safety

Designing Datacenter Power Delivery Hierarchies for the AI Era

arXiv:2605.16255v1 Announce Type: cross Abstract: Demand for AI accelerators is rapidly increasing rack power density, with projections approaching 1MW per deployment by 2027. This poses a major chall

Detecting Heel Strike and toe off Events Using Kinematic Methods and LSTM Models

DGX agent

arXiv:2503.00794v2 Announce Type: replace Abstract: Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where pre

safetyarxiv-cs-ro

18 May 2026

Differentially Private Motif-Preserving Multi-modal Hashing

arXiv:2605.15460v1 Announce Type: cross Abstract: Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic simil

Diffusion Policy for Coordinated Control of a Nonholonomic Mobile Base and Dual Arms in Door Opening and Passing

arXiv:2605.15352v1 Announce Type: new Abstract: Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arm

DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments

arXiv:2605.15519v1 Announce Type: cross Abstract: Visual active search (VAS) has been introduced as a modeling framework that leverages visual cues to direct aerial (e.g., UAV-based) exploration and p

Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space

arXiv:2605.15368v1 Announce Type: new Abstract: Group-convolutional neural networks (GCNNs) are among the most important methods for introducing symmetry as an inductive bias in deep learning: In each

Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?

arXiv:2605.15855v1 Announce Type: new Abstract: Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignme

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

arXiv:2511.19399v3 Announce Type: replace-cross Abstract: Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are tr

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power

arXiv:2512.09673v3 Announce Type: replace-cross Abstract: Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide doma

Driving Through the Network: Performance and Workload Under Latency and Video Impairment

arXiv:2605.15952v1 Announce Type: cross Abstract: Teleoperation promises to extend the operational envelope of automated vehicles, yet it critically depends on network latency and video quality. We re

DualKV: Shared-Prompt Flash Attention for Efficient RL Training with Large Rollouts and Long Contexts

arXiv:2605.15422v1 Announce Type: new Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard F

DualReg: Dual-Space Filtering and Reinforcement for Rigid Registration

arXiv:2508.17034v2 Announce Type: cross Abstract: Noisy, partially overlapping data and the need for real-time processing pose major challenges for rigid registration. Considering that feature-based m

Dynamic Plasma Shape Control with Arbitrary Sensor Subsets

arXiv:2605.15935v1 Announce Type: new Abstract: Plasma shape control in tokamaks requires a real-time controller that tracks dynamically changing shape targets while tolerating diagnostic failures. Cl

Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

arXiv:2509.23352v3 Announce Type: replace-cross Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in

Efficiently Solving Mixed-Hierarchy Games with Quasi-Policy Approximations

arXiv:2602.01568v2 Announce Type: replace-cross Abstract: Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. Whil

EgoExo-WM: Unlocking Exo Video for Ego World Models

arXiv:2605.15477v1 Announce Type: new Abstract: Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited avail

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

arXiv:2605.15684v1 Announce Type: new Abstract: The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffus

Embedding-perturbed Exploration Preference Optimization for Flow Models

arXiv:2605.15803v1 Announce Type: new Abstract: Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-

Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes

arXiv:2605.15586v1 Announce Type: cross Abstract: Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy

arXiv:2605.15711v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Exi

Eskwai for Students: Generative AI Assistant for Legal Education in Ghana

arXiv:2605.15380v1 Announce Type: new Abstract: Recent advances in generative AI have shown their potential to be leveraged for legal education. Yet, work on the development and deployment of such sys

safetyarxiv-cs-cl

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability

arXiv:2605.16041v1 Announce Type: cross Abstract: Machine learning systems increasingly make life-changing decisions about individuals, such as loan approvals, hiring, and cheating detection, raising

f-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target and model log probabilities is an effective, low v

FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures

arXiv:2604.05966v2 Announce Type: replace Abstract: Financial reporting systems increasingly leverage Large Language Models (LLMs) to extract and summarize corporate disclosures. However, most existin

safetyarxiv-cs-cl

FLASH: Efficient Visuomotor Policy via Sparse Sampling

arXiv:2605.15492v1 Announce Type: cross Abstract: Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative d

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

arXiv:2604.04539v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Poli

FlipAttack: Jailbreak LLMs via Flipping

arXiv:2410.02832v2 Announce Type: replace-cross Abstract: This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we

Flowette: Flow Matching with Graphette Priors for Graph Generation

arXiv:2602.23566v2 Announce Type: replace-cross Abstract: We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs

FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy

arXiv:2605.15944v1 Announce Type: cross Abstract: Visuomotor policies aim to learn complex manipulation tasks from expert demonstrations. However, generating smooth and coherent trajectories remains c

for the facts, courtesy @RachelBitecofer:

I cannot provide an accurate summary without access to the actual content of this post. The title fragment suggests Rachel Bitecofer provided factual information shared by Gary Marcus on X (Twitter),

safetygary-marcus--x

Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

arXiv:2605.16198v1 Announce Type: new Abstract: We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle,

From Full and Partial Intraoral Scans to Crown Proposal: A Classification-Guided Restoration Assistance Pipeline

arXiv:2605.15241v1 Announce Type: cross Abstract: Single-unit crown restoration is among the most common procedures in clinical dentistry, with CAD/CAM workflows now designing crowns directly from int

From I/O to Code with Discovery Agent

arXiv:2605.15334v1 Announce Type: cross Abstract: The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achie

From Model Design to Organizational Design: Complexity Redistribution and Trade-Offs in Generative AI

arXiv:2506.22440v2 Announce Type: replace-cross Abstract: This paper introduces the Generality-Accuracy-Simplicity (GAS) framework to analyze how large language models (LLMs) are reshaping organizatio

From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection

arXiv:2602.20630v4 Announce Type: replace Abstract: Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning

From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks

arXiv:2605.15328v1 Announce Type: new Abstract: Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for more complex mode

GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

arXiv:2605.15836v1 Announce Type: cross Abstract: Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling h

Gaussian Relational Graph Transformer

arXiv:2605.15575v1 Announce Type: new Abstract: Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals

arXiv:2508.17218v3 Announce Type: replace-cross Abstract: Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irre

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

arXiv:2605.15491v1 Announce Type: cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the

GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective

arXiv:2605.15723v1 Announce Type: cross Abstract: Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities la

HoloMotion-1 Technical Report

arXiv:2605.15336v1 Announce Type: cross Abstract: In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1

HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

arXiv:2603.03243v2 Announce Type: replace Abstract: We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulat

How Google Does It: Fleet-wide, large-scale A/B experimentation

When most people think of A/B experimentation, they think of button colors, landing page layouts, or checkout flows. At Google, many fundamental infrastructure improvements also need the rigor of A/B

safetygoogle-cloud-ai

HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion

arXiv:2605.15741v1 Announce Type: new Abstract: Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental 'granularity dilemma': captu

Imperfect World Models are Exploitable

arXiv:2605.15960v1 Announce Type: new Abstract: We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy sh

Import AI 457: AI stuxnet; cursed Muon optimizer; and positive alignment

This newsletter explores three AI topics: potential weaponization risks of AI systems (framed as 'AI stuxnet'), issues with the Muon optimizer in machine learning, and progress or approaches toward po

safetyimport-ai

Improve Large Language Model Systems with User Logs

arXiv:2602.06470v2 Announce Type: replace-cross Abstract: Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constra