research

MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data

arXiv:2603.19185v2 Announce Type: replace Abstract: Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative mo

Research

Min-Max Optimization Requires Exponentially Many Queries

DGX agent

arXiv:2605.13806v1 Announce Type: cross Abstract: We study the query complexity of min-max optimization of a nonconvex-nonconcave function f over [0,1]^d imes [0,1]^d. We show that, given oracle acces

researcharxiv-cs-lg

14 May 2026

Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models

arXiv:2601.21975v2 Announce Type: replace Abstract: Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices

Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

arXiv:2605.13225v1 Announce Type: new Abstract: For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many tim

MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

arXiv:2605.13126v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compres

More on Novita Sandbox: http://novita.ai/sandbox Sign up for Nous Portal: http://portal.nousresearch.com/manage-subscription

Nous Research is promoting two resources: the Novita Sandbox, a platform for AI experimentation and development available at novita.ai/sandbox, and the Nous Portal for subscription management at porta

researchnous-research--x

MPINeuralODE: Multiple-Initial-Condition Physics-Informed Neural ODEs for Globally Consistent Dynamical System Learning

arXiv:2605.13305v1 Announce Type: new Abstract: Neural ordinary differential equations (Neural ODEs) often fit training trajectories while generalizing poorly to unseen initial conditions and long hor

Multi-Modal World Model for Physical Robot Interactions: Simultaneous Visual and Tactile Predictions for Enhanced Accuracy

arXiv:2304.11193v2 Announce Type: replace-cross Abstract: Predicting the outcomes of robotic actions, often referred to as learning a world model, in complex environments remains a fundamental challen

Multi-Quantile Regression for Extreme Precipitation Downscaling

arXiv:2605.12762v1 Announce Type: cross Abstract: Deep super-resolution networks for precipitation downscaling achieve strong bulk skill yet systematically under-predict the heavy-tail events that dri

Multimodal Hidden Markov Models for Persistent Emotional State Tracking

arXiv:2605.12838v1 Announce Type: new Abstract: Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understandi

Multitask Multimodal Fusion with Tabular Foundation Models for Peak and Durability Prediction of Pertussis Booster Response

arXiv:2605.12852v1 Announce Type: new Abstract: Pertussis booster vaccination produces immune responses that vary widely across individuals in both peak magnitude and long-term durability. These two p

NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating

arXiv:2605.13651v1 Announce Type: cross Abstract: Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant

Neural Surrogate Forward Modelling For Electrocardiology Without Explicit Intracellular Conductivity Tensor

arXiv:2605.13366v1 Announce Type: new Abstract: Accurate forward modelling is essential for non-invasive cardiac electrophysiology, particularly in atrial fibrillation, where electrical activation is

Neural Video Compression with Domain Transfer

arXiv:2605.13476v1 Announce Type: new Abstract: Content-adaptive compression has always been a key direction in neural video coding (NVC), aiming to mitigate the domain gap between training and testin

NFR: Neural Feature-Guided Non-Rigid Shape Registration

arXiv:2505.22445v2 Announce Type: replace-cross Abstract: In this paper, we propose a novel learning-based framework for 3D shape registration, which overcomes the challenges of significant non-rigid

Obama on the Iran nuclear deal today: “We pulled it off without firing a missile. We got 97% of their enriched uranium out. There’s no dispu…

Obama on the Iran nuclear deal today: “We pulled it off without firing a missile. We got 97% of their enriched uranium out. There’s no dispute that it worked. We didn’t have to kill a whole bunch of p

researchyann-lecun--x

Object Manipulation of the Variable Topology Truss system

arXiv:2605.13086v1 Announce Type: new Abstract: This paper presents an object manipulation strategy for the Variable Topology Truss (VTT) system, a truss robot that comprises actuated truss members co

researcharxiv-cs-ro

OCH3R: Object-Centric Holistic 3D Reconstruction

arXiv:2605.13018v1 Announce Type: new Abstract: Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first app

Offline Two-Player Zero-Sum Markov Games with KL Regularization

arXiv:2605.13025v1 Announce Type: new Abstract: We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism

On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

arXiv:2605.13146v1 Announce Type: cross Abstract: Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can pro

On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning

arXiv:2605.12566v1 Announce Type: cross Abstract: The rapid development of low-altitude economy has driven the proliferation of Unmanned Aerial Vehicle (UAV) applications, including logistics, inspect

On the Limits of Latent Reuse in Diffusion Models

arXiv:2605.13448v1 Announce Type: cross Abstract: Diffusion models are often trained in low-dimensional latent spaces, which are then reused for related but shifted datasets. In this work, we study wh

On the Size Complexity and Decidability of First-Order Progression

arXiv:2605.12691v1 Announce Type: new Abstract: Progression, the task of updating a knowledge base to reflect action effects, generally requires second-order logic. Identifying first-order special cas

Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data

arXiv:2605.12753v1 Announce Type: cross Abstract: INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing re

Partial Optimality in the Preordering Problem

arXiv:2602.17346v2 Announce Type: replace-cross Abstract: Preordering is a generalization of clustering and partial ordering with applications in bioinformatics and social network analysis. Given a fi

Perceptrons and localization of attention's mean-field landscape

arXiv:2601.21366v2 Announce Type: replace Abstract: The forward pass of a Transformer can be seen as an interacting particle system on the unit sphere: time plays the role of layers, particles that of

Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging

arXiv:2605.13583v1 Announce Type: new Abstract: Recent advances have demonstrated that coded aperture snapshot spectral imaging (CASSI) systems show great potential for capturing 3D hyperspectral imag

Physics Guided Generative Optimization for Trotter Suzuki Decomposition

arXiv:2605.13268v1 Announce Type: cross Abstract: Product formulas for Trotter Suzuki simulation remain a practical route to Hamiltonian evolution on noisy intermediate scale quantum (NISQ) hardware,

Physics-informed neural particle flow for the Bayesian update step

arXiv:2602.23089v2 Announce Type: replace Abstract: The Bayesian update step poses significant computational challenges in high-dimensional nonlinear estimation. While log-homotopy particle flow filte

Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

arXiv:2506.19037v4 Announce Type: replace-cross Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask

Plug-In Classification of Drift Functions in Diffusion Processes Using Neural Networks

arXiv:2602.02791v2 Announce Type: replace-cross Abstract: We study supervised multiclass classification for diffusion processes, where each class is characterized by a distinct drift function and traj

Polyhedral Instability Governs Regret in Online Learning

arXiv:2605.13692v1 Announce Type: new Abstract: Many online decision problems over combinatorial actions are addressed via convex relaxations, leading to online convex optimization with piecewise line

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

arXiv:2605.12648v1 Announce Type: new Abstract: We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-priva

Posterior Bayesian Neural Networks with Dependent Weights

arXiv:2507.22095v5 Announce Type: replace-cross Abstract: We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to a

Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI

arXiv:2508.14950v2 Announce Type: replace-cross Abstract: 4D Flow Magnetic Resonance Imaging (4D Flow MRI) enables non-invasive quantification of blood flow and hemodynamic parameters. However, its cl

Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference

arXiv:2602.06104v2 Announce Type: replace Abstract: Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task perfor

Preconditioned Flow Matching

arXiv:2603.02337v2 Announce Type: replace-cross Abstract: Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions p_t. We identify a geometri

Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints

arXiv:2601.21033v2 Announce Type: replace Abstract: Diffusion models cannot enforce hard constraints, yet applications in the physical sciences demand exact satisfaction of conservation laws, boundary

Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy

arXiv:2605.12855v1 Announce Type: new Abstract: Clinical trial studies indicate benefit of watch-and-wait (WW) surveillance for patients with rectal cancer showing a complete or near clinical response

Prime Successor Irreducibility: Turing Machine Complexity, Kolmogorov Complexity, and Weakness-Based Formulations

arXiv:2605.12504v1 Announce Type: cross Abstract: We develop conjectures and theorems expressing the idea that the prime sequence exhibits computational irreducibility in the transition from one prime

PRISM: Perinuclear Ring-based Image Segmentation Method for Acute Lymphoblastic Leukemia Classification

arXiv:2605.12851v1 Announce Type: cross Abstract: Automated analysis of peripheral blood smears for Acute Lymphoblastic Leukemia (ALL) is hindered by low contrast and substantial variability in cytopl

Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems

arXiv:2512.08411v2 Announce Type: replace Abstract: Model-based planning in robotic domains is challenged by the hybrid nature of physical dynamics, where continuous motion is punctuated by discrete e

Profit Maximization in Bilateral Trade against a Smooth Adversary

arXiv:2605.12664v1 Announce Type: cross Abstract: Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, who wish to trade a good. We study this problem

Provable Quantization with Randomized Hadamard Transform

arXiv:2605.13810v1 Announce Type: new Abstract: Vector quantization via random projection followed by scalar quantization is a fundamental primitive in machine learning, with applications ranging from

Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising

arXiv:2605.12567v1 Announce Type: cross Abstract: The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit no

QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

arXiv:2605.13833v1 Announce Type: cross Abstract: Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through atten

QSMOTE-PGM/kPGM: QSMOTE Based PGM and kPGM for Imbalanced Dataset Classification

arXiv:2512.16960v2 Announce Type: replace Abstract: Quantum-inspired machine learning (QiML) employs mathematical principles from quantum theory, such as Hilbert-space representations and quantum stat

Radial Compensation: Fixing Radius Distortion in Chart-Based Generative Models on Riemannian Manifolds

arXiv:2511.14056v2 Announce Type: replace-cross Abstract: We study the base distribution in chart-based generative models on Riemannian manifolds. Standard methods sample in Euclidean tangent space an