research

A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

arXiv:2607.03256v1 Announce Type: new Abstract: Few-step distilled diffusion students cut text-to-image inference from ~50 to 1-8 network evaluations, but the quality gap is usually summarised by a si

Research

A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction

DGX agent

arXiv:2607.02670v1 Announce Type: new Abstract: Electroencephalography (EEG) offers a noninvasive approach for examining neurophysiological correlates of dimensional psychopathology, yet systematic ev

researcharxiv-cs-lg

7 Jul 2026

A non-invasive video-based method for individual identification of wildlife using gait dynamics

arXiv:2607.04518v1 Announce Type: new Abstract: Gait is a distinctive behavioral characteristic that enables non-invasive individual identification without requiring physical interaction with an anima

A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics

arXiv:2607.04680v1 Announce Type: new Abstract: Grain growth is governed by the reduction in grain boundary energy and exhibits well-established statistical scaling laws. Developing data-driven surrog

A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models

arXiv:2607.02782v1 Announce Type: cross Abstract: Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible e

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

arXiv:2602.02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise

A recent NYT article by @CadeMetz [1] claims that neural network distillation was first developed in 2015 by a team of Google researchers in…

A recent NYT article by @CadeMetz [1] claims that neural network distillation was first developed in 2015 by a team of Google researchers including G. Hinton [2]. Not true! I published the technique i

researchdavid-ha--x

A short tour of operator learning theory: Convergence rates, statistical limits, and open questions

arXiv:2603.00819v2 Announce Type: replace-cross Abstract: This paper surveys recent developments at the intersection of operator learning, statistical learning theory, and approximation theory. First,

A simplex-based measure of symmetry

arXiv:2607.03815v1 Announce Type: cross Abstract: For compact convex sets L,K subset R^n, denote by lambda_K(L) the smallest size of a homothet of K that contains L. We define a measure of symmetry ba

A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensors

arXiv:2408.05124v2 Announce Type: replace-cross Abstract: Image sensors are fundamental to many intelligent systems, allowing visual perception and AI-driven decision-making. However, their integrity

A Spiking Sequence Generator for Polar Trajectories on Neuromorphic Hardware

arXiv:2607.02753v1 Announce Type: cross Abstract: Neuromorphic controllers for size, weight, and power-constrained systems require neural architectures that are both energy-efficient and interpretable

researcharxiv-cs-ro

A Unified Algebraic Framework for Classification Performance Evaluation

arXiv:2607.04028v1 Announce Type: cross Abstract: We propose a unified algebraic framework for classification performance evaluation that encompasses binary, multiclass, multilabel, ordinal, hierarchi

A Unified Framework for In-Context Learning with Causal and Masked Language Models

arXiv:2607.04081v1 Announce Type: new Abstract: In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causa

A Unified Framework for Quantized and Continuous Strong Lottery Tickets

arXiv:2607.03860v1 Announce Type: new Abstract: The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks

A Vision Based System for Guided and Collaborative Reconstruction of Fragmented Documents

arXiv:2607.03621v1 Announce Type: new Abstract: This paper presents the development and evaluation of a collaborative system for real-time reconstruction of fragmented paper documents in the context o

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI

arXiv:2510.01038v2 Announce Type: replace Abstract: Perturbation-based explainability methods face criticism due to their reliance on out-of-distribution mutants. This raises doubts about the quality

Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types

arXiv:2607.03304v1 Announce Type: cross Abstract: Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets. We extend Bir

Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields

arXiv:2507.23033v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient computing paradigm for neural rendering, but existing spike-based Neural Radiance Field (

AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction

arXiv:2607.04256v1 Announce Type: new Abstract: Current feed-forward 3D reconstruction methods predict pixel aligned Gaussian primitives, resulting in highly redundant representations. A natural solut

Advanced Topic Modeling Techniques for Categorizing Software Vulnerabilities

arXiv:2607.03887v1 Announce Type: cross Abstract: The increasing complexity and frequency of software vulnerabilities demand efficient methods to analyze and prioritize threats. Traditional approaches

Aerial Manipulation: Contact, Medium Coupling, and the Geometry of Readiness

arXiv:2607.04719v1 Announce Type: new Abstract: Aerial robots are increasingly moving from remote observation toward physical interaction with objects, surfaces, structures, loads, and surrounding flo

researcharxiv-cs-ro

AI developed at @UMA_Robots Single neural network, End to End It operates robustly for hours, with precision, adapting to what it sees.

Researchers at UMA Robots have developed a single neural network that enables end-to-end robotic control, operating continuously for extended periods with high precision while adapting in real-time to

researchyann-lecun--x

AI-RAN on NPUs: Baseband Processing Without Baseband Chips

arXiv:2607.04224v1 Announce Type: cross Abstract: AI-RAN aims to unify artificial intelligence and radio access network workloads on a shared compute substrate. While this paradigm has so far been dem

AIFS-SUBS: Extending Data-Driven Forecasting to Sub-Seasonal Timescales

arXiv:2607.05100v1 Announce Type: cross Abstract: Data-driven models now rival numerical weather prediction in the medium range, but extending them to sub-seasonal lead times raises challenges absent

Air-Plan: Query-Optimized Topology Selection for Over-the-Air Decentralized Federated Learning

arXiv:2607.04254v1 Announce Type: cross Abstract: Over-the-air (OTA) aggregation exploits the superposition property of wireless multiple-access channels to aggregate model updates from multiple devic

AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario

arXiv:2506.16898v2 Announce Type: replace Abstract: Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representa

Algorithmic Shortlisting in Participatory Budgeting

arXiv:2508.06577v3 Announce Type: replace-cross Abstract: Participatory budgeting is a democratic innovation that allows citizens to propose and vote on public investment projects. To help organizers

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

arXiv:2602.06422v2 Announce Type: replace Abstract: Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome

AMT-APC: Automatic Piano Cover by Fine-Tuning an Automatic Music Transcription Model

arXiv:2409.14086v2 Announce Type: replace-cross Abstract: There have been several studies on automatically generating piano covers, and recent advancements in deep learning have enabled the creation o

An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks

arXiv:2607.02594v1 Announce Type: cross Abstract: Deep learning is widely applied in medical image analysis, but up to 10% of manually labelled images may be incorrect, degrading model performance. Th

An Automated Multimodal Glaucoma Detection Framework Using ViT and a Stacking-Based Ensemble

arXiv:2607.02692v1 Announce Type: new Abstract: Glaucoma is a progressive eye disease that can lead to irreversible vision loss if not detected at an early stage. Conventional diagnostic procedures ar

An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression

arXiv:2504.18433v3 Announce Type: replace Abstract: Uncertainty quantification is crucial in machine learning, yet most (axiomatic) studies of uncertainty measures focus on classification, leaving a g

An Interpretable Deep Learning Framework for Discovery and Clinical Validation of Deep Radiomic Signatures in Tumor Classification

arXiv:2607.03593v1 Announce Type: cross Abstract: Imaging signatures are quantitative features extracted from medical images that provide clinically meaningful information for tumor diagnosis, charact

An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures

arXiv:2607.03150v1 Announce Type: cross Abstract: While deepfake audio detection systems achieve high performance in controlled benchmarks, their reliability often diminishes in the wild. Prior work s

Analytical Standard Errors for Exploratory Factor Solutions

arXiv:1811.05336v2 Announce Type: replace-cross Abstract: Inference for factor models is often hampered by the lack of tractable and accurate variance estimates, which can materially distort downstrea

Angry but Accurate: Detecting and Profiling the Counter-Misinformation Ecosystem on Twitter

arXiv:2607.02900v1 Announce Type: cross Abstract: On social media, many users actively push back against false claims. Understanding who pushes back and how they do so matters, as this corrective acti

researcharxiv-cs-cl

Annotating Korean adnominal ending constructions in corpus data: Beyond relative-clause identification

arXiv:2607.03681v1 Announce Type: new Abstract: The Korean adnominal ending exttt{ETM} occurs in diverse noun-modifying constructions, including relative-clause-like modifiers, adjectival and copular

researcharxiv-cs-cl

AnyStyle: A Single LoRA is Sufficient for Image-Guided Style Transfer

arXiv:2607.04677v1 Announce Type: new Abstract: Image-guided style transfer aims to apply the artistic characteristics of a style image to a content image while preserving its semantic structure and l

Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects

arXiv:2603.05060v2 Announce Type: replace Abstract: Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge

Attending to Multimodal Generation One Token at a Time

arXiv:2607.03738v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Pr

Attention-Guided Efficientnet Architecture For Precise Criminal Identification in Surveillance Images

arXiv:2607.03073v1 Announce Type: cross Abstract: Criminal identification from surveillance imagery has become a critical research area in intelligent forensic surveillance systems due to the increasi

Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation

arXiv:2607.02968v1 Announce Type: new Abstract: Massive Activations (MAs) have been widely observed in Transformer-based models, yet their structure and functional roles in Diffusion Transformers (DiT

BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections

arXiv:2607.03891v1 Announce Type: new Abstract: 3D reconstruction of articulated objects from a single image is challenging because large training datasets with paired image and 3D supervision are dif

Batch effects can impair federated learning in multi-center omics studies

arXiv:2412.05894v2 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative analysis of biomedical data without exchanging sensitive patient-level information, but its perf

Bayesian Invariance Modeling of Multi-Environment Data

arXiv:2506.22675v4 Announce Type: replace-cross Abstract: Invariant prediction [Peters et al., 2016] analyzes feature/outcome data from multiple environments to identify invariant features - those wit

Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores

arXiv:2607.05090v1 Announce Type: new Abstract: Lumbar spine degeneration is a major contributor to chronic low back pain and is routinely assessed on MRI using ordinal grading systems, e.g. normal, m

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

arXiv:2607.05348v1 Announce Type: new Abstract: Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language mo

Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token

arXiv:2607.03328v1 Announce Type: new Abstract: Efficient large-scale image retrieval requires compact representations that preserve semantic similarity under fast Hamming-space search. Deep hashing i