All entries

Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City

arXiv:2606.20980v1 Announce Type: new Abstract: As Self-Driving Cars continue to expand internationally and use multi-modal systems such as VLMs as a cognitive backbone for their Action models; how we

agentsarxiv-cs-cv

RocketPFN: Accurate Time Series Classification via In-Context Learning

DGX agent

arXiv:2606.21786v1 Announce Type: new Abstract: We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-c

researcharxiv-cs-lg

23 Jun 2026

RogueRover: Autonomous Rogue Device Localization for Incident Response

arXiv:2606.21264v1 Announce Type: new Abstract: Physically localizing unauthorized wireless devices remains a critical bottleneck in cyber-physical security operations, where rogue access points can p

agentsarxiv-cs-ro

Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation

arXiv:2606.21788v1 Announce Type: cross Abstract: Point-cloud goals provide a direct way to specify dexterous in-hand reorientation: instead of defining an object-specific pose frame or estimating 6D

RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

model-releasesarxiv-cs-lg

arXiv:2606.18774v2 Announce Type: replace Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://route

RoverDevKit: An open, physics-grounded tradespace toolkit for conceptual design of lunar micro-rovers

model-releasesarxiv-cs-ro

arXiv:2606.21755v1 Announce Type: new Abstract: Pre-Phase-A design of lunar micro-rovers is dominated by tightly coupled mobility, power, thermal, and mass trades, yet conceptual-design tooling for th

RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation

arXiv:2606.23221v1 Announce Type: new Abstract: Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. Howev

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

arXiv:2606.23344v1 Announce Type: new Abstract: Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation

arXiv:2511.20651v2 Announce Type: replace Abstract: Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key

rumors of new models being delayed

model-releasesgary-marcus--x

rumors of new models being delayed 🚨 SCOOP(s): - GPT-5.6 has been delayed and will no longer release this week. New target is ~mid-July. - DeepMind are not satisfied with the current state of 3.5 Pro

Running AI on mixed hardware for speed and affordability

This IBM Research article discusses optimizing AI inference performance and costs by leveraging mixed hardware configurations, combining different types of processors and accelerators rather than rely

researchibm-research

S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix

arXiv:2508.08048v2 Announce Type: replace Abstract: While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applicat

Safe Few-Step Generation via Velocity Editing

arXiv:2606.23267v1 Announce Type: new Abstract: Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a sma

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

arXiv:2603.05497v3 Announce Type: replace Abstract: Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around

safetyarxiv-cs-ro

SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model

arXiv:2606.20698v1 Announce Type: new Abstract: Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However,

safetyarxiv-cs-ro

SAGE: An Expert-Annotated South Asian GI Endoscopy Dataset for Multimodal Learning and Hallucination Analysis

arXiv:2606.22144v1 Announce Type: new Abstract: Gastrointestinal cancers represent a growing health burden in the South Asian region, driven largely by rapid changes in socio-economic conditions & lif

Sakana Fugu Technical Report

arXiv:2606.21228v1 Announce Type: new Abstract: The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains. T

agentsarxiv-cs-lg

Sakana Fugu Technical Report https://github.com/SakanaAI/fugu/blob/main/Fugu_technical_report.pdf Release Notes: https://sakana.ai/fugu-rele…

Sakana AI's Fugu is a technical report describing an AI model or system, likely focusing on neural architecture design or evolutionary computation methods given Sakana AI's research focus. The report

researchdavid-ha--x

SamatNext v0.2-B: An Exploratory Study of RMS-Normalized Hybrid Decoders for Curriculum Retention in Small Code Models

model-releasesarxiv-cs-lg

arXiv:2606.22248v1 Announce Type: new Abstract: Standard autoregressive Transformer decoders can often exhibit substantial forgetting under sequential fine-tuning on shifting curriculum distributions.

SARIF: Segment Anything for Robust Image Forensics

arXiv:2606.21108v1 Announce Type: new Abstract: Image forgery localization remains challenging due to diverse manipulation techniques and distribution shifts. Existing forgery localization models achi

SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding

arXiv:2606.22694v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existi

Tutorials

Scalable Bayesian Additive Models for Stellar Flare Detection via Amortized Gaussian Process Inference and Hidden Markov Models

arXiv:2606.22601v1 Announce Type: cross Abstract: Gaussian Processes (GPs) are a powerful tool for Bayesian time-series modeling, yet their cubic computational cost remains a severe barrier for applic

tutorialsarxiv-cs-lg

Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching

arXiv:2606.22630v1 Announce Type: new Abstract: Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, t

researcharxiv-cs-lg

Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation

arXiv:2606.22471v1 Announce Type: new Abstract: A key bottleneck in training generalist policies for bimanual dexterous manipulation is the lack of large-scale, high-quality datasets. Synthetic data g

researcharxiv-cs-ro

Hardware

Scalable Physics-Inspired Transformers for Spin Glasses

arXiv:2606.22984v1 Announce Type: cross Abstract: Efficient sampling of the Boltzmann distribution in frustrated spin glasses is central to statistical mechanics and combinatorial optimization. Despit

hardwarearxiv-cs-lg

Tutorials

Scalable Training of Spatially Grounded 2D Vision-Language Models for Radiology

arXiv:2606.20477v2 Announce Type: replace Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a lar

tutorialsarxiv-cs-cv

ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers

arXiv:2606.21947v1 Announce Type: new Abstract: Vision Transformers have achieved remarkable success in many fields, yet their deployment on edge devices remains challenging due to their substantial c

Scaling Diverse Language Generation for 3D Visual Grounding

arXiv:2606.20946v1 Announce Type: cross Abstract: Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for en

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

model-releasesarxiv-cs-lg

arXiv:2606.23607v1 Announce Type: new Abstract: Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods

Scaling Self-Play for End-to-End Driving

arXiv:2606.19641v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving models are typically trained on offline human-demonstration datasets that provide limited state coverage and oft

Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR

arXiv:2606.23524v1 Announce Type: new Abstract: End-to-end OCR increasingly relies on autoregressive sequence models, where the quadratic cost of Transformer attention limits efficient transcription o

Scaling up fine-grained intracranial vessel annotations in computed tomography angiography

arXiv:2606.21756v1 Announce Type: cross Abstract: In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the d

ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers

arXiv:2606.23019v1 Announce Type: new Abstract: While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computat

ScanBot: A Benchmark for Precision Robotic Surface Scanning with Industrial Laser Profilers

model-releasesarxiv-cs-ro

arXiv:2505.17295v2 Announce Type: replace Abstract: We introduce ScanBot, a benchmark for instruction-conditioned, high-precision surface scanning with robot-mounted industrial laser profilers. Unlike

Scene-agnostic ALS boresight self-calibration

arXiv:2606.23101v1 Announce Type: new Abstract: ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and

Applications

Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats

arXiv:2606.21753v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physi

applicationsarxiv-cs-cv

Hardware

SCENIC: Semantic-Conditioned Edge-Aware Neural Framework for Structured IoT Command Generation

arXiv:2606.22296v1 Announce Type: new Abstract: Edge Internet of Things (IoT) agents are often constrained by memory capacity, privacy requirements, communication latency, and recurring inference cost

hardwarearxiv-cs-lg

Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models

arXiv:2606.23567v1 Announce Type: new Abstract: Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an 'order of thought' that strongly influence

safetyarxiv-cs-lg

Schur-MI: Fast Mutual Information for Robotic Information Gathering

arXiv:2602.12346v2 Announce Type: replace Abstract: Mutual information (MI) is a principled and widely used objective for robotic information gathering (RIG), providing strong theoretical guarantees f

agentsarxiv-cs-ro

scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing

arXiv:2606.13007v2 Announce Type: replace Abstract: Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity. Howev

safetyarxiv-cs-lg

SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry

arXiv:2606.21300v1 Announce Type: new Abstract: We present SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry), a novel approach for estimating 3D geometry from extended monocular video sequen

Industry

SCOTUS ends a suit alleging Cisco aided China's Falun Gong persecution, further limiting a law used to hold corporations liable for overseas human rights abuses (Jan Wolfe/Reuters)

Jan Wolfe / Reuters: SCOTUS ends a suit alleging Cisco aided China's Falun Gong persecution, further limiting a law used to hold corporations liable for overseas human rights abuses — The U.S. Supreme

industrytechmeme

SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors

arXiv:2606.22700v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising paradigm for privacy-sensitive applicatio

Sea-Scan: High-Accuracy, ML-based Dark Vessel Detection and Localisation via Weakly Supervised DAS Monitoring

arXiv:2606.21326v1 Announce Type: cross Abstract: We present an ML-based vessel detection and localization system, trained with weak supervision from imperfect AIS labels, that achieves a 97.8% detect

researcharxiv-cs-lg

Seam-to-Graph Reconstruction for Garment Configuration Alignment

arXiv:2606.15171v2 Announce Type: replace Abstract: Seams encode rich structural information about garments but are frequently partially observable in robotic manipulation scenarios. To robustly lever

safetyarxiv-cs-ro

SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection

arXiv:2606.21138v1 Announce Type: new Abstract: AI-assisted image editing threatens trust in financial, legal, and identity records. The GenText-Forensics Challenge at ACM MM 2026 addresses this by re

Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation

arXiv:2606.19120v2 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned

SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion

arXiv:2606.22568v1 Announce Type: new Abstract: Training image generation foundation models consumes substantial resources. Previous methods have attempted to leverage semantic guidance to accelerate