Knowledge catalogue
arXiv:2610.01537v1 Announce Type: new Abstract: Federated Learning (FL) enables privacy-preserving fine-tuning of Large Language Models (LLMs), yet the massive communication overhead remains a critica
arXiv:2610.01262v1 Announce Type: new Abstract: Timely and specific feedback is one of the strongest influences on student learning, yet it is difficult to sustain in large electrical engineering clas
arXiv:2610.01739v1 Announce Type: new Abstract: Sampling from discrete, unnormalized distributions without access to data is a challenging problem. Neural samplers offer a promising approach by traini
arXiv:2610.00858v1 Announce Type: new Abstract: Background and Objective: Clinicians expect recurrence risk to climb with cancer severity. In a UK multicentre trial, an unconstrained XGBoost model lea
arXiv:2610.01233v1 Announce Type: new Abstract: Flow matching is central to 3D generation, yet in practice its reinforcement learning (RL) methods are largely adapted from 2D visual generation. Repres
arXiv:2603.04349v2 Announce Type: replace Abstract: Understanding long videos is crucial for embodied intelligent agents, as their performance depends on effectively accumulating and using long-horizo
arXiv:2610.01358v1 Announce Type: cross Abstract: Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cr
arXiv:2610.00573v1 Announce Type: new Abstract: Query-aware keyframe selection enables multimodal large language models (MLLMs) to process long videos using only a small set of question-relevant frame
arXiv:2610.00009v1 Announce Type: new Abstract: Frequency-collapse attention [Zeris, 2026e] achieves large gains over standard dot-product attention by replacing the Q/K dot product with a bandpass-fi
arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate
arXiv:2610.01181v1 Announce Type: new Abstract: We consider stochastic games with independent controlled chains and unknown transition kernels, where players observe only their local states and realiz
arXiv:2610.01637v1 Announce Type: new Abstract: In recent decades, artificial intelligence has made significant progress in understanding and interacting with images. One of the important applications
arXiv:2610.00380v1 Announce Type: new Abstract: Depression is a mental condition that can lead to suicide and self-harm. Predicting the outcome of depression treatment is one of the most difficult tas
arXiv:2610.01382v1 Announce Type: new Abstract: We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-en
arXiv:2610.01633v1 Announce Type: new Abstract: Explaining generalization and training dynamics in neural networks remains a challenge, and various approaches have been developed to study different as
arXiv:2604.01997v2 Announce Type: replace Abstract: Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring acr
arXiv:2307.12226v3 Announce Type: replace-cross Abstract: Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a
arXiv:2610.00683v1 Announce Type: new Abstract: We introduce Grand Canonical Generators (GCG), a generative framework that extends Boltzmann generators to the grand canonical ensemble. We present two
arXiv:2610.01937v1 Announce Type: new Abstract: Topology is, by its nature and design, suited to structure that is nonlinear, multiscale, and nonstationary - however, within machine learning, its use
arXiv:2610.00497v1 Announce Type: cross Abstract: We present Gumbel Straight Flow (GSF), a continuous flow map language model that leverages the noise-data coupling of a pretrained autoregressive lang
arXiv:2505.12269v4 Announce Type: replace-cross Abstract: We examine how the cost of transforming qualitative information into precise numerical estimates--a form of integration cost--creates a struct
arXiv:2512.04705v3 Announce Type: replace-cross Abstract: The deployment of Early-Exiting Neural Networks (EENNs) on edge accelerators requires optimizing not only the network architecture but also it
arXiv:2610.02123v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse computation, routing each token through only a small subset of experts. In th
arXiv:2610.02193v1 Announce Type: cross Abstract: Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global
arXiv:2610.00694v1 Announce Type: cross Abstract: Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on th
arXiv:2610.00004v1 Announce Type: new Abstract: Adam is the standard optimizer in deep learning, yet its geometric relationship to natural gradient descent (NGD) contains unresolved questions. We stud
arXiv:2610.00236v1 Announce Type: new Abstract: Few-shot anomaly detectors are judged by ranking metrics, yet deployment requires an alarm threshold with a controlled false-alarm rate (FAR). We ask ho
arXiv:2610.00198v1 Announce Type: new Abstract: Recent advances in motion generation and whole-body tracking have enabled humanoid robots to execute increasingly diverse motions, yet the same motion c
Agent workload isolation is becoming a practical infrastructure challenge as research teams move beyond training models to running code and testing agents. Systems built for intensive computation must
arXiv:2610.00921v1 Announce Type: new Abstract: The cross-entropy method (CEM) uses world-model scores to select action sequences and fit the distribution sampled in its next iteration. A scoring erro
arXiv:2610.01712v1 Announce Type: new Abstract: In-context learning (ICL) enables a pretrained model to infer a task from demonstrations without updating its parameters. While much of the existing the
arXiv:2505.22767v4 Announce Type: replace-cross Abstract: Dialogue with a large language model can lead a person to insight: a sudden change in how they understand a problem. This perspective asks how
arXiv:2610.00793v1 Announce Type: cross Abstract: We consider the estimation of drift, diffusion, and noise covariance from discrete observations of stochastic differential equations driven by Gaussia
arXiv:2610.01786v1 Announce Type: new Abstract: Neural activity often exhibits multiple timescales that can vary with behavioral states and task conditions. Identifying these timescales from neural re
arXiv:2610.01015v1 Announce Type: cross Abstract: Photoacoustic tomography (PAT) is a hybrid imaging modality that combines high optical contrast with high ultrasonic resolution for biomedical imaging
arXiv:2610.00707v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks through the use of harnesses that prom
arXiv:2610.01385v1 Announce Type: cross Abstract: This work aims to answer the question of whether it is possible to generate irreversible protected templates when the PolyProtect biometric template p
arXiv:2602.18639v2 Announce Type: replace Abstract: World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-leve
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics d
arXiv:2610.00930v1 Announce Type: new Abstract: Post-training quantization for diffusion models increasingly exploits timestep, feature, and layer structure. While recent work has begun incorporating
arXiv:2610.01062v1 Announce Type: new Abstract: Activation steering provides a simple, training-free mechanism for controlling attributes of generative models such as sentiment, style, and helpfulness
arXiv:2610.02084v1 Announce Type: cross Abstract: We study free-boundary problems within a physics-informed framework using Kolmogorov-Arnold network (KAN) approximations. The proposed approach incorp
arXiv:2610.01522v1 Announce Type: new Abstract: Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimen
arXiv:2610.00265v1 Announce Type: new Abstract: Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic programs from a language model, running approximat
arXiv:2610.01926v1 Announce Type: cross Abstract: Increasing depth of transformer models improves recognition, but it comes at a substantial cost. Each additional layer requires more parameters, which
arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of
arXiv:2610.01126v1 Announce Type: new Abstract: Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, h
arXiv:2610.01947v1 Announce Type: new Abstract: Large language models offer a promising foundation for chemical reasoning, bringing together chemical knowledge and multistep problem solving. Chemical
arXiv:2610.01502v1 Announce Type: new Abstract: Diffusion models are a powerful generative paradigm used across multimedia and scientific applications. Guided diffusion methods impose requirements on
arXiv:2610.01432v1 Announce Type: cross Abstract: Simulating microstructure evolution requires quantum-mechanical accuracy and mesoscopic reach in length and time scales, a combination that no current
arXiv:2610.01373v1 Announce Type: new Abstract: World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning
arXiv:2610.00778v1 Announce Type: new Abstract: In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as quasimetric distances, connecting local constraint
arXiv:2610.00637v1 Announce Type: new Abstract: We establish non-asymptotic sample complexity bounds for the least-squares estimation of vector autoregressive models for exponentially stable systems w
arXiv:2610.01697v1 Announce Type: new Abstract: Many physical systems are driven and observed only on lower-dimensional submanifolds of a larger spatial domain, while their dynamics are governed by th
arXiv:2610.01792v1 Announce Type: cross Abstract: Quantum key distribution (QKD) links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel dri
arXiv:2610.01426v1 Announce Type: new Abstract: Prescribing the speed of gradient flow on the risk itself, by the dynamics ot w=-u(E(w))nabla E(w)/abs{nabla E(w)}^{2}, makes the risk e(t)=E(w(t)) obey
arXiv:2610.00294v1 Announce Type: cross Abstract: Automated acne severity grading requires both whole-face context and fine-grained lesion evidence. We propose LENS-GRF (Lesion Evidence Network with S
arXiv:2610.00318v1 Announce Type: cross Abstract: Simplified optical systems often exhibit residual lens aberrations and Veiling Glare (VG), resulting in spatially varying blur and contrast reduction.
arXiv:2610.01494v1 Announce Type: new Abstract: Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature space
arXiv:2607.14895v2 Announce Type: replace Abstract: Reasoning language models (RLMs) demonstrate impressive performance by leveraging test-time compute in the form of reasoning tokens. However, this b