research

CausalGuard: Conformal Inference under Graph Uncertainty

arXiv:2605.21928v1 Announce Type: new Abstract: Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph

CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning

DGX agent

arXiv:2603.21743v4 Announce Type: replace Abstract: Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug disc

researcharxiv-cs-lg

23 May 2026

Cluster-Adaptive Feature Extraction and its Theoretical Foundation with Minkowski Weighted k-Means

arXiv:2603.25958v2 Announce Type: replace Abstract: The Minkowski weighted k-means (mwk-means) algorithm extends classical k-means by incorporating feature weights and a Minkowski distance. We first s

CoFEH: LLM-driven Feature Engineering Empowered by Collaborative Bayesian Hyperparameter Optimization

arXiv:2602.09851v2 Announce Type: replace Abstract: Feature Engineering (FE) is pivotal in automated machine learning (AutoML) but remains a bottleneck for traditional methods, which operate within ri

CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation

arXiv:2605.22774v1 Announce Type: new Abstract: Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cr

Community-Aware Vertex Ordering for Reference-Based Graph Compression: A Cross-Encoder Empirical Study

arXiv:2605.21510v1 Announce Type: cross Abstract: Reference-based graph compression encodes each vertex's neighbor list relative to a recent vertex, exploiting locality to compress large directed grap

Compact Lifted Relaxations for Low-Rank Optimization

arXiv:2603.20228v2 Announce Type: replace-cross Abstract: We develop tractable convex relaxations for rank-constrained quadratic optimization problems over n imes m matrices, a setting for which tract

Conditional Neural Field based Reduced Order Model for Dynamic Ditching Load Prediction

arXiv:2605.21499v1 Announce Type: cross Abstract: Grid-based neural networks such as convolutional autoencoders are widely used in dimension reduction-based surrogate models for computational fluid dy

Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification

arXiv:2605.21742v1 Announce Type: new Abstract: Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performa

Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization

arXiv:2605.22749v1 Announce Type: new Abstract: Modern smart grids rely on dense measurement infrastructures, communication links, and intelligent field devices. Although this improves supervision and

Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

arXiv:2605.22237v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) supports only additions and multiplications, so FHE-only neural-network inference typically replaces ReLU with poly

Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary

arXiv:2510.03271v2 Announce Type: replace Abstract: Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in re

Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations

arXiv:2605.22242v1 Announce Type: new Abstract: Weather and climate forecasts are inherently uncertain due to chaotic dynamics, imperfect initial conditions, and incomplete representation of the under

Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement

arXiv:2605.22346v1 Announce Type: cross Abstract: Two of the most widely used methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different r

Doing a massive Hermes deployment today. Full team, isolated VMs, @honchodotdev shared memory for the team. This stuff is so fun. @NousResea…

Nous Research conducted a large-scale deployment of Hermes today using isolated virtual machines and shared memory infrastructure via honchodotdev for team coordination. The post highlights enthusiasm

researchnous-research--x

Double descent for least-squares interpolation on contaminated data: A simulation study

arXiv:2605.21494v1 Announce Type: new Abstract: Overparametrized models can exhibit an excellent generalization performance, although they should be prone to overfitting according to classical statist

Dynamic Mixture of Latent Memories for Self-Evolving Agents

arXiv:2605.21951v1 Announce Type: new Abstract: Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting pr

Efficient Higher-order Subgraph Attribution via Message Passing

arXiv:2605.22385v1 Announce Type: new Abstract: Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise re

End-to-End Semantic ID Generation for Generative Advertisement Recommendation

arXiv:2602.10445v3 Announce Type: replace-cross Abstract: Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to

Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model

arXiv:2605.21568v1 Announce Type: new Abstract: In this work, we extend the Equilibrium Propagation framework to skew-gradient systems and show an equivalence between deep Energy-Based Models and Hami

Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery

arXiv:2605.22613v1 Announce Type: new Abstract: Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize eac

Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs

arXiv:2605.21994v1 Announce Type: new Abstract: GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via message-passing GNNs. Because these encoders entangle node

Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies

arXiv:2605.22243v1 Announce Type: new Abstract: Predictive modelling is important for health data analysis and data-driven clinical decision-making. However, predictive studies are challenging to desi

Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models

arXiv:2605.22795v1 Announce Type: cross Abstract: We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting v

Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants

arXiv:2511.02043v4 Announce Type: replace Abstract: Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example,

Francis Fukuyama on the U.S. as a declining power: American decline is a direct product of Trump's rise since 2016. It is as if Trump had de…

Francis Fukuyama on the U.S. as a declining power: American decline is a direct product of Trump's rise since 2016. It is as if Trump had decided to do everything in his power to weaken the United Sta

From Betting to Empirical Bernstein LIL

arXiv:2605.22124v1 Announce Type: cross Abstract: This is a verbatim copy of a technical report I wrote in 2017-2018 to obtain the law of the iterated logarithm using the guarantee on the wealth of an

Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration

arXiv:2512.11587v2 Announce Type: replace Abstract: Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, i

Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks

arXiv:2605.21502v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering mea

He has directly betrayed all his followers who trusted him, all of the rest of us who never trusted him, and his country.

This post contains criticism of an unspecified individual, likely a political or public figure, accusing them of betrayal toward their supporters, skeptics, and the nation. The statement appears to be

Historically, the US has been the greatest magnet for talent on earth. Whether that continues to be the case is not inevitable.

Historically, the US has been the greatest magnet for talent on earth. Whether that continues to be the case is not inevitable. Nearly half of the founders of billion-dollar tech startups are immigran

Holographic functions and neural networks

arXiv:2605.22666v1 Announce Type: cross Abstract: A fuzzy Boolean function is a map f:ube^no [0,1], where ninmathbb N. We introduce and compare three ways of saying that such a function has bounded co

How Many Different Outputs Can a Transformer Generate?

arXiv:2605.22223v1 Announce Type: new Abstract: We study how we can leverage only a handful of characteristics of a transformer's architecture to closely predict the number of different sequences it c

How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability

arXiv:2605.21972v1 Announce Type: new Abstract: Unstructured magnitude pruning at high sparsity can reduce neural network accuracy to near-random performance, while labeled retraining may be unavailab

If Trump kicking the Tech Right in the nuts doesn't put an end to the Tech Right, I don't know what would

If Trump kicking the Tech Right in the nuts doesn't put an end to the Tech Right, I don't know what would Feeling robbed of my path to citizenship right now after grinding a PhD and contributing to fo

“If we erase January 6th, it didn’t happen” “If we don’t release certain inflation data, there’s no inflation” “If we don’t measure food ins…

“If we erase January 6th, it didn’t happen” “If we don’t release certain inflation data, there’s no inflation” “If we don’t measure food insecurity, no one’s hungry” “If we delete research on right-wi

Implicit Regularization of Mini-Batch Training in Graph Neural Networks

arXiv:2605.22480v1 Announce Type: new Abstract: Mini-batch training of Graph Neural Networks (GNNs) is fundamentally different from training on i.i.d. data: sampling a subgraph alters the topology and

Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms

arXiv:2605.22604v1 Announce Type: cross Abstract: The advent of cardless artificial intelligence (AI) banking heralds a paradigm shift in the financial landscape, offering users unprecedented security

Interpreting and Steering State-Space Models via Activation Subspace Bottlenecks

arXiv:2602.22719v2 Announce Type: replace Abstract: State-space models (SSMs) have emerged as an efficient strategy for building powerful language models, avoiding the quadratic complexity of computin

Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks

arXiv:2602.05873v2 Announce Type: replace Abstract: Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertain

Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms

arXiv:2601.05157v2 Announce Type: replace-cross Abstract: In this work, we give a {rm poly}(d,k) time and sample algorithm for efficiently learning the parameters of a mixture of k spherical distribut

LEMUR: Learned Multi-Vector Retrieval

arXiv:2601.21853v2 Announce Type: replace-cross Abstract: Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vecto

Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition

arXiv:2605.21565v1 Announce Type: new Abstract: Multimodal Emotion Recognition in Conversations (MERC) is a crucial task for understanding human interactions, where multimodal approaches integrating l

Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts

arXiv:2506.21035v5 Announce Type: replace Abstract: Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based M

Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans

arXiv:2605.21762v1 Announce Type: new Abstract: Non-contrast computed tomography calcium scoring (CTCS) is a cost-effective imaging modality widely used to detect coronary artery calcifications. This

MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

arXiv:2605.21783v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to predictio

Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis

arXiv:2605.20747v1 Announce Type: cross Abstract: Long non-coding RNAs (lncRNAs) are emerging regulatory molecules implicated in chronic disease pathogenesis, including Type 2 Diabetes Mellitus (T2D).

Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning

arXiv:2605.22724v1 Announce Type: new Abstract: We study the approximation and statistical complexity of learning collections of operators in a shared multi-task setting, with a focus on the Multiple