Search: “concepts”

Steering Vision-Language Models with Joint Sparse Autoencoders

arXiv:2606.25657v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representat

TheoremGraph: Bridging Formal and Informal Mathematics

DGX agent

arXiv:2606.25363v1 Announce Type: cross Abstract: Mathematical knowledge is organized around statements and their dependencies, but this structure is exposed unevenly: informal papers cite mostly at t

agentsarxiv-cs-ai

25 Jun 2026

Towards a Bathroom-Centered Human-Building Digital Twin Framework for Indoor Safety Analysis

arXiv:2606.23292v2 Announce Type: replace-cross Abstract: Bathroom use is a critical safety challenge for older adults because wet surfaces, constrained layouts, limited support, and frequent posture

safetyarxiv-cs-ai

Two-dimensional Hyperbolic RNN Neural Quantum State

model-releasesarxiv-cs-lg

arXiv:2606.25600v1 Announce Type: cross Abstract: In the first part of this work, we construct the first type of two-dimensional (2D) hyperbolic neural quantum state (NQS) in the form of the Lorentz 2

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

arXiv:2606.25034v1 Announce Type: new Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversaria

safetyarxiv-cs-cv

Local Ai

ActiveScope: Actively Seeking and Correcting Perception for MLLMs

arXiv:2606.24292v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive vision-language understanding, yet still struggle with fine-grained perception in

local-aiarxiv-cs-cv

Explaining Failures of Cyber-Physical Systems with Actual Causality

arXiv:2606.24546v1 Announce Type: new Abstract: Modern autonomous Cyber-Physical Systems (CPSs), such as self-driving cars, face increasingly complex demands, and yet are expected to act reliably. The

agentsarxiv-cs-ro

Industry

If you have a few minutes today, watch this short film. I highly recommend it. You won’t be disappointed. It’s one of the winners of AIF and…

industrycristobal-valenzuela--x

If you have a few minutes today, watch this short film. I highly recommend it. You won’t be disappointed. It’s one of the winners of AIF and a film that everyone I meet keeps mentioning. It’s mesmeriz

KANLib -- A Modular, Extensible and Fast Kolmogorov-Arnold Network Implementation

model-releasesarxiv-cs-ai

arXiv:2606.17927v2 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional multilayer perceptrons by replacing linear w

LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation

arXiv:2509.17773v2 Announce Type: replace Abstract: The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring t

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation

model-releasesarxiv-cs-lg

arXiv:2506.10520v5 Announce Type: replace-cross Abstract: Graph-based multi-task learning at billion-scale presents a significant challenge, as different tasks correspond to distinct billion-scale gra

AI Agents Can Already Autonomously Perform Experimental High Energy Physics

model-releasesarxiv-cs-lg

arXiv:2603.20179v3 Announce Type: replace-cross Abstract: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipelin

An LLM-Explainable DRL Framework for Passenger-Directed Autonomous Driving

arXiv:2606.20640v1 Announce Type: cross Abstract: Autonomous vehicles offer the potential for safer and more efficient mobility, yet public trust remains limited due to the lack of transparency in the

safetyarxiv-cs-lg

Autonomous and Self-Adapting System for Synthetic Media Detection and Attribution

arXiv:2504.03615v2 Announce Type: replace Abstract: Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose s

agentsarxiv-cs-cv

Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models

arXiv:2606.21645v1 Announce Type: cross Abstract: Large language models (LLMs) can readily reproduce conventional expressions, yet their ability to model gradient frequency distributions remains under

safetyarxiv-cs-lg

Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies

arXiv:2606.23494v1 Announce Type: new Abstract: Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and

Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition

arXiv:2412.06190v2 Announce Type: replace Abstract: Benefiting from the generalization capability of CLIP, recent vision language pre-training (VLP) models have demonstrated the ability to capture a w

Decoupling the Declarative from the Procedural in Vision-Language-Action Models

arXiv:2606.21496v1 Announce Type: cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-spe

DT-GOL: Dual-Track Geometric Online Learning in Nonstationary Environment with Label Delay

arXiv:2606.22950v1 Announce Type: new Abstract: Online learning is crucial for handling complex data streams in big data applications. Recent research has begun to focus on dynamic scenarios, i.e., no

safetyarxiv-cs-lg

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

arXiv:2510.26113v2 Announce Type: replace Abstract: Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introd

Tutorials

FPAS: Frontier-Based Path Planning with Adaptive Sampling for Large-Scale Unknown Environments

arXiv:2606.22838v1 Announce Type: new Abstract: In this work, we propose Frontier-based Path Planning with Adaptive Sampling (FPAS), a novel framework designed for efficient goal-reaching in large-sca

tutorialsarxiv-cs-ro

Fusing Backdoors, Machine Learning, and Optimization for Large-Scale Parametric Mixed-Integer Programs

arXiv:2606.21440v1 Announce Type: new Abstract: Large-scale optimization problems are often solved repeatedly under similar structural conditions, leading to substantial computational overhead. This o

applicationsarxiv-cs-lg

Gradient-Descent Steps to Success over Mean Accuracy: A Paradigm Shift for ML

arXiv:2606.22053v1 Announce Type: new Abstract: Traditional evaluation of machine learning (ML) models typically focuses on achieving the maximum possible accuracy irrespective of the computational co

GTA-Net: Cooperative Game Theory for Vision-Language Alignment in Chest X-Ray Report Generation

arXiv:2606.21915v1 Announce Type: new Abstract: Automated chest X-ray report generation requires precise cross-modal grounding to ensure clinically reliable descriptions. However, existing vision-lang

safetyarxiv-cs-cv

Guide to Agentic Systems and AI Agents

This guide from Databricks covers the fundamentals of agentic systems and AI agents, including their architecture, capabilities, and how they differ from traditional AI applications. It likely explain

agentsdatabricks

HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning

arXiv:2509.22645v2 Announce Type: replace Abstract: Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-traine

Integrated cloud-based architecture for robot-robot and human-robot collaboration using ROS 2--MQTT in Mediterranean Greenhouses

arXiv:2606.22682v1 Announce Type: new Abstract: The imperative to develop more sustainable agriculture demands a transition from isolated automation toward the deployment of multi-robot systems (MRS)

applicationsarxiv-cs-ro

Interpretable machine learning of halo gas density profiles: a sensitivity analysis of cosmological hydrodynamical simulations

arXiv:2512.09021v3 Announce Type: replace-cross Abstract: Stellar and AGN-driven feedback processes affect the distribution of gas on a wide range of scales, from within galaxies well into the interga

Manipulider: A Multi-Engine Buoyancy-Controlled Robot for Thrusterless Underwater Gliding and Manipulation

arXiv:2606.21461v1 Announce Type: new Abstract: The Manipulider is a buoyancy-actuated underwater robot that enables thrusterless, glide-like locomotion and attitude-based manipulation, while providin

researcharxiv-cs-ro

MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models

arXiv:2606.21194v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains

No Reference-Free Generalization in Quantum Machine Learning

arXiv:2606.22331v1 Announce Type: cross Abstract: Quantum machine learning is often motivated by the exponentially large state space of quantum systems, but this promise leaves a basic generalization

PenduMorph: Development and Motion Analysis of Pendulum-Actuated Rolling Reconfigurable Spherical Robot with Magnetic-Coupling

arXiv:2606.22491v1 Announce Type: new Abstract: This paper presents 'PenduMorph', a wireless reconfigurable rolling spherical robot designed as a modular platform for enclosed locomotion and inter-mod

researcharxiv-cs-ro

PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs

arXiv:2606.20913v1 Announce Type: new Abstract: Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deploym

Ranking-and-Selection with Multiple Correct Answers and Non-Answerable Estimates

arXiv:2606.21889v1 Announce Type: new Abstract: We study fixed-precision ranking-and-selection in structured settings where the answer may be non-unique and where noisy estimates may temporarily admit

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

arXiv:2606.21289v1 Announce Type: new Abstract: Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistr

applicationsarxiv-cs-lg

SPiralRoll: A Novel Adjustable-Stiffness Underactuated 3-DoF Joint with Torsion Springs for Rolling Robots

arXiv:2606.22443v1 Announce Type: new Abstract: Compliant mechanisms are important in robotics because they can improve adaptability, safety, and energy efficiency while reducing hardware complexity.

safetyarxiv-cs-ro

Tutorials

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space

arXiv:2606.21705v1 Announce Type: new Abstract: Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset mor

tutorialsarxiv-cs-cv

Local Ai

SuperCond-GNN: Scalable Graph Neural Network Surrogate for Superconducting Circuit Simulations

arXiv:2606.23548v1 Announce Type: cross Abstract: This paper presents SuperCond-GNN, a graph neural network-based surrogate model for predicting the voltage distribution in high-temperature supercondu

local-aiarxiv-cs-lg

Want to get into Hermes Agent but don't know where to start? Perhaps you're not ready to invest multiple hours of listening to my voice (unt…

Want to get into Hermes Agent but don't know where to start? Perhaps you're not ready to invest multiple hours of listening to my voice (unthinkable!), so I made a quick 10 minute video to get you up

agentsnous-research--x

Industry

1/ Regardez cette courbe. C’est la fréquence du terme « white supremacy » dans la presse américaine (travaux de David Rozado). Explosion bru…

1/ Regardez cette courbe. C’est la fréquence du terme « white supremacy » dans la presse américaine (travaux de David Rozado). Explosion brutale après 2013. Pas une explosion du racisme réel. Une expl

industryelon-musk--x

21 Jun 2026

Building Social World Models with Large Language Models

model-releasesarxiv-cs-cl

arXiv:2606.11482v1 Announce Type: cross Abstract: Understanding and predicting how social beliefs evolve in response to events -- from policy changes to scientific breakthroughs -- remains a fundament

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

arXiv:2606.12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and

researcharxiv-cs-ai

Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions

arXiv:2604.25018v2 Announce Type: replace-cross Abstract: The Internet of Everything (IoE) represents an evolution of the Internet of Things (IoT) by integrating people, data, processes, and things in

applicationsarxiv-cs-ai

Learning Ordinal Response Policies in Rank-Based Stochastic Prize-Collecting Games

model-releasesarxiv-cs-ro

arXiv:2510.24515v2 Announce Type: replace Abstract: The Team Orienteering Problem (TOP) generalizes many real-world multi-agent scheduling and routing tasks that occur in autonomous mobility, aerial l

RePAIR: Predictive Self-Supervised Representation Learning in Chess

arXiv:2606.11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation lear

Semantic Segmentation of Node and Edge Diagrams for Assistive Technology

arXiv:2606.11320v1 Announce Type: new Abstract: In this paper, we present a novel set of related models for semantic segmentation of node-link diagrams. These diagrams are frequently used to represent

STEAM: Squeeze and Transform Enhanced Attention Module

arXiv:2412.09023v3 Announce Type: replace Abstract: Channel and spatial attention mechanisms introduced in earlier work enhance the representational capabilities of deep convolutional neural networks

The N-Body Problem: Parallel Execution from Single-Person Egocentric Video

arXiv:2512.11393v2 Announce Type: replace Abstract: Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we i