research

From Generalist to Specialist Representation

arXiv:2605.12733v1 Announce Type: cross Abstract: Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptot

From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning

DGX agent

arXiv:2605.12944v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) data selection is commonly formulated as instance ranking: score each example and retain a top-k subset. However, effective

researcharxiv-cs-lg

14 May 2026

GAAMA: Graph Augmented Associative Memory for Agents

arXiv:2603.27910v2 Announce Type: replace Abstract: AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current

Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report

arXiv:2605.13555v1 Announce Type: cross Abstract: Radiation therapy (RT) requires precise dose delivery over multiple fractions, with CT fundamental for treatment planning due to its electron density

Generative Modeling by Minimizing the Wasserstein-2 Loss

arXiv:2406.13619v4 Announce Type: replace-cross Abstract: This paper develops a generative model by minimizing the second-order Wasserstein loss (the W_2 loss) through a distribution-dependent ordinar

Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

arXiv:2512.10857v2 Announce Type: replace-cross Abstract: Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scienti

Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process

arXiv:2605.13150v1 Announce Type: cross Abstract: Discrete automated processes in industrial and cyber-physical systems often exhibit a repetitive structure in which successive repetitions follow a co

Generative Motion In-betweening by Diffusion over Continuous Implicit Representations

arXiv:2605.12778v1 Announce Type: cross Abstract: Recent advances in generative models have yielded impressive progress on motion in-betweening, allowing for more complex, varied, and realistic motion

GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding

arXiv:2605.13352v1 Announce Type: new Abstract: Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through ell_2 normalization t

Gradual Domain Adaptation for Graph Learning

arXiv:2501.17443v4 Announce Type: replace Abstract: Existing machine learning literature lacks graph-based domain adaptation techniques capable of handling large distribution shifts, primarily due to

Guidestar-Free Adaptive Optics with Asymmetric Apertures

arXiv:2602.07029v3 Announce Type: replace-cross Abstract: This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guid

HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonization

arXiv:2605.13073v1 Announce Type: new Abstract: In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies. Exist

Hermes and Athena

Hermes and Athena are two major deities in ancient Greek mythology, representing commerce/communication and wisdom/warfare respectively. This post likely discusses their mythological roles, symbolic s

researchnous-research--x

HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation

arXiv:2605.13586v1 Announce Type: cross Abstract: Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for em

High-Order Epistasis Detection Using Factorization Machine with Quadratic Optimization Annealing and MDR-Based Evaluation

arXiv:2601.01860v2 Announce Type: replace Abstract: Detecting high-order epistasis is a fundamental challenge in genetic association studies due to the combinatorial explosion of candidate locus combi

High-Rate Quantized Matrix Multiplication I

arXiv:2601.17187v2 Announce Type: replace-cross Abstract: This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of larg

Higher-order Linear Attention

arXiv:2510.27258v2 Announce Type: replace-cross Abstract: The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-ti

Human face perception reflects inverse-generative and naturalistic discriminative objectives

arXiv:2605.12619v1 Announce Type: cross Abstract: The perceptual representations supporting our ability to recognize faces remain a computational mystery. Deep neural networks offer mechanistic hypoth

I don't like “fake” social. For truly good things and people, I genuinely appreciate them from the very beginning. And my friends never disa…

I don't like “fake” social. For truly good things and people, I genuinely appreciate them from the very beginning. And my friends never disappoint and always succeed! tbh, Nous is one of the ai labs w

researchnous-research--x

Identification of Non-Transversal Bifurcations of Linkages

arXiv:2605.13094v1 Announce Type: new Abstract: The local analysis is an established approach to the study of singularities and mobility of linkages. Key result of such analyses is a local picture of

researcharxiv-cs-ro

IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback

arXiv:2605.12693v1 Announce Type: new Abstract: Decision-focused learning trains predictive models end-to-end against downstream decision loss, but online settings suffer delayed feedback: outcomes ma

Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion

arXiv:2605.13293v1 Announce Type: new Abstract: Boundary Representation (BRep) is the standard format for Computer-Aided Design (CAD), yet reconstructing high-quality BReps from single-view images rem

Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks

arXiv:2605.08320v1 Announce Type: cross Abstract: Monocular depth estimation (MDE) with self-supervised training approaches struggles in low-texture areas, where photometric losses may lead to ambiguo

Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle

arXiv:2605.12536v1 Announce Type: cross Abstract: The Free Energy Principle (FEP) is a leading framework for mathematically modeling self-organization and learning, while Integrated Information Theory

Integrating 3D Heat Equation into a PINN for Real-Time Aerospace Simulation (C++ WASM Engine)[P]

researchr-machinelearning

This post discusses implementing Physics-Informed Neural Networks (PINNs) to solve the 3D heat equation within a C++ WebAssembly engine for real-time aerospace applications. The work combines machine

Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data

arXiv:2605.13786v1 Announce Type: new Abstract: Background: Pregnancy-associated thrombotic microangiopathy (P-TMA) is rare but life-threatening. Early risk prediction before overt clinical presentati

Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity

arXiv:2604.04692v2 Announce Type: replace-cross Abstract: Automated fact-checking is a crucial task that supports a responsible information ecosystem. While recent research has progressed from text-on

'It became a self-fulfilling prophecy': How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps

arXiv:2605.13261v1 Announce Type: cross Abstract: In menstrual cycle tracking apps (MCTAs), AI-based predictions and insights have become increasingly popular. These features enable users to receive p

IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning

arXiv:2605.12924v1 Announce Type: new Abstract: The instrumental-variables (IV) setting is standard for partial identification of causal effects when unobserved confounding makes point identification

JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift

arXiv:2605.13813v1 Announce Type: new Abstract: Automated CT triage requires models that are simultaneously accurate across diverse pathologies and reliable under institutional shift. While Vision Tra

Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs

arXiv:2605.12772v1 Announce Type: new Abstract: Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system promp

Latent-Augmented Discrete Diffusion Models

arXiv:2510.18114v3 Announce Type: replace-cross Abstract: Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implemen

Learning to Approximate Uniform Facility Location via Graph Neural Networks

arXiv:2602.13155v2 Announce Type: replace Abstract: Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization probl

Learning to Optimize Radiotherapy Plans via Fluence Maps Diffusion Model Generation and LSTM-based Optimization

arXiv:2605.13713v1 Announce Type: new Abstract: Volumetric Modulated Arc Therapy (VMAT) is a cornerstone of modern radiation therapy, enabling highly conformal tumor irradiation and healthy-tissue spa

LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstruction

arXiv:2605.13741v1 Announce Type: cross Abstract: Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However,

LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections

arXiv:2605.13265v1 Announce Type: new Abstract: Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface int

Limitations of Quantum Advantage in Unsupervised Machine Learning

arXiv:2511.10709v2 Announce Type: replace-cross Abstract: Machine learning models are used for pattern recognition analysis of big data, without direct human intervention. The task of unsupervised lea

Limits of Personalizing Differential Privacy Budgets

arXiv:2605.13503v1 Announce Type: cross Abstract: A key technical difficulty in differential privacy is selecting a privacy budget that satisfies privacy requirements while maximizing utility. A natur

LLMs as Implicit Imputers: Uncertainty Should Scale with Missing Information

arXiv:2605.13188v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in settings where the available context is incomplete or degraded. We argue that an LLM generat

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

arXiv:2510.19304v3 Announce Type: replace Abstract: Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall

M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement

arXiv:2605.12556v1 Announce Type: new Abstract: Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based

M3Net: A Macro-to-Meso-to-Micro Clinical-inspired Hierarchical 3D Network for Pulmonary Nodule Classification

arXiv:2605.12570v1 Announce Type: new Abstract: The accurate classification of benign and malignant pulmonary nodules in CT scans is critical for early lung cancer screening, yet remains challenging d

Machine Learning-Driven Multimodal Spectroscopic Liquid Biopsy for Early Multicancer Detection

arXiv:2605.13218v1 Announce Type: new Abstract: Cancer is one of the leading causes of death worldwide, making the development of rapid, minimally invasive, label-free and scalable diagnostic strategi

Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

arXiv:2512.16767v2 Announce Type: replace Abstract: Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-c

MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation

arXiv:2605.12640v1 Announce Type: new Abstract: Panoptic segmentation requires the simultaneous recognition of countable thing instances and amorphous stuff regions, placing joint demands on long-rang

Manipulation Planning for Construction Activities with Repetitive Tasks

arXiv:2605.13754v1 Announce Type: new Abstract: In this paper, we study the problem of manipulation skill acquisition for performing construction activities consisting of repetitive tasks (e.g., build

researcharxiv-cs-ro

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning

arXiv:2605.13101v1 Announce Type: cross Abstract: Synthesis planning seeks an efficient sequence of chemical reactions that produce a target molecule. Typically, a pretrained single-step (autoregressi

McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting

arXiv:2605.13197v1 Announce Type: cross Abstract: Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. Howe