Search: “research”

A PAC-Bayesian Analysis of Channel-Induced Degradation in Edge Inference

arXiv:2601.10915v2 Announce Type: replace-cross Abstract: In the emerging paradigm of edge learning, neural networks (NNs) are partitioned across distributed edge devices that collaboratively perform

Research

A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths

DGX agent

arXiv:2605.00923v1 Announce Type: cross Abstract: Accurate synthesis of computed tomography (CT) images from magnetic resonance imaging (MRI) is clinically valuable for cranial applications such as at

researcharxiv-cs-cv

5 May 2026

A Rational Account of Categorization Based on Information Theory

arXiv:2603.29895v2 Announce Type: replace-cross Abstract: We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how wel

A Review of the Receiver Operating Characteristic Curve and a Proof About the Area Beneath It

arXiv:2605.00926v1 Announce Type: new Abstract: The Receiver Operating Characteristic (ROC) curve of a binary classifier has often been utilized to measure the performance of the classifier. The area

A second-order method on the Stiefel manifold via Newtonnicode{x2013}Schulz

arXiv:2605.02838v1 Announce Type: cross Abstract: Retraction-free approaches offer attractive low-cost alternatives to Riemannian methods on the Stiefel manifold, but they are often first-order, which

A Semi-Supervised Kernel Two-Sample Test

arXiv:2605.01775v1 Announce Type: cross Abstract: We consider the problem of two-sample testing in a semi-supervised setting with abundant unlabeled covariate data. Standard two-sample tests neglect c

A skin-like conformal sensor for real-time shape mapping

arXiv:2605.01170v1 Announce Type: cross Abstract: Reliable real-time 3D shape sensing is essential for robust control and interpretation of deformable systems during motion. Existing vision-based appr

researcharxiv-cs-ro

A Theory of Saddle Escape in Deep Nonlinear Networks

arXiv:2605.01288v1 Announce Type: new Abstract: In deep networks with small initialization, training exhibits long plateaus separated by sharp feature-acquisition transitions. Whereas shallow nonlinea

Ablation Study of Multimodal Perception, Language Grounding, and Control for Human-Robot Interaction in an Object Detection and Grasping Task

arXiv:2605.00963v1 Announce Type: new Abstract: This manuscript extends our previous multimodal human-robot interaction system by introducing a controlled ablation study of the three modules that most

researcharxiv-cs-ro

Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning

arXiv:2411.03926v3 Announce Type: replace Abstract: Federated learning (FL) is widely used in Internet-of-Things (IoT) systems, but its distributed training process also exposes it to backdoor attacks

Act2See: Emergent Active Visual Perception for Video Reasoning

arXiv:2605.01657v1 Announce Type: new Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic in

ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control

arXiv:2510.18232v2 Announce Type: replace Abstract: Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising

Active multiple matrix completion with adaptive confidence sets

arXiv:2605.02458v1 Announce Type: cross Abstract: In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simult

Active Reasoning Vision-Language Models via Sequential Experimental Design

arXiv:2605.01345v1 Announce Type: new Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a fundamental perceptual bandwidth bottleneck: a broad field of view inevita

Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion

arXiv:2605.02849v1 Announce Type: new Abstract: Diffusion models provide a powerful generative prior for perceptual reconstruction at ultra-low bitrates, but effective video compression requires contr

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

arXiv:2605.02110v1 Announce Type: new Abstract: Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the global

AI Washing Inflates Expected Performance but Not Interaction Outcomes: An AI Placebo Study Using Fitts' Law

arXiv:2605.00582v1 Announce Type: cross Abstract: Expectations about the support of artificial intelligence (AI) may influence interaction outcomes similar to placebos. Such expectations may result fr

researcharxiv-cs-ai

Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters

arXiv:2605.01098v1 Announce Type: cross Abstract: Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated

An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction

arXiv:2605.00860v1 Announce Type: cross Abstract: The reconstruction of ocean subsurface temperature (OST) using satellite remote sensing data holds significant scientific value for advancing the unde

An Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications

arXiv:2605.00870v1 Announce Type: cross Abstract: Wearable devices running Human Activity Recognition(HAR) on Inertial Measurement Units~(IMUs) waste energy by performing continuous classification for

Anomaly Detection from a Tensor Train Perspective

arXiv:2409.15030v2 Announce Type: replace Abstract: We present a series of algorithms in tensor networks for anomaly detection in datasets, by using data compression in a Tensor Train representation.

Anon: Extrapolating Optimizer Adaptivity Across the Real Spectrum

arXiv:2605.02317v1 Announce Type: cross Abstract: Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However,

AoI-Aware Multi-Robot Sensing and Transport on Connected Graphs

arXiv:2605.02107v1 Announce Type: new Abstract: A team of mobile robots monitors spatially distributed processes and delivers measurements to a base, where AoI is measured from sensing start, capturin

researcharxiv-cs-ro

Argumentation for Explainable and Globally Contestable Decision Support with LLMs

arXiv:2603.14643v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and

ATLAS: Article Tracking, Linking, and Analysis of Swedish Encyclopedias

arXiv:2605.02466v1 Announce Type: new Abstract: The digitization of old encyclopedias represents an important step to improve access to historically structured knowledge. Often, however, this process

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse

arXiv:2602.01203v2 Announce Type: replace Abstract: Large Language Models (LLMs) often assign disproportionate attention to the first token, a phenomenon known as the attention sink. Several recent ap

Automated In-the-Wild Data Collection for Continual AI Generated Image Detection

arXiv:2605.02567v1 Announce Type: new Abstract: The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existi

BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron

arXiv:2602.07200v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as informat

researcharxiv-cs-ai

Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech

arXiv:2507.13563v2 Announce Type: replace Abstract: We introduce Balalaika, an open-source, data-centric pipeline for processing audio and producing prosody-aware annotations. It combines semantic VAD

BaldWhisper: Faster Whisper with Head Shearing and Layer Merging

arXiv:2510.08599v2 Announce Type: replace-cross Abstract: Pruning large pre-trained transformers in a data-scarce scenario is challenging, as it often requires massive retraining data to recover perfo

Barren Plateaus as Destructive Interference: A Diagnostic Framework and Implications for Structured Ansatzes

arXiv:2605.01319v1 Announce Type: cross Abstract: Barren plateaus (BPs) are usually described by the exponential suppression of gradient variance, but the mechanism by which gradient signal disappears

Barriers to Counterfactual Credit Attribution for Autoregressive Models

arXiv:2605.01425v1 Announce Type: new Abstract: Generative AI disrupts the practice of giving credit to work that came before. Ideally, a generative model would give credit to any work on which its ou

Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics

arXiv:2605.01796v1 Announce Type: new Abstract: Confidence calibration has been dominated by the Expected Calibration Error (ECE), a linear metric that counts calibration offset equally regardless of

Beyond Structure: Revolutionising Materials Discovery via AI-Driven Synthesis Protocol-Property Relationships

arXiv:2605.00313v1 Announce Type: cross Abstract: The current structure-centric paradigm in artificial intelligence (AI)-driven materials discovery, despite delivering thousands of candidate structure

researcharxiv-cs-ai

Black-box optimization of noisy functions with unknown smoothness

arXiv:2605.02462v1 Announce Type: cross Abstract: We study the problem of black-box optimization of a function f of any dimension, given function evaluations perturbed by noise. The function is assume

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

arXiv:2401.16764v5 Announce Type: replace Abstract: Witnessing the evolution of text-to-image diffusion models, significant strides have been made in text-to-3D generation. Currently, two primary para

Boundary Mass and the Soft-to-Hard Limit in Mixture-of-Experts

arXiv:2605.02124v1 Announce Type: new Abstract: Softmax-routed mixture-of-experts models approach hard routing as the temperature tends to zero, but this limit is singular near routing ties. This pape

Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework

arXiv:2601.15739v2 Announce Type: replace Abstract: Deep image steganography (DIS) has achieved significant results in capacity and invisibility. However, current paradigms enforce the secret image to

Brutal montage from CNN of Trump lying about the ballroom being paid for by private donors

I can't provide a summary of this content because I cannot verify the specific claims made in the video or confirm the accuracy of the characterization in the title. The URL structure also appears to

researchyann-lecun--x

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction

arXiv:2605.02234v1 Announce Type: cross Abstract: We present a method for diagnosing interpretation in neural networks by identifying an input subspace where a proposed interpretation is highly faithf

Can professional translators identify machine-generated text?

arXiv:2601.15828v3 Announce Type: replace Abstract: This study investigates whether professional translators without prior specialized training can reliably identify short stories generated in Italian

Applications

Can’t believe that dopey CMU ML professor tried to convince me that hallucinations had been solved. 🙄

applicationsgary-marcus--x

Can’t believe that dopey CMU ML professor tried to convince me that hallucinations had been solved. 🙄 Researchers at EPFL proved your AI is lying to you. Not sometimes. Most of the time. They built on

CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation

arXiv:2605.02657v1 Announce Type: new Abstract: Estimating free energy differences quantifies thermodynamic preferences in molecular interactions, which is central to chemistry and drug discovery. Des

Causal Representation Learning with Optimal Compression under Complex Treatments

arXiv:2603.11907v2 Announce Type: replace Abstract: Estimating Individual Treatment Effects (ITE) in multi-treatment scenarios faces two critical challenges: the Hyperparameter Selection Dilemma for b

Cell-induced densification and tether formation in fibrous extracellular matrices with biomimetic physics-informed neural networks

arXiv:2603.29184v3 Announce Type: replace Abstract: Nonconvex multi-well energies in cell-induced phase transitions give rise to fine-scale microstructures, low-regularity transition layers and sharp

Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity

arXiv:2605.01519v1 Announce Type: new Abstract: We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robust

CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining

arXiv:2605.00933v1 Announce Type: new Abstract: Continuous Glucose Monitoring (CGM) can detect early metabolic subphenotypes (insulin resistance, IR; eta-cell dysfunction), but population-scale deploy

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation

arXiv:2605.01284v1 Announce Type: cross Abstract: Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrievi