Localizing Transfer Between Memorization Tasks
arXiv:2610.00771v1 Announce Type: new Abstract: A central puzzle in transfer learning is why pre-training on one task can accelerate training or improve performance on another task, and what mechanism
Knowledge catalogue
arXiv:2610.00771v1 Announce Type: new Abstract: A central puzzle in transfer learning is why pre-training on one task can accelerate training or improve performance on another task, and what mechanism
arXiv:2610.01199v1 Announce Type: new Abstract: We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high ac
arXiv:2404.17569v4 Announce Type: replace Abstract: This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to gene
arXiv:2610.00331v1 Announce Type: new Abstract: When selecting mathematical training data for LLMs, a natural organizing principle is topic: probability examples for probability targets. An alternativ
arXiv:2610.00389v1 Announce Type: cross Abstract: Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited inform
arXiv:2610.01707v1 Announce Type: new Abstract: Mesh extraction from 3D Gaussian Splatting (3DGS) aims to endow 3D Gaussians with accurate geometric structures, enabling explicit and precise 3D occupa
arXiv:2610.02136v1 Announce Type: cross Abstract: Unsupervised anomaly detection (UAD) methods for brain MRI are ranked by a single score, yet that score rests on choices that are rarely reported: how
arXiv:2610.00620v1 Announce Type: cross Abstract: Grokking refers to the delayed emergence of validation-set generalization after a model has already overfit the training set. Although first observed
arXiv:2604.01329v2 Announce Type: replace Abstract: Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While some merg
arXiv:2610.01917v1 Announce Type: cross Abstract: Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual r
arXiv:2610.02210v1 Announce Type: new Abstract: I don't think I have ever done anything as peculiar in my life. Among other things, it shows a young man looking with interest at a print on the wall of
arXiv:2610.00268v1 Announce Type: new Abstract: Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Exi
arXiv:2610.00148v1 Announce Type: cross Abstract: Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype. Biological brains combine neuromodulation, which
arXiv:2610.00057v1 Announce Type: new Abstract: Guiding a tractor along a predefined reference path is a key component of precision agriculture. This study develops a path tracking controller based on
arXiv:2610.02158v1 Announce Type: new Abstract: We consider the problem of sampling from Gibbs distributions on matrix spaces whose potential energies are neither convex nor globally gradient-Lipschit
arXiv:2610.01434v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation com
arXiv:2511.15445v3 Announce Type: replace-cross Abstract: Accurately simulating wave propagation is crucial in fields such as acoustics, electromagnetism, and seismic analysis. Traditional numerical m
arXiv:2610.00397v1 Announce Type: new Abstract: Identifying which speaker a listener is attending to in a noisy room -- the cocktail-party problem -- is the missing ingredient for next-generation hear
arXiv:2610.00678v1 Announce Type: cross Abstract: Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high res
arXiv:2610.01270v1 Announce Type: new Abstract: Personalization encoders compress evolving interaction histories into preference states used to rank items or condition text generation. A task head ope
arXiv:2610.00381v1 Announce Type: new Abstract: Medical models are judged not only on correctness, but on whether reported confidence matches actual accuracy. Generalist multimodal medical models have
arXiv:2610.02015v1 Announce Type: cross Abstract: Recent advances in LLM reasoning models---driven primarily by the paradigm of post-training via reinforcement learning with verifiable reward (RLVR)--
arXiv:2610.00820v1 Announce Type: cross Abstract: General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaini
arXiv:2610.00095v1 Announce Type: new Abstract: Tutoring systems use mastery thresholds to decide when students can stop practicing and advance, but the same numerical threshold can lead to very diffe
arXiv:2602.10469v2 Announce Type: replace-cross Abstract: We study online fair allocation of T sequentially arriving items among n agents with heterogeneous preferences, with the objective of maximizi
arXiv:2610.00529v1 Announce Type: new Abstract: The ontology-based contextual AI evaluation (OB-CAIE) methodology was developed to address a lack of scientific rigor that arises from unclear testing c
arXiv:2610.00682v1 Announce Type: new Abstract: Large language models (LLMs) increasingly underpin scientific AI applications that reason over structured knowledge, from biomedical question answering
arXiv:2610.01134v1 Announce Type: new Abstract: An optical character recognition (OCR) can scan a paper and extract text using technology, making people's jobs easier. While various OCR systems are av
arXiv:2604.05518v2 Announce Type: replace-cross Abstract: We propose an active learning algorithm for linear system identification with optimal centered noise excitation. Notably, our algorithm, based
arXiv:2610.01572v1 Announce Type: cross Abstract: This paper investigates stochastic multi-level optimization where the objective is a nested composition of several smooth non-convex functions. We ass
arXiv:2610.01843v1 Announce Type: cross Abstract: We study nonconvex--strongly-convex bilevel optimization under a stochastic first-order oracle. We introduce MRT-FD, a single-loop first-order method
arXiv:2610.01413v1 Announce Type: cross Abstract: Reinforcement learning (RL) algorithms frequently compare probability distributions, such as state visitation distributions induced by policies and ex
arXiv:2610.01148v1 Announce Type: new Abstract: Generating compact and geometrically faithful 3D meshes directly from point clouds remains a fundamental challenge. Point clouds are unordered and spars
arXiv:2610.00720v1 Announce Type: cross Abstract: A Condorcet domain is a set of rankings over a given candidate set, such that every election that consists only of (an odd number of) votes from the d
arXiv:2607.15579v3 Announce Type: replace Abstract: Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (
arXiv:2610.00809v1 Announce Type: new Abstract: Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one fra
arXiv:2610.01663v1 Announce Type: new Abstract: Biomolecular therapeutics often start from known sequences and require targeted editing to improve multiple properties while satisfying hard biochemical
arXiv:2610.00149v1 Announce Type: cross Abstract: Biological neurons achieve computational diversity through specialized types: tonic, bursting, adapting, and fast-spiking cells coexist within the sam
arXiv:2610.01807v1 Announce Type: new Abstract: Reliable clinical deployment of deep medical image models is hindered by distribution shifts across scanners, sites, and acquisition protocols. Existing
arXiv:2610.01279v1 Announce Type: cross Abstract: Motion blur arises from the temporal integration of a continuous sharp signal over a finite exposure window, yet existing learning-based methods sides
arXiv:2610.01088v1 Announce Type: cross Abstract: The nonparametric maximum likelihood estimator (NPMLE) of a Gaussian location mixture maximizes the likelihood over the infinite-dimensional space of
arXiv:2610.01831v1 Announce Type: new Abstract: Group attention, introduced by the time series forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both
arXiv:2610.01356v1 Announce Type: new Abstract: Stable port-Hamiltonian neural networks certify asymptotic stability by construction. Yet, their Hamiltonian is a global Lyapunov function with a single
arXiv:2610.01034v1 Announce Type: cross Abstract: Bayesian inference increasingly uses informative but implicit priors represented only by samples, such as historical ensembles, simulator outputs, and
arXiv:2610.00695v1 Announce Type: cross Abstract: Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the ag
arXiv:2512.04696v3 Announce Type: replace-cross Abstract: We develop a flexible feature selection framework based on deep neural networks that approximately controls the false discovery rate (FDR), a
arXiv:2610.00063v1 Announce Type: cross Abstract: Instance-billed serverless platforms charge for CPU and memory over the lifetime of a warm instance, making idle inference state a direct serving cost
arXiv:2610.00818v1 Announce Type: new Abstract: Ambulance ramping, the delay between hospital arrival and patient handover, is a critical operational bottleneck in Emergency Medical Services (EMS), ye
arXiv:2610.00405v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasti
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-ima
arXiv:2610.00064v1 Announce Type: new Abstract: Assembly actions are compositional: they combine a manipulation with a part or tool. In deployment, systems routinely encounter novel combinations of fa
arXiv:2610.00823v1 Announce Type: new Abstract: We present a planning and control approach to reactively use hand contacts to stabilize a humanoid in low stability scenarios, where only using feet con
arXiv:2610.00897v1 Announce Type: new Abstract: We propose a human-factor-aware method of allocating robot supervision tasks to multiple human operators. In scenarios where multiple operators occasion
arXiv:2606.13607v3 Announce Type: replace Abstract: When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not
arXiv:2610.00558v1 Announce Type: new Abstract: While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive
arXiv:2610.00970v1 Announce Type: cross Abstract: Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has follo
arXiv:2610.02033v1 Announce Type: new Abstract: Individual mobility trajectories support urban analysis and location-based services, yet most trajectory generators require observations from their depl
arXiv:2610.01453v1 Announce Type: new Abstract: Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the o
arXiv:2610.01140v1 Announce Type: new Abstract: Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a tra
arXiv:2610.01206v1 Announce Type: new Abstract: Partially transmissive screens and protective covers are common in robotic inspection, but they create mixed LiDAR returns from both the foreground mate