Knowledge catalogue
NEW WORLD MODEL: @ylecun's team is back with an efficient model! This project involves @ylecun, @lukaskuhn77, @lucasmaes_, @quentinlldc, and @randall_balestr. A couple definitions first: - DINO: self-
arXiv:2512.00234v3 Announce Type: replace Abstract: There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. How
arXiv:2608.27882v1 Announce Type: new Abstract: Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current
arXiv:2608.28216v1 Announce Type: new Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is abs
arXiv:2608.26506v1 Announce Type: cross Abstract: Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior wo
arXiv:2608.27226v1 Announce Type: new Abstract: We introduce a self-supervised framework for learning joint visuospatial representations from RGB-D observations. While modern vision foundation models
arXiv:2608.26962v1 Announce Type: new Abstract: Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecu
arXiv:2608.26334v1 Announce Type: new Abstract: Automated theorem proving offers a natural foundation for recursive self-improvement in scientific discovery. However, existing neural provers do not fu
arXiv:2608.27033v1 Announce Type: new Abstract: We introduce Riemann-1.0, a fully causal autoregressive World Action Model for embodied intelligence. Riemann-1.0 jointly models multi-view visual obser
arXiv:2608.26958v1 Announce Type: cross Abstract: Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger s
arXiv:2608.26973v1 Announce Type: new Abstract: Pre-training under limited data requires a different view of scaling than web-scale language modeling. With a fixed data budget but relatively abundant
arXiv:2608.27190v1 Announce Type: new Abstract: Accurate 3D segmentation of cone-beam CT (CBCT) is critical for interventional and radiation therapy applications, yet it remains limited by two compoun
arXiv:2608.26655v1 Announce Type: new Abstract: Model merging promises to construct a single multi-task model from independently fine-tuned task models without accessing the original task data. This m
arXiv:2608.25956v1 Announce Type: new Abstract: Current world action models (WAMs) typically operate on 2D visual data. These models can achieve exceptional visual quality, but they lack explicit spat
arXiv:2502.02118v2 Announce Type: replace-cross Abstract: Self-supervised learning has been a powerful approach for learning meaningful representations from unlabeled data across various domains, redu
arXiv:2608.25692v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) is an intriguing open-world problem that has garnered increasing attention: given partially labelled data, the goal
arXiv:2608.25109v1 Announce Type: cross Abstract: Whole-heart segmentation from CT and MRI is essential for quantitative cardiac image analysis, but remains challenging under multi-center and multi-mo
arXiv:2608.25757v1 Announce Type: cross Abstract: Generalist vision--language--action (VLA) policies learn long-horizon behavior mainly through short-horizon action prediction and reveal little beyond
arXiv:2608.25648v1 Announce Type: new Abstract: Dynamic contrast-enhanced breast MRI is central to cancer diagnosis and monitoring, but requires gadolinium-based contrast agents. In this work, we addr
arXiv:2608.25903v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) is an effective approach to machine learning over multi-table relational databases. In RDL, a database is modeled as a
arXiv:2608.24931v1 Announce Type: cross Abstract: Multimodal neuroimaging combining structural MRI and positron emission tomography (PET) captures complementary structure-function relationships across
arXiv:2608.25924v1 Announce Type: new Abstract: This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning ma
arXiv:2608.24482v1 Announce Type: cross Abstract: Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative appro
arXiv:2608.23850v1 Announce Type: new Abstract: Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-vi
arXiv:1812.00877v2 Announce Type: replace Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant melanoma,
arXiv:2608.24723v1 Announce Type: new Abstract: Retinal fundus photography is widely used for screening and monitoring ocular diseases, but many modern classification pipelines rely on deep latent rep
arXiv:2608.23831v1 Announce Type: cross Abstract: While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist
arXiv:2608.24068v1 Announce Type: new Abstract: Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, m
arXiv:2608.24136v1 Announce Type: new Abstract: Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reaso
arXiv:2509.18778v2 Announce Type: replace-cross Abstract: Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly fo
arXiv:2608.21712v1 Announce Type: new Abstract: Transformer-based models are widely used for clinical prediction from electronic health records (EHRs), yet their architectures still require substantia
arXiv:2608.21427v1 Announce Type: new Abstract: Tuberculosis (TB) is one of the most common and dangerous bacterial ailments. Every year, it causes a large number of deaths worldwide. Although many de
arXiv:2608.23486v1 Announce Type: new Abstract: World action models (WAMs) have recently gained increasing attention as a framework for jointly modeling scene evolution and ego actions in autonomous d
arXiv:2506.00209v3 Announce Type: replace-cross Abstract: Population health management requires scalable methods to identify individuals at risk of chronic diseases such as cardiovascular conditions a
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at hand
arXiv:2608.20561v1 Announce Type: cross Abstract: Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensiv
Standard constrained RL assumes consequences are immediate and attributable to the current action. This breaks down whenever violations are delayed and stochastic, which is most real-world settings yo
arXiv:2608.20557v1 Announce Type: new Abstract: Domain shift across clinical centers using different imaging hardware or acquisition protocols remains a fundamental barrier to deploying deep learning
arXiv:2608.20659v1 Announce Type: new Abstract: Methods that transfer predictions from two-dimensional foundation models into three-dimensional segmentation are commonly grouped by task or representat
arXiv:2608.20639v1 Announce Type: new Abstract: Multi-View Pedestrian Detection (MVPD) aims to detect pedestrians in the form of a bird's eye view map from multi-view images. Recent MVPD methods adopt
arXiv:2608.20418v1 Announce Type: cross Abstract: We introduce Malaria-Instruct, a curated instruction-following dataset derived from the ChEMBL Legacy Malaria corpus for Malaria virtual screening, an
arXiv:2608.20430v1 Announce Type: new Abstract: World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagin
arXiv:2608.20918v1 Announce Type: new Abstract: Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain exist
arXiv:2608.20181v1 Announce Type: cross Abstract: Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on
arXiv:2602.18400v3 Announce Type: replace-cross Abstract: Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in c
arXiv:2608.19323v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is essential for the safe deployment of large language models (LLMs). Existing methods, from verbalized confidence to
arXiv:2603.18853v3 Announce Type: replace-cross Abstract: Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things networks, but their trajectories couple nonli
arXiv:2608.19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL. One promising approach
arXiv:2608.19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead. However
arXiv:2606.15654v2 Announce Type: replace-cross Abstract: Real-world robot task planning must operate under both stochastic action execution and partial observability, yet constructing Partially Obser
arXiv:2608.19710v1 Announce Type: cross Abstract: Reliable underwater robotic perception remains difficult because optical imagery degrades under turbidity, wavelength-dependent attenuation, low illum
arXiv:2512.00691v2 Announce Type: replace Abstract: Gait patterns play a critical role in human identification and healthcare analytics, yet current progress remains constrained by small, narrowly des
The sense of touch is the most criminally under-explored modality in robotics. Imagine doing sleight of hand wearing thick oven mitts. That's exactly how a robot feels today if it were alive. A magnet
arXiv:2608.18230v1 Announce Type: new Abstract: Looped language models improve reasoning and knowledge manipulation by applying shared computation repeatedly. Existing systems usually repeat an entire
arXiv:2608.19000v1 Announce Type: new Abstract: Automating graphic design synthesis from user-provided elements requires both a coherent overall composition and the exact preservation of each asset. E
arXiv:2608.19080v1 Announce Type: new Abstract: Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD)
arXiv:2608.18667v1 Announce Type: new Abstract: Modern deep learning architectures have demonstrated strong performance in dental CBCT segmentation. One remaining crucial challenge is accurate tooth l
arXiv:2608.18984v1 Announce Type: new Abstract: Museum and archival datasets do not mirror historical artistic production, but materialize the contingent histories of collecting, preservation, catalog
arXiv:2608.17453v1 Announce Type: new Abstract: Long-horizon humanoid vision--language--action (VLA) control with head-mounted stereo cameras requires visual interfaces that can exploit complementary
arXiv:2608.17843v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model beh