All entries

arXiv:2606.31836v1 Announce Type: new Abstract: In the field of robot learning, large-scale and diverse demonstration trajectories provide the fundamental basis for enhancing robotic manipulation abil

applicationsarxiv-cs-ro

Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling

DGX agent

arXiv:2507.11061v3 Announce Type: replace-cross Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content.

local-aiarxiv-cs-ai

1 Jul 2026

Robust Autonomous UAV Landing on Maritime Platforms via Multimodal Agentic AI and Active Wave Compensation

arXiv:2606.31613v1 Announce Type: new Abstract: Autonomous aerial inspection of marine infrastructure is frequently compromised by stochastic sea states, introducing risks of high-kinetic impacts, pos

agentsarxiv-cs-cv

Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings

arXiv:2606.31602v1 Announce Type: new Abstract: This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and toke

safetyarxiv-cs-cl

Robustness-Based Synthesis for Time Window Temporal Logic Specifications via Mixed-Integer Linear Programming

arXiv:2606.30820v1 Announce Type: new Abstract: Time Window Temporal Logic (TWTL) is a rich specification language for cyber-physical systems that can compactly express sequential tasks with explicit

researcharxiv-cs-ro

Applications

Robustness of neural networks to random noise perturbations of their inputs

arXiv:2606.31581v1 Announce Type: new Abstract: We investigate the problem of the robustness of a trained neural network to the perturbation of its input values. More specifically, we examine the inte

applicationsarxiv-cs-lg

Robustness of Robotic Manipulation: Foundations and Frontiers

arXiv:2606.31494v1 Announce Type: cross Abstract: Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robu

safetyarxiv-cs-ai

RoPoLL: Robust Panel of LLM Judges

arXiv:2606.30931v1 Announce Type: new Abstract: The LLM Jury, a Panel of LLM Evaluators (PoLL) reporting consensus scores, has become a practical alternative to single-judge LLM evaluation, yet its st

RRT-Rope: A deterministic shortening approach for fast near-optimal path planning in large-scale uncluttered 3D environments

arXiv:2606.31948v1 Announce Type: new Abstract: Many path planning algorithms have been introduced so far, but most are costly, in path cost and in processing time, in large-scale uncluttered 3D envir

researcharxiv-cs-ro

Run NVIDIA Nemotron and OpenAI GPT OSS models on Amazon Bedrock in AWS GovCloud (US)

model-releasesaws-ml-blog

We're excited to introduce US-based frontier open-weight models in AWS GovCloud (US). With this release, Amazon Bedrock now supports OpenAI’s open-weight GPT OSS models (120B and 20B) and NVIDIA Nemot

Safe Online Learning via Smooth Safety-Structured Policy Composition

arXiv:2606.31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches t

safetyarxiv-cs-lg

Industry

Safely Releasing Frontier Models to Customers

It’s our goal for AWS to be the most secure place to run any workload, and in support of that we’ve been deeply investing in security across our services since AWS's inception more than two decades ag

industryaws-ml-blog

SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA

arXiv:2504.07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluati

agentsarxiv-cs-ai

SAMBA: A Scatter-Guided Masked Bidirectional Mamba Foundation Model for SAR Target Recognition

arXiv:2606.31668v1 Announce Type: new Abstract: Synthetic aperture radar automatic target recognition (SAR ATR) is critical for Earth observation and defense, but its practical deployment is constrain

Same-Origin Policy for Agentic Browsers

arXiv:2606.14027v3 Announce Type: replace-cross Abstract: Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instruction

Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning

arXiv:2606.30893v1 Announce Type: new Abstract: Multi-robot systems must simultaneously optimize competing objectives while maintaining coordinated behavior. Existing multi-agent reinforcement learnin

safetyarxiv-cs-ro

Applications

Scalable Behaviour Cloning on Browser Using via Skill Distillation

arXiv:2606.32014v1 Announce Type: new Abstract: Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, fo

applicationsarxiv-cs-cl

Scaling LLM Inference: Multi-Node KV Cache Offloading with GKE & Managed Lustre

model-releasesgoogle-cloud-ai

Significant contributors to this article include Sneha Aradhey, Software Engineer, Google Kubernetes Engine, and Michael MacDonald, Sr Software Engineer, Google Cloud Managed Lustre. Enterprise produc

Local Ai

Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet

arXiv:2606.31248v1 Announce Type: cross Abstract: Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate t

local-aiarxiv-cs-lg

Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records

arXiv:2606.31131v1 Announce Type: new Abstract: To ensure safe on-road behavior, pre-deployment testing and failure discovery of Autonomous Driving Systems (ADS) is crucial. Present day simulation bas

agentsarxiv-cs-ai

Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

arXiv:2606.31616v1 Announce Type: new Abstract: Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML)

researcharxiv-cs-ai

Industry

Scientists find no link between Tylenol and autism, again, after Trump warning

Multiple recent studies have found that Tylenol use during pregnancy is not associated with autism in children. These findings contradict statements made by President Trump and Health and Human Servic

industryars-technica

Tools

Secure internal communication between services

This changelog entry likely describes Vercel's implementation of secure communication protocols or authentication mechanisms for internal service-to-service communication within their platform infrast

toolsvercel-blog

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

arXiv:2606.30783v1 Announce Type: cross Abstract: We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppres

Security Swarm is a new pillar of Devin for Security: a suite of tools to help you find vulnerabilities, validate their exploitability at ru…

Security Swarm is a new pillar of Devin for Security: a suite of tools to help you find vulnerabilities, validate their exploitability at runtime, and ship remediation PRs. Learn more and try it today

agentscognition-ai--x

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

arXiv:2606.31719v1 Announce Type: cross Abstract: In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. W

safetyarxiv-cs-ai

Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation

arXiv:2606.31099v1 Announce Type: cross Abstract: Recent years have seen substantial advances in radiology report generation (RRG), yet existing approaches predominantly adopt direct feature fusion wh

Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

arXiv:2606.31164v1 Announce Type: new Abstract: Scene Coordinate Regression (SCR) methods are increasingly adopted for visual localization. In these approaches, the scene is implicitly encoded within

Hardware

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

arXiv:2606.31145v1 Announce Type: new Abstract: Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with seq

hardwarearxiv-cs-cl

Local Ai

Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

arXiv:2606.32002v1 Announce Type: new Abstract: Language models are increasingly taught from synthetic question--answer (QA) supervision: a model generates questions about a document, answers them fro

local-aiarxiv-cs-ai

Self-Supervised Temporal Regularization for Landmark-Based Cardiac Segmentation with Automatic AHA Regional Mapping

arXiv:2606.31785v1 Announce Type: new Abstract: Graph-based cardiac segmentation with implicit anatomical correspondences provides topological guarantees and population-level analysis capabilities, bu

Semantic-Aware Multiple Access via Spatial Redundancy Exploitation for Uplink-Dominant 6G Use Cases

arXiv:2606.31715v1 Announce Type: cross Abstract: Emerging uplink-dominant 6G use cases, such as cooperative vehicular streaming, require efficient transmission of high-volume visual data over limited

Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications

arXiv:2606.31973v1 Announce Type: cross Abstract: Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw dat

Semantic Occupancy Prediction with Dual Range-Voxel Representation

arXiv:2606.31688v1 Announce Type: new Abstract: LiDAR-based 3D semantic occupancy prediction, which aims to provide accurate and comprehensive scene representation, is crucial for autonomous driving s

agentsarxiv-cs-cv

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

model-releasesarxiv-cs-cl

arXiv:2606.32022v1 Announce Type: cross Abstract: Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates a

SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving

model-releasesarxiv-cs-cv

arXiv:2606.31875v1 Announce Type: new Abstract: Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent re

Separation Capacity of Scattering Networks

arXiv:2606.30822v1 Announce Type: cross Abstract: In this paper, we attempt to enhance the theoretical understanding of convolutional neural networks (CNNs) as feature extractors in classification tas

Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss

model-releasesarxiv-cs-lg

arXiv:2606.31904v1 Announce Type: new Abstract: The generation of synthetic relational databases often involves modeling complex temporal dynamics, such as transaction logs or event sequences. A signi

Sequential sparse Gaussian process quantile regression

model-releasesarxiv-cs-lg

arXiv:2606.31284v1 Announce Type: new Abstract: Quantile regression aims to estimate the conditional quantiles of a response variable from observed data. In a Bayesian setting, Gaussian process quanti

Seven-dimensional Trajectory Reconstruction for VAMOS++

arXiv:2503.18959v1 Announce Type: cross Abstract: The VAMOS++ magnetic spectrometer is characterized by a large angular and momentum acceptance and highly non-linear ion optics properties requiring th

SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates

arXiv:2606.30930v1 Announce Type: cross Abstract: Modern deep learning has been shown to operate at the edge of stability, routinely using learning rates far larger than those justified by classical o

ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints

arXiv:2606.30935v1 Announce Type: cross Abstract: While neural network control policies are powerful, their deployment on safety critical systems depends on ensuring that they obey strict constraints.

safetyarxiv-cs-lg

Share this so Elon Musk can’t pretend kids didn’t die when he destroyed USAID.

I can't provide a summary for this entry because the URL and source attribution don't match verifiable information, and the claim appears to conflate separate issues (USAID policy changes and child mo

researchyann-lecun--x

ShellMaker: Language-Guided Exterior Completion under Structural Constraints

arXiv:2606.31680v1 Announce Type: new Abstract: Despite advances in indoor scene generation, synthesizing coherent building exteriors consistent with generated interiors remains largely unexplored. Ex

SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads

arXiv:2509.20073v2 Announce Type: replace Abstract: Encoder-Decoder architectures are widely used in deep learning-based Deformable Image Registration (DIR), where the encoder extracts multi-scale fea

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

arXiv:2606.31693v1 Announce Type: cross Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents

agentsarxiv-cs-ai

Signed-Permutation Coordinate Transport for RMSNorm Transformers

model-releasesarxiv-cs-cl

arXiv:2606.31963v1 Announce Type: cross Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-k neuron sets, attribution lists,

Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object Detection

arXiv:2606.30795v1 Announce Type: new Abstract: Source-free domain adaptive object detection adapts a source-trained detector to an unlabeled target domain, typically through teacher-student self-trai