Knowledge catalogue
arXiv:2409.02708v2 Announce Type: replace Abstract: Data scarcity poses a serious threat to modern machine learning and artificial intelligence, as their practical success typically relies on the avai
arXiv:2604.00001v2 Announce Type: replace-cross Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but exist
arXiv:2602.10326v2 Announce Type: replace Abstract: Despite the remarkable success of sampling-based generative models such as flow matching, they can still produce samples of inconsistent or degraded
This paper presents a method for controllable generation in flow matching models by adapting them through reference examples. The key insight is that the velocity field in flow matching is determined
arXiv:2605.12826v1 Announce Type: cross Abstract: The proliferation of sophisticated image editing tools and generative artificial intelligence models has made verifying the authenticity of digital im
arXiv:2603.05093v2 Announce Type: replace-cross Abstract: Feature attributions often hide a critical modeling choice: they explain a prediction along a counterfactual path from a reference state to an
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
arXiv:2605.13245v1 Announce Type: new Abstract: Language models can produce convincing scientific analyses, but repeated generations on the same data do not guarantee the same result. A researcher may
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
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
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
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
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
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
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,
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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