Search: “papers”

Findings of the Counter Turing Test: AI-Generated Image Detection

arXiv:2605.20787v1 Announce Type: new Abstract: The rapid advancements in generative AI technologies, such as Stable Diffusion, DALL-E, and Midjourney, have significantly transformed the creation of s

applicationsarxiv-cs-cv

Findings of the Counter Turing Test: AI-Generated Text Detection

DGX agent

arXiv:2605.20761v1 Announce Type: new Abstract: The rapid proliferation of AI-generated text has introduced significant challenges in maintaining the integrity of digital content. Advanced generative

model-releasesarxiv-cs-cl

21 May 2026

Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models

arXiv:2605.20950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existin

researcharxiv-cs-cv

Gated DeltaNet has been one of my favorite 'hybrid attention' newcomers in the good old transformer stack. Excited to see Gated DeltaNet-2. …

researchsebastian-raschka--x

Gated DeltaNet has been one of my favorite 'hybrid attention' newcomers in the good old transformer stack. Excited to see Gated DeltaNet-2. Adding it to my reading stack. In the meantime, I have a pri

Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification

arXiv:2605.20248v1 Announce Type: new Abstract: In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classificat

GSA-YOLO: A High-Efficiency Framework via Structured Sparsity and Adaptive Knowledge Distillation for Real-Time X-ray Security Inspection

arXiv:2605.20669v1 Announce Type: new Abstract: X-ray security inspection requires accurate real-time detection of prohibited items, but existing models often struggle to balance the challenges of sev

researcharxiv-cs-cv

Tutorials

Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation

arXiv:2605.20600v1 Announce Type: new Abstract: Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching

tutorialsarxiv-cs-cv

Agents

HITL-D: Human In The Loop Diffusion Assisted Shared Control

arXiv:2605.21460v1 Announce Type: new Abstract: Autonomous manipulation systems have achieved remarkable capabilities, yet the integration of human expertise with diffusion-based policies in shared co

agentsarxiv-cs-ro

How Open Must Language Models be to Enable Reliable Scientific Inference?

arXiv:2603.26539v2 Announce Type: replace Abstract: How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this pa

researcharxiv-cs-cl

Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation

model-releasesarxiv-cs-cv

arXiv:2605.21309v1 Announce Type: new Abstract: Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental repre

Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction

arXiv:2605.21107v1 Announce Type: new Abstract: We consider Constrained Online Convex Optimization (COCO) with adversarially chosen constraints. At each round, the learner chooses an action before obs

Intent-First Aerial V2V for Tactical Coordination and Separation: Protocol and Performance Under Density and Disturbance

arXiv:2605.20595v1 Announce Type: new Abstract: Dense low-altitude aerial operations require more than pre-flight route coordination and last-resort collision avoidance. Once aircraft are airborne, di

local-aiarxiv-cs-ro

Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

arXiv:2605.21475v1 Announce Type: new Abstract: Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational

applicationsarxiv-cs-lg

Tutorials

Latent Process Generator Matching

arXiv:2605.20547v1 Announce Type: new Abstract: Many recent flow-matching and diffusion-style generative models rely on auxiliary stochastic dynamics during training: a richer process is simulated to

tutorialsarxiv-cs-lg

Latent Space Guided Scenario Sampling for Multimodal Segmentation Under Missing Modalities

arXiv:2605.20372v1 Announce Type: new Abstract: Multimodal semantic segmentation benefits remote sensing analysis by combining complementary information from different sensor modalities. In real-world

applicationsarxiv-cs-cv

Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning

arXiv:2605.21160v1 Announce Type: new Abstract: The discovery of first integrals is of fundamental scientific importance for understanding conservation laws in dynamical systems. However, existing sym

Learning Robust Dexterous In-Hand Manipulation from Joint Sensors with Proprioceptive Transformer

arXiv:2605.21330v1 Announce Type: new Abstract: In-hand object manipulation is a fundamental yet challenging capability for dexterous robots. Despite significant progress in dexterous manipulation, ex

Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution

model-releasesarxiv-cs-cl

arXiv:2605.21465v1 Announce Type: new Abstract: In model-driven engineering, metamodel evolution leads to the need to adapt corresponding grammars to maintain consistency, which typically requires ted

Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models

arXiv:2605.21123v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are co

safetyarxiv-cs-cv

LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control

arXiv:2605.21086v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly integrated into in-vehicle conversational systems, identifying the optimal model remains challenging

local-aiarxiv-cs-cl

Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs

arXiv:2605.21446v1 Announce Type: new Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world

Measuring and mitigating overreliance to build human-compatible AI

arXiv:2509.08010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) distinguish themselves from previous technologies by functioning as collaborative ``thought partners,'' capable o

applicationsarxiv-cs-cl

Mercer Large-Scale Kernel Machines from Ridge Function Perspective

arXiv:2307.11925v3 Announce Type: replace Abstract: To present Mercer large-scale kernel machines from a ridge function perspective, we recall the results by Lin and Pinkus from {it Fundamentality of

Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation

arXiv:2605.20894v1 Announce Type: new Abstract: Mobile imitation learning on portable demonstration interfaces faces two coupled bottlenecks: locomotion-contaminated action labels and inference-induce

Agents

Multi-agent Collaboration with State Management

arXiv:2605.20563v1 Announce Type: cross Abstract: Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase conc

agentsarxiv-cs-cl

Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty

arXiv:2605.20255v1 Announce Type: new Abstract: Simulation-based testing of self-driving cars (SDCs) typically relies on scripted or simplified pedestrian models that do not capture the heterogeneity

Multi-needle Localization for Pelvic Seed Implant Brachytherapy based on Tip-handle Detection and Matching

arXiv:2509.17931v2 Announce Type: replace Abstract: Accurate multi-needle localization in intraoperative CT images is crucial for optimizing seed placement in pelvic seed implant brachytherapy. Howeve

local-aiarxiv-cs-cv

Multimodal Fusion for Sim2real Transfer in Visual Reinforcement Learning

arXiv:2507.09180v4 Announce Type: replace Abstract: Depth information is robust to scene appearance variations and inherently carries 3D spatial details. Thus, a visual backbone based on the vision tr

applicationsarxiv-cs-cv

Tutorials

On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

arXiv:2605.21388v1 Announce Type: new Abstract: Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largel

tutorialsarxiv-cs-lg

One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration

arXiv:2605.21484v1 Announce Type: new Abstract: Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass th

local-aiarxiv-cs-cv

Online 3D Multi-Camera Perception through Robust 2D Tracking and Depth-based Late Aggregation

arXiv:2509.09946v2 Announce Type: replace Abstract: Multi-Target Multi-Camera Tracking (MTMC) is an essential computer vision task for automating large-scale surveillance. With camera calibration and

local-aiarxiv-cs-cv

Online Conformal Prediction with Corrupted Feedback

arXiv:2605.20515v1 Announce Type: new Abstract: Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Onli

applicationsarxiv-cs-lg

PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction

arXiv:2605.21414v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-languag

safetyarxiv-cs-cv

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems

arXiv:2603.10726v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previousl

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

arXiv:2605.21072v1 Announce Type: new Abstract: Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time inte

researcharxiv-cs-cv

Q-SpiRL: Quantum Spiking Reinforcement Learning for Adaptive Robot Navigation

arXiv:2605.20801v1 Announce Type: new Abstract: Adaptive robot navigation in dynamic environments requires policies that can reach the target reliably while producing efficient and stable trajectories

Q-SYNTH: Hybrid Quantum-Classical Adversarial Augmentation for Imbalanced Fraud Detection

arXiv:2605.21164v1 Announce Type: new Abstract: Credit card fraud detection is fundamentally challenged by extreme class imbalance, where fraudulent transactions are rare yet operationally critical. T

Quadratic Characterizations for Reachability Analysis of Neural Networks

arXiv:2605.20482v1 Announce Type: new Abstract: Quadratic constraints (QCs) are widely used to characterize nonlinearities and uncertainties, but generic analytical characterizations can be conservati

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate

model-releasesarxiv-cs-lg

arXiv:2605.21486v1 Announce Type: new Abstract: Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large lang

QwenSafe: Multimodal Content Rating Description Identification via Preference-Aligned VLMs

model-releasesarxiv-cs-cv

arXiv:2605.20584v1 Announce Type: new Abstract: Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or res

rePIRL: Learn PRM with Inverse RL for LLM Reasoning

arXiv:2602.07832v2 Announce Type: replace Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In

Rethinking Cross-Layer Information Routing in Diffusion Transformers

arXiv:2605.20708v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization,

safetyarxiv-cs-cv

Retrospective Sparse Attention for Efficient Long-Context Generation

arXiv:2508.09001v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, i

researcharxiv-cs-cl

Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework

arXiv:2605.20721v1 Announce Type: new Abstract: Learning from implicit feedback in recommender systems is fundamentally challenged by pervasive label noise. While conventional denoising approaches oft

Safety-Critical Control for Smoothed Implicit Contact Dynamics

model-releasesarxiv-cs-ro

arXiv:2605.21138v1 Announce Type: new Abstract: Smoothed implicit contact dynamics enables gradient-based planning and control for contact-rich tasks without predefined mode sequences. However, safety

Seeing Through Fog: Towards Fog-Invariant Action Recognition

model-releasesarxiv-cs-cv

arXiv:2605.20645v1 Announce Type: new Abstract: Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather

Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs

arXiv:2605.20191v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have recently attracted much attention for their ability to simulate human behavior and generate text that reflects

safetyarxiv-cs-cl

Testing Support Size More Efficiently Than Learning Histograms

arXiv:2410.18915v4 Announce Type: replace-cross Abstract: Consider two problems about an unknown probability distribution p: 1. How many samples from p are required to test if p is supported on n elem