Knowledge catalogue
arXiv:2605.03769v1 Announce Type: new Abstract: Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a fo
arXiv:2503.17715v3 Announce Type: replace Abstract: We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching betwee
arXiv:2505.08203v2 Announce Type: replace-cross Abstract: While recent advancements in AI music generation have predominantly focused on direct audio synthesis, these systems suffer from inherent rigi
arXiv:2605.03144v1 Announce Type: new Abstract: In computational pathology, nuclear instance segmentation is a fundamental task with many downstream clinical applications. With the advent of deep lear
arXiv:2605.03153v1 Announce Type: cross Abstract: Static benchmarks measure a model frozen at training time. Real systems face distribution shift: new categories, paraphrased queries, drift: and must
arXiv:2605.03065v1 Announce Type: new Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv:2605.03869v1 Announce Type: new Abstract: We investigate the effectiveness of adaptive zeroth-order (ZO) optimization for memory-constrained fine-tuning of large language models (LLMs). Contrary
arXiv:2605.03839v1 Announce Type: cross Abstract: We study the problem of approximating the total variation distance between two mixtures of product distributions over an n-dimensional discrete domain
arXiv:2511.11362v2 Announce Type: replace-cross Abstract: On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent m
arXiv:2605.03290v1 Announce Type: new Abstract: Domain randomization (DR) is widely used in policy learning to improve robustness to modeling error, but remains underexplored in contact-rich sampling-
arXiv:2605.02907v1 Announce Type: new Abstract: Softmax attention maps every query--key interaction into a probability distribution, but the underlying structure remains largely unexplored. We define
arXiv:2605.02255v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While at
arXiv:2605.03283v1 Announce Type: cross Abstract: We provide a unified theoretical analysis of Linear Discriminant Analysis with simultaneous multilabel scatter matrix formulations and Stiefel orthogo
arXiv:2412.14737v2 Announce Type: replace Abstract: The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustwo
arXiv:2605.03098v1 Announce Type: new Abstract: Deep learning-based medical image segmentation is increasingly used to support clinical diagnosis and develop new treatment strategies. However, model p
arXiv:2506.14067v4 Announce Type: replace Abstract: As interactive generative systems are increasingly deployed in real-world applications, their tendency to generate unreliable or false responses rai
arXiv:2605.04036v1 Announce Type: cross Abstract: Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominat
arXiv:2511.08717v4 Announce Type: replace-cross Abstract: Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (
arXiv:2605.03921v1 Announce Type: new Abstract: We study the (arepsilon, elta)-PAC policy identification problem in finite-horizon episodic Markov Decision Processes. Existing approaches provide finit
arXiv:2605.02045v1 Announce Type: cross Abstract: Using reinforcement learning, we optimize for practical hardware constraints, including limited FIR filter taps at the transmitter and receiver, mean
arXiv:2508.17466v3 Announce Type: replace-cross Abstract: This paper presents a deep learning framework designed to enhance the grasping capabilities of quadrupeds equipped with arms, with a focus on
arXiv:2605.03490v1 Announce Type: new Abstract: The clinical integration of deep learning models for brain tumor diagnosis in neuro-oncology is severely constrained by limited expert-annotated MRI dat
arXiv:2605.02728v1 Announce Type: new Abstract: This paper presents ORPilot, an open-source agentic AI system that translates real-world business problems into solver-ready optimization models. Unlike
arXiv:2605.03252v1 Announce Type: cross Abstract: LoRA fine-tuning of diffusion transformers (DiT) on multi-style data suffers from style bleed: a single low-rank residual cannot represent several dis
arXiv:2605.03160v1 Announce Type: new Abstract: The standard sparse-autoencoder (SAE) interpretability protocol labels each feature from its top-activating contexts and validates by single-feature ste
arXiv:2605.02938v1 Announce Type: new Abstract: Reliable periodic patterns serve as a fundamental basis for accurate multivariate time series forecasting. However, existing methods either implicitly e
arXiv:2505.04310v2 Announce Type: replace-cross Abstract: Distributional Reinforcement Learning (DistRL) improves upon expectation-based methods by modeling full return distributions, but standard app
arXiv:2605.03848v1 Announce Type: new Abstract: Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identificatio
arXiv:2602.00378v2 Announce Type: replace-cross Abstract: We present a method for parametrizing sub-grid processes in the Shallow Water equations. We define coarse variables and local spatial averages
arXiv:2605.03520v1 Announce Type: cross Abstract: We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly repre
arXiv:2408.01914v4 Announce Type: replace-cross Abstract: Several forms for constructing novel physics-informed neural-networks (PINN) for the solution of partial-differential-algebraic equations base
arXiv:2605.03267v1 Announce Type: cross Abstract: Causality is a central topic in scientific inquiry, yet for complex systems, the identification and analysis of synergistic causation remain a challen
arXiv:2605.03268v1 Announce Type: new Abstract: Here we introduce Partially Observed Structural Causal Models (POSCMs) that formalize causal systems where latent contexts co-determine both the interac
arXiv:2605.03571v1 Announce Type: new Abstract: Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising applicati
arXiv:2605.03548v1 Announce Type: new Abstract: Reconstructing PDE-governed fields from sparse and irregular measurements is challenging due to their ill-posed nature. Deterministic surrogates are tra
arXiv:2603.20562v2 Announce Type: replace Abstract: Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We
arXiv:2605.01123v1 Announce Type: new Abstract: Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while m
arXiv:2605.02004v1 Announce Type: new Abstract: Personalized models are essential in digital health because individuals exhibit substantial physiological and behavioral heterogeneity. Yet personalizat
arXiv:2605.03929v1 Announce Type: cross Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal infor
arXiv:2605.02974v1 Announce Type: cross Abstract: Structured launch signals on Product Hunt contain statistically significant predictive information for Series A funding outcomes. We construct PHBench
arXiv:2605.03079v1 Announce Type: cross Abstract: Recent advances in emotional voice conversion (EVC) have enabled the generation of expressive synthetic speech, raising new concerns in audio deepfake
arXiv:2601.20303v2 Announce Type: replace Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of
arXiv:2605.02240v1 Announce Type: new Abstract: We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record
arXiv:2605.03129v1 Announce Type: cross Abstract: Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style persona
arXiv:2605.03399v1 Announce Type: new Abstract: Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operati
arXiv:2604.17654v3 Announce Type: replace Abstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and sca
arXiv:2605.03357v1 Announce Type: new Abstract: Mean Field Games (MFGs) provide a powerful framework for modeling the collective behavior of large populations of interacting agents. In this paper, we
arXiv:2605.03105v1 Announce Type: new Abstract: This paper introduces the ensemble directional Kalman filter (EnDKF), an ensemble-based Kalman filtering approach for pose tracking that jointly estimat
arXiv:2605.02452v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding o
arXiv:2605.01280v1 Announce Type: cross Abstract: This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic founda
arXiv:2605.01147v1 Announce Type: new Abstract: As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety propertie
arXiv:2605.02844v1 Announce Type: cross Abstract: Scientists increasingly rely on sensor-based data; however transforming raw streams into insights across the edge-to-cloud continuum remains difficult
arXiv:2605.03247v1 Announce Type: new Abstract: Neural PDE simulators often receive only a single observed field at deployment. In this setting, a field-to-future predictor can collapse distinct laten
arXiv:2410.09457v2 Announce Type: replace Abstract: Modern cryptographic methods for implementing privacy-preserving LLMs such as gls{HE} require the LLMs to have a polynomial form. Forming such a rep
arXiv:2605.01471v1 Announce Type: cross Abstract: Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study o
arXiv:2605.02947v1 Announce Type: new Abstract: This study proposes a novel approach to extract topological properties, specifically the Euler characteristic, from input images using neural networks w
arXiv:2605.03733v1 Announce Type: cross Abstract: Minimizing the Mean Squared Error (MSE) is a key objective in machine learning and is commonly used for imputing missing values. While this approach p
arXiv:2511.09290v2 Announce Type: replace Abstract: Predictive learning has emerged as a central paradigm for training models across diverse data domains and is increasingly viewed as a foundation for
arXiv:2507.05561v2 Announce Type: replace Abstract: Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans levera
arXiv:2605.03964v1 Announce Type: new Abstract: Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and th