research

Content Creation with Spillovers: An Incentive Design Approach

arXiv:2603.14372v3 Announce Type: replace Abstract: The rise of AI amplifies the economic phenomenon of positive spillovers: when creators contribute content that can be reused and adapted by LLMs, on

Context-structured Video Anomaly Detection with Large Vision-Language Models

DGX agent

arXiv:2607.19077v1 Announce Type: new Abstract: Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vis

researcharxiv-cs-cv

23 Jul 2026

Convergence-Latency-Aware Adaptive Modulation and Resource Allocation in RIS-Assisted Wireless Federated Learning

arXiv:2607.19759v1 Announce Type: cross Abstract: Federated learning (FL) over wireless networks suffers from significant training latency and degraded convergence due to unreliable wireless transmiss

Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments

arXiv:2607.20289v1 Announce Type: cross Abstract: We consider a task planning scenario in which robots sharing a persistent environment are assigned tasks one at a time from a held-out sequence. Stand

Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks

arXiv:2604.01363v2 Announce Type: replace Abstract: We propose that AI automation is a continuum between: (i) crashing waves where AI capabilities surge abruptly over small sets of tasks, and (ii) ris

CRB-Driven Beamforming and Trajectory Optimization for UAV-assisted ISAC System

arXiv:2607.19609v1 Announce Type: cross Abstract: In this paper, we study an unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system, where a UAV enhances the sensing

CURED: Creating, Understanding, and Repairing Errors Demonstrator

arXiv:2607.20140v1 Announce Type: new Abstract: Detecting and cleaning errors in tabular data is a prerequisite for data intense software applications. Recent research at the intersection of Machine L

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning

arXiv:2607.20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocate

Data-Poisoning Audits for Causal Effect Estimation

arXiv:2607.19692v1 Announce Type: cross Abstract: Observational causal analyses increasingly pool records across sites, vendors, and collection systems, creating vulnerability to append-only attacks i

Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions

arXiv:2607.20316v1 Announce Type: cross Abstract: We study decentralized online optimization for strongly geodesically convex (strongly g-convex) losses on Riemannian manifolds with bounded sectional

Deep Learning Estimation of Sex, Age, Height, and Weight from CT-derived Digitally Reconstructed Radiographs

arXiv:2607.18638v1 Announce Type: new Abstract: Purpose: To develop and validate a deep learning ensemble for estimating adult sex, age, height, and weight from coronal digitally reconstructed radiogr

Denoising Monte Carlo Renders with Diffusion Models

arXiv:2404.00491v3 Announce Type: replace Abstract: Physically-based renderings contain Monte Carlo noise, with variance that increases as the number of rays per pixel decreases. This noise, while zer

Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream

arXiv:2607.19476v1 Announce Type: new Abstract: Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model. Dete

Differentially Private Neural Network Training Under the Hidden State Assumption

arXiv:2407.08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over trai

Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes

arXiv:2601.21026v2 Announce Type: replace-cross Abstract: Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics. Boltzmann Generators (BGs) tackle it by co

Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparison

arXiv:2607.20119v1 Announce Type: cross Abstract: We introduce the Directional Kernel Mean Difference (DKMD), a signed statistic for univariate distribution comparison that preserves the direction of

Distributed Acoustic Localization Array Deployed Using a Soft Everting Vine Robot

arXiv:2607.20392v1 Announce Type: new Abstract: Soft robot exteroception is increasingly being explored for a variety of field applications. In this work, we present a sound-based system for localizin

researcharxiv-cs-ro

Distributed Optimization via Energy Conservation Laws in Dilated Coordinates

arXiv:2409.19279v2 Announce Type: replace-cross Abstract: Continuous-time models can reveal accelerated structures in distributed optimization, but their rates need not survive direct discretization.

Do Sheaf Neural Networks Use Holonomy? A Measure--Intervene--Control Study

arXiv:2607.19514v1 Announce Type: new Abstract: Geometric architectures are often justified by internal mechanisms such as rotations, yet task performance alone cannot show whether those mechanisms dr

Domain-Adapted Power Curve for Cross-Farm Applications

arXiv:2607.19744v1 Announce Type: cross Abstract: The wind energy industry relies on accurate power curve models to make power forecast, evaluate turbine performance, quantify upgrade, or support site

Domain Shift in Echocardiography: Interpretable Quantification and Prediction of Cross-Dataset Left Ventricular Segmentation

arXiv:2607.19643v1 Announce Type: new Abstract: Cross-dataset generalisation remains a major barrier to clinical deployment of echocardiographic left ventricular segmentation, yet the sources of this

Don't Trust the Label: License Laundering in AI Supply Chains

arXiv:2607.20300v1 Announce Type: cross Abstract: AI artifacts move through a multi-platform supply chain, spanning datasets and models on Hugging Face and applications on GitHub. While each artifact

Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching

arXiv:2607.18688v1 Announce Type: new Abstract: Visible-Infrared Person Re-Identification (VI-ReID) operates under a closed-world assumption, where queries and galleries are from heterogeneous modalit

DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer

arXiv:2607.18510v1 Announce Type: new Abstract: Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this info

Dynamical and Optimization Trade-offs of Levi--Civita Coordinates for Learned Close-Encounter Dynamics

arXiv:2607.20235v1 Announce Type: cross Abstract: Classical regularization removes the binary-collision singularity from the Kepler problem, but its value as a representation for learned Hamiltonian d

EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Images

arXiv:2310.10051v3 Announce Type: replace Abstract: Absolute rotation estimation is an important topic in 3D computer vision. Existing works in literature generally employ a multi-stage (at least two-

Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models

arXiv:2607.19932v1 Announce Type: new Abstract: Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language

researcharxiv-cs-cl

ELSAA: Efficient Low-Rank and Sparse Attention Approximation for Training Transformers

arXiv:2607.20214v1 Announce Type: cross Abstract: The quadratic Nimes N attention score matrix remains a central obstacle to extending Transformers to longer input lengths. Existing efficient attentio

emb-diversity: A Tool for Embedding-Based Measurement of Data Diversity

arXiv:2607.19848v1 Announce Type: new Abstract: There is growing evidence that data diversity is crucial for developing fair and robust NLP models. However, current approaches to measure diversity rem

researcharxiv-cs-cl

End-to-End Differential Privacy in Training Deep Neural Network Classifiers

arXiv:2607.19580v1 Announce Type: new Abstract: Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from

Enhanced Neural Quantum State via Annealed Gradient Descent

arXiv:2607.18865v2 Announce Type: replace-cross Abstract: Neural quantum states offer expressive representations of quantum many-body wave functions, yet their practical accuracy can be limited by sto

Enhancing next token prediction based pre-training for jet foundation models

arXiv:2512.04149v2 Announce Type: replace-cross Abstract: Next token prediction is an attractive pre-training task for jet foundation models, in that it is simulation free and enables excellent genera

Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States

arXiv:2607.19531v1 Announce Type: cross Abstract: Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors. Our Equilibrium Causal Gam

ERank in Latent Space as an Image-Complexity and Richness Measure

arXiv:2607.19315v1 Announce Type: new Abstract: We propose the effective rank (ERank) of the channel covariance of an image's deep feature map as a per-sample, label-free measure of visual richness, c

Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean

arXiv:2607.19374v1 Announce Type: new Abstract: Recent formal reasoning systems have reached IMO-level performance, yet they leave a fragmented landscape: algebra and number theory are handled in Lean

EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization

arXiv:2607.19962v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such

Exposure is Optional: Learning Unlike Coordination in Language Models

arXiv:2607.20251v1 Announce Type: new Abstract: Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics.

researcharxiv-cs-cl

Factor-Informed Uncertainty Distillation for Gaze Estimation

arXiv:2607.20072v1 Announce Type: new Abstract: Deep gaze estimation works well in controlled capture but degrades in unconstrained settings, where systems must reject unreliable predictions. Single-p

Failure Modes of Always-On Inter-Cluster Repulsion in Replay-Based Continual Learning

arXiv:2510.07648v3 Announce Type: replace Abstract: Feature-space objectives are often added to replay-based continual learning systems with the expectation that better geometric separation will impro

Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory

arXiv:2601.00821v4 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts (extracted facts, decisions, or events) on th

First ML coding round (HackerRank) at Adyen, what should I expect? [D]

researchr-machinelearning

Hi everyone, I recently received an interview offer for ML position at Adyen, and the first round will be a live coding round on HackerRank. I scheduled it for the end of August because that was the l

FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility

arXiv:2607.19100v1 Announce Type: new Abstract: Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital

FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation

arXiv:2607.19354v1 Announce Type: new Abstract: Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier. Existing approaches rely on sta

From Bit-Position Sensitivity to Unequal Error Protection for DNN Inference Memory

arXiv:2607.19623v1 Announce Type: cross Abstract: We characterize per-bit-position fault sensitivity in ML inference across 16 workloads -- spanning transformer-based models and attention-free CNNs --

Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR

arXiv:2607.19040v1 Announce Type: new Abstract: Infrared small target detection (ISTD) remains challenging because tiny, low-contrast targets are easily overwhelmed by clutter, noise, or occlusion. Co

Generalized Kalman filter based temporal difference reinforcement learning

arXiv:2607.20010v1 Announce Type: new Abstract: In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations. The v

Generating Bearing Vibration Signals at User-Specified Fault Probabilities Using PR-GAN and Counterfactual Methods

arXiv:2607.19455v1 Announce Type: new Abstract: In bearing vibration datasets, most samples receive predicted fault probabilities close to 0 or 1, while samples with intermediate (gray-zone) probabili

Generative AI floods and dilutes the market for books

arXiv:2607.20349v1 Announce Type: cross Abstract: Generative AI can produce book-length works of fiction at near-zero cost. These books are often dismissed as low-quality ``slop'' that buyers will ign