Knowledge catalogue
arXiv:2607.01145v1 Announce Type: new Abstract: Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distri
arXiv:2607.00223v1 Announce Type: new Abstract: Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of
arXiv:2603.27757v2 Announce Type: replace Abstract: Event-based cameras capture visual information as asynchronous streams of per-pixel brightness changes, generating sparse, temporally precise data.
arXiv:2607.00545v1 Announce Type: new Abstract: Controllable traffic simulation is critical for testing autonomous driving systems, yet existing approaches often require retraining large generative mo
arXiv:2607.00958v1 Announce Type: new Abstract: Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self
arXiv:2607.00409v1 Announce Type: new Abstract: Medical image segmentation relies on the ability of encoder-decoder architectures to translate rich feature representations into accurate pixel-level pr
arXiv:2606.30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks. We present BEST-RQ-2, an evolution of BEST-RQ that reta
arXiv:2606.31126v1 Announce Type: new Abstract: Predicting biomolecular properties from limited labeled data is a central bottleneck in protein engineering and small-molecule design. As strong pretrai
arXiv:2606.28578v1 Announce Type: cross Abstract: Closed-loop materials discovery iterates between proposing candidate structures and evaluating their properties, and property evaluation dominates the
arXiv:2601.18778v3 Announce Type: replace-cross Abstract: RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigat
arXiv:2606.29463v1 Announce Type: new Abstract: Recent advances in pathology foundation models have substantially improved patch and slide level representation learning from whole-slide images (WSIs).
arXiv:2606.29198v1 Announce Type: new Abstract: As the most perceptually powerful Face Video Super-Resolution (FVSR) method, existing works in Generative FVSR (GFVSR) mainly exploit the generative pri
arXiv:2603.25144v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong
arXiv:2606.29948v1 Announce Type: new Abstract: Tactile sensors are inherently heterogeneous: a model trained on one sensor cannot be directly used on another, which limits learning contact-rich manip
arXiv:2602.15257v3 Announce Type: replace-cross Abstract: We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-docum
arXiv:2603.17576v3 Announce Type: replace Abstract: Precise localization and delineation of brain tumors using magnetic resonance imaging (MRI) are essential for planning therapy and guiding surgical
arXiv:2606.18066v2 Announce Type: replace Abstract: We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving
arXiv:2606.30360v1 Announce Type: cross Abstract: The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized m
arXiv:2512.20606v2 Announce Type: replace Abstract: Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the
arXiv:2606.29579v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substant
arXiv:2409.00654v2 Announce Type: replace Abstract: We introduce Seed-to-Seed Translation (StS), a novel approach that combines GANs and diffusion models (DMs) for unpaired Image-to-Image Translation.
arXiv:2606.29901v1 Announce Type: cross Abstract: Sound event detection (SED) is a core module for acoustic environmental analysis, yet its performance is often limited by scarce labeled data. Recent
arXiv:2606.28626v1 Announce Type: new Abstract: Sign language translation (SLT) remains challenging due to its high spatio-temporal complexity, long sequences, and the need to model multiple articulat
arXiv:2602.23353v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model
arXiv:2606.29162v1 Announce Type: new Abstract: Self-supervised learning (SSL) currently drives state-of-the-art performance in no-reference image quality assessment (NR-IQA). However, standard SSL pi
arXiv:2606.29933v1 Announce Type: new Abstract: The alignment of language models is typically studied through the lens of capability benchmarks, but the dynamics of how models change during post-train
arXiv:2606.27935v1 Announce Type: new Abstract: Deep learning has demonstrated remarkable success in high-throughput histopathology image analysis. However, the performance of learning-based models cr
arXiv:2606.28323v1 Announce Type: cross Abstract: Dexterous manipulation policies can solve individual skills, but composing them to perform multiple tasks with a single hand remains challenging. Addi
arXiv:2603.03710v3 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-pos
arXiv:2606.27752v1 Announce Type: new Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. While recent gen
arXiv:2606.28077v1 Announce Type: new Abstract: In real-world deployments, scene text detectors inevitably face distribution shifts beyond the training distribution. Prior work often depends on large-
arXiv:2606.27014v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have recently emerged as a promising paradigm for world modeling by learning predictive dynamics in a l
arXiv:2606.27304v1 Announce Type: new Abstract: Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engine
arXiv:2606.27084v1 Announce Type: new Abstract: Reliable organ localization in abdominal CT can provide spatial priors for downstream trauma analysis. We propose CT-3GDINO, a lightweight 3D detector t
arXiv:2606.27345v1 Announce Type: new Abstract: Modern video diffusion transformers position their tokens through RoPE on the (u,v,t) axes -- a description of the camera's sampling grid that says noth
arXiv:2606.27305v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise ex
arXiv:2510.11047v2 Announce Type: replace Abstract: Laryngeal cancer imaging research lacks standardised public datasets to enable reproducible deep learning (DL) model development. We present Larynge
arXiv:2606.25579v1 Announce Type: cross Abstract: Background: Response to neoadjuvant imatinib in gastrointestinal stromal tumors (GISTs) is highly variable and cannot be reliably predicted using curr
arXiv:2606.24984v1 Announce Type: cross Abstract: Learning representations that remain robust across centuries of variation in handwriting is a key challenge in diachronic representation learning. Tak
arXiv:2606.17945v2 Announce Type: replace Abstract: Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although p
arXiv:2606.24962v1 Announce Type: new Abstract: Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions
arXiv:2606.24120v1 Announce Type: new Abstract: Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB ima
arXiv:2606.24669v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direc
arXiv:2606.23566v2 Announce Type: replace Abstract: Language-specific tokenizers improve tokenization quality and the downstream performance of models on those languages. However, using such a tokeniz
arXiv:2606.24138v1 Announce Type: new Abstract: Generating explicit 3D city assets from a single satellite image is important for digital twins, urban simulation, and geospatial intelligence. Unlike s
arXiv:2606.24477v1 Announce Type: cross Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolu
arXiv:2606.21014v1 Announce Type: new Abstract: Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives speci
arXiv:2606.20812v1 Announce Type: new Abstract: EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical an
arXiv:2606.23626v1 Announce Type: new Abstract: Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstre
arXiv:2606.21030v1 Announce Type: cross Abstract: Diffusion-based image compression methods, leveraging powerful generative priors, have demonstrated remarkable perceptual quality at ultra-low bitrate
arXiv:2509.25665v2 Announce Type: replace Abstract: Sparse neural network methods typically assume that the target sparsity (or density) is fixed in advance, even though the relationship between netwo
arXiv:2606.20729v1 Announce Type: cross Abstract: Quantum chemistry simulations underpin modern materials discovery, yet their impact is limited by steep computational cost and dependence on fixed app
arXiv:2606.22400v1 Announce Type: new Abstract: This study introduces a computationally efficient convolutional neural network (CNN) architecture enhanced with transfer learning for multi-cancer detec
arXiv:2606.20673v1 Announce Type: cross Abstract: A central challenge in EEG authentication is that models are typically tied to the acquisition settings in which they are trained. In particular, vari
arXiv:2606.17276v3 Announce Type: replace-cross Abstract: Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been
arXiv:2602.03531v2 Announce Type: replace-cross Abstract: Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain le
arXiv:2606.21786v1 Announce Type: new Abstract: We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-c
arXiv:2606.14150v2 Announce Type: replace Abstract: Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5-
arXiv:2606.21973v1 Announce Type: new Abstract: Physiological signals such as EEG, ECG, and PPG are widely used in clinical monitoring. Recent self-supervised learning (SSL) methods offer an attractiv
arXiv:2606.20670v1 Announce Type: new Abstract: Wireless foundation models offer a path toward reusable channel state information (CSI) intelligence for sixth-generation (6G) systems. However, existin