Search: “safety”

Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints

arXiv:2601.23221v2 Announce Type: replace Abstract: As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical

OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework

DGX agent

arXiv:2606.08574v1 Announce Type: cross Abstract: Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined p

safetyarxiv-cs-cv

9 Jun 2026

Outage Detection in Self-Healing Smart Grids Using Reinforcement Learning with Spectral Graph Neural Networks

arXiv:2606.07583v1 Announce Type: cross Abstract: Self-healing smart grids can quickly adjust their network configuration during outages to minimize power disruptions. During an outage, several action

PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR

arXiv:2606.08543v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, wher

PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

arXiv:2606.07988v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models a

PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

arXiv:2605.06582v2 Announce Type: replace Abstract: Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In lan

PairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies

arXiv:2606.08795v1 Announce Type: new Abstract: Change detection and scene recognition techniques have been widely applied to Street View Imagery (SVI) to understand changes in scenes across the years

Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach

arXiv:2606.07855v1 Announce Type: new Abstract: Path-planning for autonomous vehicles in threat-laden environments is a fundamental challenge because the problem is nonlinear and nonconvex even in sim

PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow

arXiv:2606.07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patc

Payoff scaling shapes cooperation in LLM agents across languages

arXiv:2601.19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they coo

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

arXiv:2606.09348v1 Announce Type: new Abstract: Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final

Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems

arXiv:2508.00724v2 Announce Type: replace-cross Abstract: The increasing demand for flexible automation has accelerated the adoption of heterogeneous automated guided vehicles (AGVs). This work invest

Physically Consistent Null Space Alignment for Detection of Low-Magnitude False Data Injection Attacks

arXiv:2606.08473v1 Announce Type: new Abstract: False data injection attacks (FDIAs) introducing small measurement perturbations can still cause large deviations in power system state estimation when

Polaffini: A feature-based approach for robust affine and polyaffine image registration

arXiv:2602.17337v2 Announce Type: replace Abstract: In this work we present Polaffini, a robust and versatile framework for anatomically grounded registration. Medical image registration is dominated

PriFT: Prior-Support Guided Supervised Fine-Tuning

arXiv:2606.09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement le

Prisma-World: Camera-Controllable Multi-Agent Video World Model

arXiv:2606.09507v1 Announce Type: new Abstract: Video world models have made rapid progress in generating controllable visual experiences, but most of them still simulate the world from a single obser

PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models

arXiv:2606.08926v1 Announce Type: new Abstract: Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring

Property-Informed Diffusion-Based Text-to-Microstructure Generation

arXiv:2606.08150v1 Announce Type: new Abstract: Designing 3D metamaterial microstructures that meet the intended functions remains a major challenge, as it typically requires domain expertise, iterati

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

arXiv:2606.09711v1 Announce Type: new Abstract: Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

arXiv:2606.08708v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language M

PTDL:Multi-Terrain Fall Recovery via Phase-Terrain Decoupled Learning

arXiv:2606.08922v1 Announce Type: new Abstract: Humanoid robots can fall on slopes, gravel, and uneven ground in unstructured environments. We target integrated fall recovery and locomotion: rebuildin

Q-VGM: Q-Guided Value-Gradient Matching for Flow-Matching VLA Policies

arXiv:2606.08015v1 Announce Type: new Abstract: We propose Q-Guided Value-Gradient Matching (Q-VGM), an off-policy reinforcement learning (RL) method that tackles a long-standing challenge in fine-tun

QnRL: Quantum-Native Reinforcement Learning

arXiv:2606.08276v1 Announce Type: cross Abstract: Quantum reinforcement learning (QRL) is a promising approach to learn effective decision strategies across several applications with stochastic enviro

Quantifying Uncertainty in Space Debris Capture with Active Tether-Net Systems Caused by Noisy Observations

arXiv:2606.07580v1 Announce Type: cross Abstract: As Low Earth Orbit has grown more crowded with space debris, the need for reliable and efficient debris removal solutions becomes more urgent. An acti

Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents

arXiv:2606.08552v1 Announce Type: new Abstract: I discuss some quantitative representations of Promise Theory for processes involving autonomous agents. Agent models are common in software systems, ma

ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies

arXiv:2606.09630v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring

ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration

arXiv:2606.09381v1 Announce Type: new Abstract: Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the

Region-Wise Correspondence Prediction between Manga Line Art Images

arXiv:2509.09501v4 Announce Type: replace Abstract: Understanding region-wise correspondences between manga line art images is fundamental for high-level manga processing, supporting downstream tasks

Reinforcement Learning for Flow-Matching Policies with Density Transport

arXiv:2606.08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems. Our key insight is t

Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations

arXiv:2606.08104v1 Announce Type: new Abstract: Soft-bodied organisms such as octopuses and elephant trunks exhibit remarkable morphological adaptability, dynamically reconfiguring body shape and stif

Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning

arXiv:2606.08436v1 Announce Type: new Abstract: The task of temporal answer grounding in instructional video (TAGV), which aims to locate precise video segments that respond to natural language querie

Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning

arXiv:2606.08020v1 Announce Type: cross Abstract: Hard-constraint decision systems usually veto infeasible candidates. This is too rigid when the system can act: if a known affordable repair would mak

Rethinking the Divergence Regularization in LLM RL

arXiv:2606.09821v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of

Revisiting Articulated Parts Perception in Robot Manipulation

arXiv:2606.08103v1 Announce Type: cross Abstract: We are surrounded by various objects with movable, articulated parts, e.g., box, handle, door. An accurate and generalizable perception of articulated

Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective

arXiv:2602.02572v2 Announce Type: replace-cross Abstract: Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regulariza

ridiculous oversimplification, from a prominent OpenAI employee no less. does this capture your impression of how the two companies have beh…

ridiculous oversimplification, from a prominent OpenAI employee no less. does this capture your impression of how the two companies have behaved? The OAI / Anthropic values difference is deeply misund

safetygary-marcus--x

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

arXiv:2511.07317v2 Announce Type: replace-cross Abstract: We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedur

Robot-DIFT: Correspondence-Sensitive Diffusion Features for Contact-Rich Robot Manipulation

arXiv:2602.11934v2 Announce Type: replace Abstract: Robot manipulation often fails in the final millimeters: a policy may recognize the right object yet miss the pose offsets, boundaries, or pre-conta

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

arXiv:2606.07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility. We identify a data-induced failure mode, PhysHack, in wh

SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models

arXiv:2606.07705v1 Announce Type: cross Abstract: Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing pra

SecureClaw: Clawing Back Control of LLM Agents

arXiv:2606.09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext in

See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning

arXiv:2606.09262v1 Announce Type: new Abstract: Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underl

SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance

arXiv:2606.09157v1 Announce Type: cross Abstract: This paper revisits our pipeline called Syllogistic Evaluation Framework-Common Logic Grammar Construction (SEF-CLGC). We combine formal logical notat

Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control

arXiv:2606.08405v1 Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires

Self-Supervised Learning with a Multi-Task Latent Space Objective

arXiv:2602.05845v2 Announce Type: replace Abstract: We propose a multi-task formulation of self-predictive Siamese SSL in which each spatial transformation defines a distinct latent-space alignment ta

SemDINO: A DINOv3-Driven Network for Cross-Temporal Semantic Alignment in Change Detection

arXiv:2606.09772v1 Announce Type: new Abstract: Semantic change detection (SCD) aims to simultaneously locate land-cover changes and identify semantic categories before and after transition. However,

Sequential statistical inference for Large Language Models: Representation, validity, and monitoring

arXiv:2606.07624v1 Announce Type: new Abstract: This discussion argues that sequential statistical inference can naturally contribute to LLM trustworthiness. In deployment, LLM systems are queried rep

SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling

arXiv:2606.09304v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories with dense per-token supervision from a stronger teacher, and often outperforms