Knowledge catalogue
arXiv:2605.18466v1 Announce Type: new Abstract: Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid mo
arXiv:2605.17180v1 Announce Type: new Abstract: We develop a geometric theory of projection heads in self-supervised learning by modeling the head as a trainable Riemannian metric on the backbone repr
arXiv:2605.17087v1 Announce Type: new Abstract: Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approac
arXiv:2510.14466v3 Announce Type: replace-cross Abstract: Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and
arXiv:2605.18163v1 Announce Type: new Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor unif
arXiv:2603.18178v2 Announce Type: replace-cross Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-co
arXiv:2605.16775v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has advanced medical image analysis be enabling learning form large unlabelled data. However, in brain magnetic resonan
arXiv:2605.18507v1 Announce Type: new Abstract: Due to the difficulty of obtaining ground-truth data for 4D radar scene flow estimation, previous methods typically rely on either self-supervised losse
arXiv:2602.05813v2 Announce Type: replace Abstract: We study adaptive learning rate scheduling for norm-constrained optimizers (e.g., Muon and Lion). We introduce a generalized smoothness assumption u
arXiv:2605.18150v1 Announce Type: new Abstract: Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesi
arXiv:2605.18115v1 Announce Type: new Abstract: Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with
arXiv:2605.18137v1 Announce Type: new Abstract: This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and wo
arXiv:2505.21698v3 Announce Type: replace Abstract: Vision-language foundation models achieve promising performance in natural image classification, yet their direct application to medical imaging is
arXiv:2605.15213v1 Announce Type: cross Abstract: Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (AI) have enabled food recommendation systems to ad
arXiv:2605.15354v1 Announce Type: new Abstract: Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tas
arXiv:2509.23352v3 Announce Type: replace-cross Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in
arXiv:2605.15592v1 Announce Type: new Abstract: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Desp
arXiv:2601.23068v2 Announce Type: replace-cross Abstract: Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely us
arXiv:2505.21535v4 Announce Type: replace-cross Abstract: While transformers dominate modern vision and language models, their attention mechanism remains poorly suited for in-memory computing (IMC) d
arXiv:2605.15320v1 Announce Type: cross Abstract: Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limit
arXiv:2605.15334v1 Announce Type: cross Abstract: The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achie
arXiv:2605.15562v1 Announce Type: new Abstract: Augmenting Transformers with linguistic structures effectively enhances the syntactic generalization performance of language models. Previous work in th
arXiv:2605.16056v1 Announce Type: new Abstract: Research on Vision Language Action (VLA) models has been increasing rapidly in recent years. Although some of them focus on detecting, preventing, and r
arXiv:2605.15741v1 Announce Type: new Abstract: Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental 'granularity dilemma': captu
arXiv:2605.16234v1 Announce Type: cross Abstract: When researchers ask whether two transformer layers are 'equivalent' for compression, they often conflate distinct tests. Replacement asks whether one
arXiv:2605.15582v1 Announce Type: new Abstract: Modern deep learning models for change detection (CD) often struggle to explicitly represent task-relevant semantic differences. This paper proposes the
arXiv:2605.15916v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as an critical technique for adapting large-scale foundation models across natural language process
arXiv:2509.05030v2 Announce Type: replace Abstract: To enable large-scale reuse of real-world 3D assets, where garments and characters rarely share skeletons, templates, or dense correspondences, we p
arXiv:2605.16118v1 Announce Type: new Abstract: The source distribution in conditional flow matching is a design parameter that can be calibrated to data, not a default isotropic prior. We exploit thi
arXiv:2605.15615v1 Announce Type: new Abstract: Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-off (BNT): improving performance on unseen (new) cla
arXiv:2510.02307v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emp
arXiv:2605.15403v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability. However, existing load-balancing methods are lar
arXiv:2511.18719v4 Announce Type: replace Abstract: Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) in
arXiv:2603.15269v2 Announce Type: replace Abstract: The tortuosity of corneal nerve fibers are used as indication for different diseases. Current state-of-the-art methods for grading the tortuosity he
arXiv:2605.15488v1 Announce Type: new Abstract: Survival analysis provides a powerful statistical framework for modeling time-to-event outcomes in the presence of censoring. However, selecting an appr
arXiv:2605.15465v1 Announce Type: new Abstract: Physiological time series signals reflect complex, multi-scale dynamical processes of the human body. Existing modeling studies focus on static tasks su
arXiv:2605.14761v1 Announce Type: new Abstract: Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been pr
arXiv:2605.14716v1 Announce Type: cross Abstract: Sparse anchors provide a compact interface for human motion authoring: users specify a few root positions, planar trajectory samples, or body-point ta
arXiv:2605.14255v1 Announce Type: cross Abstract: Industrial visual inspection systems increasingly rely on deep classifiers whose heatmap explanations may appear visually plausible while failing to i
arXiv:2605.05686v2 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM). We
arXiv:2605.14231v1 Announce Type: cross Abstract: Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have b
arXiv:2603.14851v3 Announce Type: replace Abstract: Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding.
arXiv:2605.14461v1 Announce Type: new Abstract: Existing object removal tools often rely on manual masks or text prompts, making precise removal difficult for non-expert users in complex scenes and of
arXiv:2605.14752v1 Announce Type: cross Abstract: Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distr
arXiv:2605.14171v1 Announce Type: new Abstract: Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usual
arXiv:2605.14546v1 Announce Type: new Abstract: Recent advances in neural operators have made partial differential equation (PDE) surrogate modeling increasingly scalable and transferable through larg
arXiv:2605.15116v1 Announce Type: new Abstract: Large-scale labelled driving video data is essential for training autonomous driving systems. Although simulation offers scalable and fully annotated da
arXiv:2605.15179v1 Announce Type: cross Abstract: Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of d
arXiv:2605.14513v1 Announce Type: cross Abstract: Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the
arXiv:2605.14821v1 Announce Type: new Abstract: Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit
arXiv:2605.14487v1 Announce Type: cross Abstract: Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover
arXiv:2602.04585v2 Announce Type: replace Abstract: We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that ha
arXiv:2511.15407v3 Announce Type: replace Abstract: Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarl
arXiv:2605.14907v1 Announce Type: new Abstract: Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure.
arXiv:2605.14301v1 Announce Type: new Abstract: Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant sou
arXiv:2604.05306v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We st
arXiv:2509.01416v2 Announce Type: replace Abstract: The computational overhead of traditional numerical solvers for partial differential equations (PDEs) remains a critical bottleneck for large-scale
arXiv:2605.14120v1 Announce Type: cross Abstract: Geospatial foundation models compress multispectral observations into dense embeddings increasingly used in natural-language environmental reasoning s
arXiv:2602.00520v3 Announce Type: replace Abstract: Event stream data often exhibit hierarchical structure in which multiple events co-occur, resulting in a sequence of multisets (i.e., bags of events
arXiv:2601.22197v3 Announce Type: replace-cross Abstract: Generating clinical reports that summarize abnormal patterns, diagnostic findings, and clinical interpretations from long-term EEG recordings