safety

Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing

arXiv:2604.20704v1 Announce Type: cross Abstract: Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected g

Safety

Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs

DGX agent

arXiv:2604.19780v1 Announce Type: new Abstract: Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, exis

safetyarxiv-cs-cl

23 Apr 2026

Best Policy Learning from Trajectory Preference Feedback

arXiv:2501.18873v4 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned rew

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring

arXiv:2604.19984v1 Announce Type: cross Abstract: Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs generate c

Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation

arXiv:2601.03396v2 Announce Type: replace Abstract: Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underex

safetyarxiv-cs-cl

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics

arXiv:2602.15861v2 Announce Type: replace-cross Abstract: Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labelin

ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration

arXiv:2604.19856v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for generating Register-Transfer Level (RTL) code from natural language specifications, but single-shot gene

CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation

arXiv:2603.25383v3 Announce Type: replace Abstract: CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requir

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment

arXiv:2510.18471v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between the

Cognitive Alignment At No Cost: Inducing Human Attention Biases For Interpretable Vision Transformers

arXiv:2604.20027v1 Announce Type: cross Abstract: For state-of-the-art image understanding, Vision Transformers (ViTs) have become the standard architecture but their processing diverges substantially

CoRe: Joint Optimization with Contrastive Learning for Medical Image Registration

arXiv:2603.23694v2 Announce Type: replace Abstract: Medical image registration is a fundamental task in medical image analysis, enabling the alignment of images from different modalities or time point

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation

arXiv:2604.20763v1 Announce Type: cross Abstract: Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristi

CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction

arXiv:2505.04897v2 Announce Type: replace-cross Abstract: Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly em

DAIRE: A lightweight AI model for real-time detection of Controller Area Network attacks in the Internet of Vehicles

arXiv:2604.20771v1 Announce Type: cross Abstract: The Internet of Vehicles (IoV) is advancing modern transportation by improving safety, efficiency, and intelligence. However, the reliance on the Cont

Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms

arXiv:2604.20492v1 Announce Type: cross Abstract: In this paper, it is shown, for the first time, that centralized performance is achievable in decentralized learning without sharing the local dataset

Diagnosing CFG Interpretation in LLMs

arXiv:2604.20811v1 Announce Type: new Abstract: As LLMs are increasingly integrated into agentic systems, they must adhere to dynamically defined, machine-interpretable interfaces. We evaluate LLMs as

Distributional Inverse Reinforcement Learning

arXiv:2510.03013v3 Announce Type: replace Abstract: We propose a distributional framework for offline Inverse Reinforcement Learning (IRL) that jointly models uncertainty over reward functions and ful

DRIV-EX: Counterfactual Explanations for Driving LLMs

arXiv:2603.00696v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose

safetyarxiv-cs-cl

Dubious predictions that have yet to be fulfilled have given dubious people like Sam Altman and Elon Musk extraordinary power over society. …

Dubious predictions that have yet to be fulfilled have given dubious people like Sam Altman and Elon Musk extraordinary power over society. @carissaveliz's lecture @@TEDTalks (which I was lucky enough

safetygary-marcus--x

Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems

arXiv:2604.19980v1 Announce Type: new Abstract: This paper presents a model-based reinforcement learning (RL) framework for optimal closed-loop control of nonlinear robotic systems. The proposed appro

Efficiently Closing Loops in LiDAR-Based SLAM Using Point Cloud Density Maps

arXiv:2501.07399v2 Announce Type: replace Abstract: Consistent maps are key for most autonomous mobile robots, and they often use SLAM approaches to build such maps. Loop closures via place recognitio

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

arXiv:2604.20012v1 Announce Type: cross Abstract: Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from

Environmental Understanding Vision-Language Model for Embodied Agent

arXiv:2604.19839v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown strong perception and reasoning abilities for instruction-following embodied agents. However, despite these a

Epistemic Constitutionalism Or: how to avoid coherence bias

arXiv:2601.14295v3 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their

Epistemology gives a Future to Complementarity in Human-AI Interactions

arXiv:2601.09871v2 Announce Type: replace Abstract: Human-AI complementarity is the claim that a human supported by an AI system can outperform either alone in a decision-making process. Since its int

ETac: A Lightweight and Efficient Tactile Simulation Framework for Learning Dexterous Manipulation

arXiv:2604.20295v1 Announce Type: new Abstract: Tactile sensors are increasingly integrated into dexterous robotic manipulators to enhance contact perception. However, learning manipulation policies t

Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis

arXiv:2604.20577v1 Announce Type: cross Abstract: An assurance case is a structured argument document that justifies claims about a system's requirements or properties, which are supported by evidence

Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations

arXiv:2603.15867v2 Announce Type: replace Abstract: The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainabil

Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks

arXiv:2604.19755v1 Announce Type: new Abstract: Anti-money laundering (AML) transaction monitoring generates large volumes of alerts that must be rapidly triaged by investigators under strict audit an

Explainable Speech Emotion Recognition: Weighted Attribute Fairness to Model Demographic Contributions to Social Bias

arXiv:2604.19763v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) systems have growing applications in sensitive domains such as mental health and education, where biased predictions

Fairness-Aware Multi-Group Target Detection in Online Discussion

arXiv:2407.11933v4 Announce Type: replace Abstract: Target-group detection is the task of detecting which group(s) a piece of content is ``directed at or about''. Applications include targeted marketi

Faster Fixed-Point Methods for Multichain MDPs

arXiv:2506.20910v2 Announce Type: replace-cross Abstract: We study value-iteration (VI) algorithms for solving general (a.k.a. multichain) Markov decision processes (MDPs) under the average-reward cri

FingerEye: Continuous and Unified Vision-Tactile Sensing for Dexterous Manipulation

arXiv:2604.20689v1 Announce Type: new Abstract: Dexterous robotic manipulation requires comprehensive perception across all phases of interaction: pre-contact, contact initiation, and post-contact. Su

FLOSS: Federated Learning with Opt-Out and Straggler Support

arXiv:2507.23115v2 Announce Type: replace-cross Abstract: Previous work on data privacy in federated learning systems focuses on privacy-preserving operations for data from users who have agreed to sh

FluSplat: Sparse-View 3D Editing without Test-Time Optimization

arXiv:2604.20038v1 Announce Type: new Abstract: Recent advances in text-guided image editing and 3D Gaussian Splatting (3DGS) have enabled high-quality 3D scene manipulation. However, existing pipelin

Frictionless Love: Associations Between AI Companion Roles and Behavioral Addiction

arXiv:2604.20011v1 Announce Type: cross Abstract: AI companion chatbots increasingly shape how people seek social and emotional connection, sometimes substituting for relationships with romantic partn

From Fuzzy to Formal: Scaling Hospital Quality Improvement with AI

arXiv:2604.20055v1 Announce Type: new Abstract: Hospital Quality Improvement (QI) plays a critical role in optimizing healthcare delivery by translating high-level hospital goals into actionable solut

From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP

arXiv:2510.12817v3 Announce Type: replace-cross Abstract: Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the diversity of human perspectives rather than mere

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

arXiv:2604.20300v1 Announce Type: new Abstract: For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--

FurnSet: Exploiting Repeats for 3D Scene Reconstruction

arXiv:2604.20093v1 Announce Type: new Abstract: Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independe

Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework

arXiv:2604.20288v1 Announce Type: new Abstract: Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency. Howeve

Generative Flow Networks for Model Adaptation in Digital Twins of Natural Systems

arXiv:2604.20707v1 Announce Type: new Abstract: Digital twins of natural systems must remain aligned with physical systems that evolve over time, are only partially observed, and are typically modeled

Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs

arXiv:2604.20382v1 Announce Type: new Abstract: Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high

safetyarxiv-cs-cl

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning

arXiv:2604.20659v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct out

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

arXiv:2604.19790v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g.

Hybrid Latent Reasoning with Decoupled Policy Optimization

arXiv:2604.20328v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, a

Hybrid Policy Distillation for LLMs

arXiv:2604.20244v1 Announce Type: cross Abstract: Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of

i-WiViG: Interpretable Window Vision GNN

arXiv:2503.08321v2 Announce Type: replace Abstract: Vision graph neural networks have emerged as a popular approach for modeling the global and spatial context for image recognition. However, a signif