safety

Adaptive FastOPD: Progress-Aware Rollout Horizon Expansion for Efficient On-Policy Distillation

arXiv:2607.29494v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense teacher supervision along student-generated trajectories, but its online rollout process incurs substantial

Safety

Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning

DGX agent

arXiv:2607.28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and

safetyarxiv-cs-ai

3 Aug 2026

Advances, challenges, and opportunities for legged robots

arXiv:2607.28952v1 Announce Type: new Abstract: Humanoid and quadrupedal robots have the potential to revolutionize the way we work, interact, and coexist with intelligent machines. To understand thei

safetyarxiv-cs-ro

Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth

arXiv:2607.28890v1 Announce Type: cross Abstract: Evaluations of LLM-assisted qualitative coding almost universally measure model performance as agreement with human coders, a practice that presumes h

An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks

arXiv:2607.28854v1 Announce Type: new Abstract: Discrete choice modeling is a common tool used for preference elicitation during policy-making, but this is typically done through parametric models. Ma

Automated Reasoning policy refinement in Amazon Bedrock

Amazon Bedrock now supports automatic Automated Reasoning policy refinement. The refinement engine diagnoses failing tests and proposes formal-logic fixes for rule issues and language issues, and you

safetyaws-ml-blog

Automated Straight-line Sewing of Stretchable Fabrics with Different Lengths

arXiv:2607.29464v1 Announce Type: new Abstract: Different Length Alignment Sewing (DLAS), which involves stretching the shorter fabric to match the longer one and sewing them together in a straight li

safetyarxiv-cs-ro

Beyond Component Testing: Validating Agentic AI Systems

arXiv:2607.29405v1 Announce Type: new Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches val

Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models

arXiv:2607.28980v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains. Unlike traditional

Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings

arXiv:2607.29402v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems synergize retrieval mechanisms with generative language models to enhance the accuracy and relevance of r

CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents

arXiv:2607.29190v1 Announce Type: new Abstract: Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates gener

Can Zero-Shot LLMs Predict Child Malnutrition? A Fairness and Temporal Robustness Study

arXiv:2607.29082v1 Announce Type: new Abstract: Child malnutrition remains a major public health challenge in low- and middle-income countries, particularly in South Asia, where early identification o

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges

arXiv:2607.28636v1 Announce Type: new Abstract: LLMs increasingly serve as automated judges, but their judgments remain vulnerable to cognitive biases. Existing mitigations mostly rely on prompt-drive

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation

arXiv:2604.05150v2 Announce Type: replace-cross Abstract: We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which wor

ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning

arXiv:2607.28647v1 Announce Type: cross Abstract: This paper presents ConnectED, a human-centered AI system that supports the full instructional lifecycle in Vietnamese education by linking curriculum

Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment

arXiv:2607.29593v1 Announce Type: new Abstract: This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equ

Deformable Medical Image Registration with KAN-based Implicit Neural Representations

arXiv:2509.22874v2 Announce Type: replace Abstract: Deformable image registration (DIR) is central to medical image analysis, supporting spatial alignment for longitudinal studies and multi-modal fusi

Design Concept: Scaffolding Geopolitical Reflection Among Tech Workers

arXiv:2607.28904v1 Announce Type: cross Abstract: This paper presents a speculative Human-Computer Interaction design proposal for encouraging geopolitical reflexivity amongst tech workers at geopolit

Distance-aware Soft Prompt Guidance for Multimodal Valence-Arousal Estimation

arXiv:2603.13415v2 Announce Type: replace Abstract: Valence-arousal (VA) estimation is crucial for capturing the nuanced nature of human emotions in naturalistic environments. While pre-trained vision

Do Medical Foundation Models Generalize on the African Brain?

arXiv:2607.28771v1 Announce Type: new Abstract: Medical foundation models (FMs) are increasingly used for brain MRI analysis. However, their evaluation remains dominated by high-resource datasets, lea

Domain-Adaptive Deep Joint Source-Channel Coding for Image Classification

arXiv:2607.28907v1 Announce Type: cross Abstract: Deep joint source--channel coding (Deep JSCC) enables visual semantic transmission by mapping inputs directly to channel symbols and task outputs, but

Domain-Division based Progressive Learning for Source-Free Domain Adaptation

arXiv:2607.29202v1 Announce Type: new Abstract: With growing privacy and portability concerns, source-free domain adaptation requires only a source pre-trained model and an unlabeled target domain, al

Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

arXiv:2607.29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a

DoubleHelix: Structured Cross-Modal Fusion for Audio-Visual Speech Recognition with LLMs

arXiv:2607.29112v1 Announce Type: cross Abstract: Audio-visual speech recognition (AVSR) relies on effective fusion of audio and visual modalities, yet existing approaches treat cross-modal interactio

DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search

arXiv:2607.29491v1 Announce Type: cross Abstract: Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circu

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

arXiv:2501.04426v2 Announce Type: replace-cross Abstract: Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improv

DuetHOI: Language-Guided Bimanual Hand--Object Motion Generation with Articulation Planning and Contact Refinement

arXiv:2603.08390v3 Announce Type: replace-cross Abstract: Bimanual articulated-object interaction generation requires a model to capture the evolution of object articulation, coordination between the

DynoDINO: Harnessing Dynamic Latent Information from DINO Features for Multi-Phase Medical Image Segmentation

arXiv:2607.29568v1 Announce Type: new Abstract: Multi-phase Contrast-Enhanced Computed Tomography (CECT) plays a central role in the diagnosis and characterization of focal lesions by capturing tempor

End-to-End Fairness Optimization with Fair Decision-Focused Learning

arXiv:2607.29441v1 Announce Type: new Abstract: Many real-world systems rely on predictive models to inform decisions, and fairness concerns arise in both the prediction and decision stages. We introd

Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models

arXiv:2602.02685v3 Announce Type: replace Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree i

FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents

arXiv:2607.28945v1 Announce Type: new Abstract: Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias. State-of-

fascinating comments on possible slowdown – but probably a red herring. - Anthropic and OpenAI presumably aren’t colluding to slowdown, they…

fascinating comments on possible slowdown – but probably a red herring. - Anthropic and OpenAI presumably aren’t colluding to slowdown, they are asking governments to build a framework such that a slo

safetygary-marcus--x

Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models

arXiv:2607.29079v1 Announce Type: new Abstract: Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content

Few-shot Deep Learning for Phase-Amplitude Aberration Correction in Transcranial Focused Ultrasound

arXiv:2607.29182v1 Announce Type: cross Abstract: Transcranial focused ultrasound (tFUS) is a non-invasive technique that delivers focused acoustic energy through the skull for neuromodulation and the

First Investigation of Deep Learning for Intraoperative Gauze Segmentation in Minimally Invasive Abdominal Surgery

arXiv:2607.29132v1 Announce Type: new Abstract: Surgical gauze is an essential part of surgical procedures, primarily used for controlling bleeding and absorbing bodily fluids. The post-surgical reten

Fisher Information, Training and Bias in Fourier Regression Models

arXiv:2510.06945v2 Announce Type: replace Abstract: Motivated by the growing interest in quantum machine learning, in particular quantum neural networks (QNNs), we study how recently introduced evalua

Flow Matching with Missing Data

arXiv:2607.28698v1 Announce Type: new Abstract: Flow matching assumes fully observed training data, which many real-world applications rarely provide. We propose Missing-Data Flow Matching, which trea

Fragility of Value under Imperfect Alignment

arXiv:2607.28881v1 Announce Type: new Abstract: As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that these systems are aligned with humanity. A common

future generations will have no idea what was real and what was not.

Gary Marcus warns that, with increasingly sophisticated generative‑AI tools, future generations may struggle to tell what is real from what is fabricated. Matt Stoller adds that generative AI will tra

safetygary-marcus--x

GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System

arXiv:2607.29213v1 Announce Type: cross Abstract: Modern recommender systems in food delivery increasingly leverage multimodal signals, including images, text, and user interaction histories, to enhan

Gated Q-learning: Add Off-Policy Bias to Taste

arXiv:2607.28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental

HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering

arXiv:2607.29638v1 Announce Type: new Abstract: Multi-page document visual question answering requires locating sparse evidence at both the page and region levels. Existing approaches typically emphas

Homotopy-Aware Corridor Generation without Predefined Reference Paths

arXiv:2607.29513v1 Announce Type: new Abstract: Generating safe corridors is essential for collision-free robotic motion planning, yet most existing methods rely on predefined reference paths, which b

safetyarxiv-cs-ro

How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

arXiv:2607.28674v1 Announce Type: new Abstract: Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpr

Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity

arXiv:2607.28849v1 Announce Type: cross Abstract: Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems

Implicit Reasoning for Large Language Model-based Generative Recommendation

arXiv:2606.14142v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world kn

In-situ Autoguidance: Eliciting Self-Correction in Diffusion Models

arXiv:2510.17136v2 Announce Type: replace Abstract: The generation of high-quality, diverse, and prompt-aligned images is a central goal in image-generating diffusion models. The popular classifier-fr

Incorporating data drift to perform survival analysis on credit risk

arXiv:2601.20533v2 Announce Type: replace-cross Abstract: Survival analysis has become a standard approach for modelling time to default by time-varying covariates in credit risk. Unlike most existing