Search: “safety”

Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data

arXiv:2605.19641v1 Announce Type: cross Abstract: Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation sch

Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment

DGX agent

arXiv:2605.18759v1 Announce Type: cross Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance acros

safetyarxiv-cs-ai

20 May 2026

Inverse Design of Metasurface based Absorbers using Physics Guided Conditional Diffusion Models

arXiv:2605.19611v1 Announce Type: new Abstract: Inverse design of metasurfaces for specific electromagnetic responses requires generating geometries that satisfy stringent spectral constraints while m

Kickstarter retracts stricter rules on mature content after creator backlash, and says it adopted the tougher rules because of its payment processor Stripe (Mariella Moon/Engadget)

Mariella Moon / Engadget: Kickstarter retracts stricter rules on mature content after creator backlash, and says it adopted the tougher rules because of its payment processor Stripe — It explained tha

safetytechmeme

LambdaPO: A Lambda Style Policy Optimization for Reasoning Language Models

arXiv:2605.19416v1 Announce Type: new Abstract: Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an ex

safetyarxiv-cs-cl

Learning ORDER-Aware Multimodal Representations for Composite Materials Design

arXiv:2602.02513v2 Announce Type: replace Abstract: Artificial intelligence has shown remarkable success in materials discovery and property prediction, particularly for crystalline and polymer system

Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction

arXiv:2605.19975v1 Announce Type: cross Abstract: Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current train

LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process long contexts, recove…

LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process long contexts, recover earlier information, and reason over many updates that cre

safetyjeremy-howard--x

Low-Compute Watermark Removal via Dual-Domain Natural Projection

arXiv:2510.07538v2 Announce Type: replace Abstract: Effective removal of semantic watermarks requires balancing three competing objectives: high removal success, low perceptual distortion, and low com

Measuring Stereotype and Deviation Biases in Large Language Models

arXiv:2508.06649v3 Announce Type: replace Abstract: Large language models (LLMs) are widely applied across diverse domains, raising concerns about their limitations and potential risks. In this study,

safetyarxiv-cs-cl

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

arXiv:2605.19833v1 Announce Type: cross Abstract: Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains li

Memory-Augmented Reinforcement Learning Agent for CAD Generation

arXiv:2605.19748v1 Announce Type: new Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation

Metric-Gradient Projection for Stable Multi-Agent Policy Learning

arXiv:2605.18809v1 Announce Type: cross Abstract: General-sum multi-agent learning is often governed by a stacked update field in which each agent's policy update changes the optimization landscape fa

Multi-Session Ground Texture SLAM in Low-Dynamic Environments

arXiv:2605.19701v1 Announce Type: new Abstract: The simultaneous localization and mapping community has introduced a growing number of systems adapted for multi-session operations where the operationa

Neuron Incidence Redistribution for Fairness in Medical Image Classification

arXiv:2605.19393v1 Announce Type: new Abstract: Deep learning models for medical image classification are susceptible to subgroup performance disparities across demographic attributes such as age, gen

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients

arXiv:2510.18924v3 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOT

Not all uncertainty is alike: volatility, stochasticity, and exploration

arXiv:2605.19215v1 Announce Type: new Abstract: Adaptive decision-making in biological and artificial intelligence requires balancing the exploitation of known outcomes with the exploration of uncerta

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

arXiv:2605.20164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many impo

One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

arXiv:2511.22940v3 Announce Type: replace Abstract: Recent advances in diffusion models have greatly improved pose-driven character animation. However, existing methods are limited to spatially aligne

Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing

arXiv:2605.20105v1 Announce Type: new Abstract: Learning to generalise from limited data is a fundamental challenge for both artificial and biological systems. A common strategy is to extract reusable

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models

arXiv:2605.19580v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models show promising ability in language-guided robotic tasks. However, making VLA policies reliable remains challenging,

patches allow for trust boundaries > patches separate 'system wants to change state' from 'change is now accepted policy determines what hap…

Patches represent a mechanism for establishing trust boundaries in systems by decoupling the intent to change state from the acceptance and policy-driven implementation of that change. This separation

safetyyohei-nakajima--x

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in

Phase-Aware Mixture of Experts for Agentic Reinforcement Learning

arXiv:2602.17038v3 Announce Type: replace Abstract: Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a single

Physics-informed simulation framework for realistic sonar image generation and statistical validation

arXiv:2605.19712v1 Announce Type: new Abstract: Synthetic sonar datasets offer a scalable alternative to costly real-world acquisition, yet their utility remains limited by the absence of rigorous qua

Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance

arXiv:2605.18801v1 Announce Type: new Abstract: Data is fundamental to large language models (LLMs). However, understanding of what makes certain data useful for different stages of an LLM workflow, i

Precision Physical Activity Prescription via Reinforcement Learning for Functional Actions

arXiv:2605.19208v1 Announce Type: cross Abstract: Physical activity (PA) plays an important role in maintaining and improving health. Daily steps have been a key PA measure that is easily accessible w

Prediction Is Not Physics: Learning and Evaluating Conserved Quantities in Neural Simulators

arXiv:2605.18883v1 Announce Type: cross Abstract: A diffusion model trained on Hamiltonian trajectories can achieve rollout MSE near 10^{-3}, but the standard deviation of its energy over time is betw

Probabilistic Multivariate Time Series Forecasting with Diffusion Copulas

arXiv:2605.19685v1 Announce Type: cross Abstract: Accurately assessing financial risk requires capturing both individual asset volatility and the complex, asymmetric dependence structures that emerge

Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use

arXiv:2605.19151v1 Announce Type: new Abstract: We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human ap

PROWL: Prioritized Regret-Driven Optimization for World Model Learning

arXiv:2605.18803v1 Announce Type: cross Abstract: Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transiti

Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models

arXiv:2605.19462v1 Announce Type: cross Abstract: The success of self-supervised learning (SSL) in vision and NLP has motivated its rapid adoption for time series. However, research has focused primar

Rapid patient-specific neural networks for intraoperative X-ray to volume registration

arXiv:2503.16309v2 Announce Type: replace-cross Abstract: Advanced navigation techniques in image-guided interventions and surgical robotics require the rapid and precise alignment of 3D preoperative

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era

arXiv:2605.18903v1 Announce Type: cross Abstract: Vision-Language Models in Continual Learning (VLM-CL) aim to continuously adapt to new multimodal tasks while retaining prior knowledge. The emerging

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

arXiv:2602.04663v2 Announce Type: replace-cross Abstract: Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

arXiv:2605.20061v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactiv

safetyarxiv-cs-cl

RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning

arXiv:2605.19033v1 Announce Type: cross Abstract: Supervised open-loop training has been widely adopted for training traffic simulation models; however, it fails to capture the inherently dynamic, mul

RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields

arXiv:2412.02818v4 Announce Type: replace-cross Abstract: Robot manipulation policies, while central to the promise of physical AI, are highly vulnerable in the presence of external variations in the

RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations

arXiv:2605.19924v1 Announce Type: new Abstract: Human-in-the-loop reinforcement learning systems achieve near-perfect success on the workstation where they are trained, but collapse when the same robo

RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models

arXiv:2605.19678v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong performance on embodied manipulation, yet they remain brittle under visual observation changes, pa

SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection

arXiv:2605.20157v1 Announce Type: new Abstract: Music streaming fraud, where bad actors artificially inflate stream counts to manipulate chart rankings and royalty payments, poses a significant threat

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

arXiv:2605.18864v1 Announce Type: cross Abstract: Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yiel

Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling

arXiv:2503.06310v4 Announce Type: replace Abstract: Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence,

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

arXiv:2605.19587v1 Announce Type: new Abstract: Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only w

Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weighting

arXiv:2605.19554v1 Announce Type: new Abstract: Instilling creativity in text-to-image (T2I) generation presents a significant challenge, as it requires synthesized images to exhibit not only visual n

Set-Valued Policy Learning

arXiv:2605.19830v1 Announce Type: new Abstract: Conventional treatment policies map patient covariates to a single recommended intervention in order to maximize expected clinical outcomes. Although a

SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents

arXiv:2605.19219v1 Announce Type: new Abstract: A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistica

Smooth Partial Lotteries for Stable Randomized Selection

arXiv:2605.20069v1 Announce Type: new Abstract: Competitive selection processes, from scientific funding to admissions and hiring, use evaluations to score candidates, and eventually choose a subset o