Search: “models”

Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation

arXiv:2606.15837v2 Announce Type: replace Abstract: Deep neural networks (DNNs) frequently fail to generalize to out-of-distribution (OOD) medical images because of variations in scanners and acquisit

Safety

Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection

DGX agent

arXiv:2606.30951v1 Announce Type: cross Abstract: Micro-ultrasound (muUS) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspici

safetyarxiv-cs-ai

1 Jul 2026

LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music

arXiv:2606.31158v1 Announce Type: cross Abstract: The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid

Local Ai

Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair

arXiv:2606.30963v1 Announce Type: cross Abstract: Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeti

local-aiarxiv-cs-ai

Machine Learning-based Feedback Linearization Control of Quadrotor Subject to Unmodeled Dynamics

arXiv:2606.31199v1 Announce Type: cross Abstract: The control of agile quadrotors in dynamic and uncertain environments remains an open area of investigation to this day, particularly when the complet

Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment

arXiv:2606.30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk

On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting

arXiv:2601.13913v2 Announce Type: replace Abstract: Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3

PRISM: Latent Composition Consistency for Single-Image Reflection Removal

arXiv:2606.31513v1 Announce Type: new Abstract: Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections -- a severely ill-posed problem.

Probabilistic Inversion with Flow Matching

arXiv:2606.31288v1 Announce Type: new Abstract: We demonstrate the application of Flow Matching, a technique originating from generative Artificial Intelligence, to probabilistic inversion in geophysi

RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection

arXiv:2604.06687v2 Announce Type: replace Abstract: Multimodal fake news video detection is a crucial research direction for maintaining the credibility of online information. Existing studies primari

Rhythm-Structured Predictive Learning for Remote Photoplethysmography

arXiv:2606.31736v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) estimates physiological signals from facial videos by analyzing subtle pulse induced skin color variations. Despite r

safetyarxiv-cs-cv

Spatial Reasoning via Modality Switching Between Language and Symbolic Representation

arXiv:2606.31285v1 Announce Type: new Abstract: Human reasoning is inherently multimodal: when problems become difficult, we rarely think in words alone. We often externalize our reasoning by sketchin

SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views

arXiv:2509.17246v2 Announce Type: replace Abstract: We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth pose

Stealthy Multi-Task Adversarial Attacks

arXiv:2411.17936v2 Announce Type: replace-cross Abstract: Deep neural networks are highly vulnerable to adversarial perturbations, raising serious safety concerns in the real-world systems. While prio

safetyarxiv-cs-cv

Tutorials

Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance

arXiv:2506.20995v4 Announce Type: replace Abstract: We propose a step-by-step video-to-audio (V2A) generation method that provides finer control over the generation process and more realistic audio sy

tutorialsarxiv-cs-cv

Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking

arXiv:2606.30754v1 Announce Type: new Abstract: Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint re

The Quadruped Soft Tail: Compliant Grasping and Swabbing for Contamination Surveys in Harsh Environments

arXiv:2606.30900v1 Announce Type: new Abstract: Beryllium contamination surveys in radioactive areas are challenging for robots in environments cluttered with cables and electronics. To address this p

researcharxiv-cs-ro

Towards Voxel Spacing Consistency for Medical Image Segmentation

arXiv:2606.31839v1 Announce Type: new Abstract: Volumetric medical image segmentation is essential for both preoperative diagnosis and intraoperative guidance. While recent years have witnessed rapid

UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables

arXiv:2606.31242v1 Announce Type: new Abstract: With the advancement of imaging technology, ultra-high-definition images have become increasingly essential in modern visual applications. However, exis

Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing

arXiv:2606.31517v1 Announce Type: cross Abstract: Compared to supervised cross-modal hashing (CMH), unsupervised CMH reduces the reliance on manual labeling by learning binary codes from unlabeled ima

safetyarxiv-cs-cv

VertiAdaptor: Online Kinodynamics Adaptation for Vertically Challenging Terrain

arXiv:2603.06887v3 Announce Type: replace Abstract: Autonomous driving in off-road environments presents significant challenges due to the dynamic and unpredictable nature of unstructured terrain. Tra

agentsarxiv-cs-ro

When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency

arXiv:2606.30975v1 Announce Type: new Abstract: Adaptive agents are usually judged by what they do, but an agent can appear stable while the internal effort required to keep it stable is increasing. T

agentsarxiv-cs-ai

you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, …

you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, proposed by @a1zhang from MIT, help: instead of working mode

agentsharrison-chase--x

A Deep Multiscale Neural Network for Accurate Neurological Disorder Detection from MRI Scans and Real-Time Web Deployment

arXiv:2606.29106v1 Announce Type: cross Abstract: Neurological disorders involve diverse pathologies of the brain and nervous system, making early and accurate detection essential. While many deep CNN

A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP

arXiv:2508.02923v3 Announce Type: replace Abstract: Maximum A Posteriori (MAP) estimation is a cornerstone framework for blind inverse problems, where an image and a forward operator are jointly estim

A Unified Framework for Multi-Contact Path Planning in the Rolling Robot Systems

arXiv:2606.29065v1 Announce Type: new Abstract: Rolling motion planning is challenging because rolling contact imposes nonholonomic constraints and the configuration evolves on a curved manifold. The

researcharxiv-cs-ro

AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills

arXiv:2606.29999v1 Announce Type: new Abstract: Designing an algorithm from a natural-language problem statement requires identifying the problem structure, reading constraints, choosing a suitable pa

An Integrated Machine Learning and Hierarchical Variance Decomposition Pipeline for Student Performance Prediction and Metacognitive Calibration on Multi-Signal Telemetry

arXiv:2606.28881v1 Announce Type: cross Abstract: Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems. Prior r

safetyarxiv-cs-ai

Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-View Matching

arXiv:2606.28474v1 Announce Type: cross Abstract: Accurate correspondence matching across multiple angiographic views is the prerequisite for 3D coronary reconstruction and interventional guidance. Ho

Applications

Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data

arXiv:2606.29167v1 Announce Type: new Abstract: Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments. These environments pre

applicationsarxiv-cs-cv

ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving

arXiv:2606.29286v1 Announce Type: new Abstract: Synthetic data mitigates the data scarcity problem in autonomous driving perception. However, the synthetic-to-real gap leads to performance degradation

agentsarxiv-cs-cv

Applications

Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients

arXiv:2606.28345v1 Announce Type: cross Abstract: LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status,

applicationsarxiv-cs-ai

Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics

arXiv:2606.29620v1 Announce Type: cross Abstract: This work presents a new bidirectional autoregressive latent diffusion approach for predicting the evolution of multiple fields (mass density, pressur

Brownian Bridge Diffusion-Based Joint Channel Estimation and Data Detection for Jamming-Resilient Receivers

arXiv:2606.28778v1 Announce Type: cross Abstract: In next-generation wireless networks, the growing density of devices and limited spectrum resources pose severe jamming challenges to fragile legitima

CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval

arXiv:2606.28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.g., synthetic queries or summaries generated from c

safetyarxiv-cs-ai

Can LLMs Rank? A Tale of Triads and Triage

arXiv:2606.30412v1 Announce Type: cross Abstract: From housing allocation for households experiencing homelessness to triage in emergency departments, LLMs are increasingly being considered as judges

Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent Frameworks

arXiv:2606.28679v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, ye

agentsarxiv-cs-ai

Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

arXiv:2606.30246v1 Announce Type: new Abstract: Existing autonomous research agents can support parts of the research process, but most systems still treat research as either an isolated assistant tas

agentsarxiv-cs-ai

CLIMP: Contrastive Language-Image Mamba Pretraining

arXiv:2601.06891v2 Announce Type: replace Abstract: Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and

Tutorials

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

arXiv:2606.28953v1 Announce Type: cross Abstract: Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a

tutorialsarxiv-cs-ai

Hardware

ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services

arXiv:2606.28361v1 Announce Type: cross Abstract: Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative r

hardwarearxiv-cs-ai

CouCE: A Unified Causal Framework for Debiased Deep Metric Learning

arXiv:2606.30365v1 Announce Type: new Abstract: Deep Metric Learning (DML) often struggles with zero-shot generalization because standard objectives inherently capture what co-occurs rather than what

Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet

arXiv:2606.29324v1 Announce Type: new Abstract: Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive me

Local Ai

Depth-Staggered Fibonacci Spacing for Sparse Attention: Static Schedules Beat Learned Dilation and Extrapolate Where Dense Attention Fails

arXiv:2606.28560v1 Announce Type: new Abstract: We study sparse self-attention in which each query attends to a dense local window plus a set of Fibonacci-spaced offsets, with a per-layer scalar alpha

local-aiarxiv-cs-cl

Applications

Differentiable Physics-Informed Adaptive Koopman Control for Stable Flight under Unknown Disturbances

arXiv:2506.08319v2 Announce Type: replace-cross Abstract: Uncertainties and disturbances in robotic systems, such as aerodynamic forces, are fundamentally outcomes of physical interactions with the en

applicationsarxiv-cs-ro

DOPD: Dual On-policy Distillation

arXiv:2606.30626v1 Announce Type: new Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish hi

safetyarxiv-cs-ai

Dynamic High-frequency Convolution for Infrared Small Target Detection

arXiv:2602.02969v2 Announce Type: replace Abstract: Infrared small targets are typically tiny and locally salient, which belong to high-frequency components (HFCs) in images. Single-frame infrared sma

EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics

arXiv:2606.30557v1 Announce Type: new Abstract: DiT video generation is latency-intensive due to iterative full-frame denoising, while prior cloud-edge methods largely rely on static inter-step decoup