inertial odometry (VIO) overcomes the inherent limitations of pure visual systems by expanding the field of view. However, existing

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

arXiv:2510.12784v2 Announce Type: replace-cross Abstract: Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding

StackingNet: Collective Inference Across Independent AI Foundation Models

arXiv:2602.13792v2 Announce Type: replace Abstract: Artificial intelligence built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems r