Knowledge catalogue
arXiv:2511.06331v2 Announce Type: replace Abstract: Detailed structural and species information on individual tree level is increasingly important to support precision forestry, biodiversity conservat
arXiv:2606.04191v1 Announce Type: cross Abstract: We describe our approach to the CTF4Science Lorenz challenge, a benchmark that mixes short-horizon forecasting, long-time distribution matching, and t
arXiv:2606.04171v1 Announce Type: cross Abstract: File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing. Learned systems such
arXiv:2606.04414v1 Announce Type: new Abstract: Multi-view cardiac magnetic resonance (CMR) imaging provides complementary anatomical information and is widely used for noninvasive disease assessment.
Nemotron 3 Ultra (550B-A55B) is here - our strongest open-weight model and full training recipe to date. Heavy emphasis on real-world inference efficiency for long-context agentic workloads. Everythin
arXiv:2602.01083v2 Announce Type: replace Abstract: Weight-space learning studies neural architectures that operate directly on the parameters of other neural networks. Motivated by the growing availa
arXiv:2606.04680v1 Announce Type: cross Abstract: Automatic speech recognition systems commonly rely on reference transcriptions for evaluation, while reference-free approaches often depend on interna
arXiv:2606.04706v1 Announce Type: new Abstract: AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable
arXiv:2502.01576v2 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce h
arXiv:2511.16624v2 Announce Type: replace-cross Abstract: We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single i
arXiv:2512.08094v2 Announce Type: replace Abstract: The goal of this work is to develop a universal approach for aligning subtitles (i.e., spoken language text with corresponding timestamps) to contin
arXiv:2603.02697v2 Announce Type: replace-cross Abstract: This paper presents ShareVerse, a video generation framework enabling multi-agent shared world modeling, addressing the gap in existing works
arXiv:2606.04511v1 Announce Type: new Abstract: Sparse attention reduces compute and memory bandwidth for long-context LLM inference. However, two key challenges remain: (1) KV cache capacity still gr
arXiv:2606.04271v1 Announce Type: cross Abstract: Autonomous driving has shifted from modular perception-prediction-planning stacks toward end-to-end (E2E) models that map sensor inputs directly to ve
arXiv:2606.04564v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have made rapid progress in standard classification and regression, but time-to-event survival prediction tasks have re
arXiv:2606.04798v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and senso
arXiv:2606.05058v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD resea
arXiv:2606.04708v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI d
arXiv:2606.03148v1 Announce Type: new Abstract: Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we
arXiv:2606.02809v1 Announce Type: new Abstract: Evaluating vision-language models (VLMs) on medical images requires benchmarks that are clinically grounded, scalable, and controlled for evaluation con
arXiv:2606.02937v1 Announce Type: cross Abstract: Multi-view video recordings are increasingly used to capture the 3D movements of animals in experimental settings, yet extracting rich 3D representati
arXiv:2606.03795v1 Announce Type: new Abstract: Vision-language models map visual features into a shared embedding space through learned projection layers, yet it remains unclear how these transformat
arXiv:2606.02947v1 Announce Type: cross Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that
arXiv:2606.03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks ca
arXiv:2606.02605v1 Announce Type: cross Abstract: Coronary artery stenosis is a common cardiovascular disease, with severe, untreated cases posing significant risks of heart attack. Although coronary
arXiv:2603.01576v3 Announce Type: replace Abstract: Geo-Foundation Models (GFMs) have been evaluated across diverse Earth observation task including multiple domains and have demonstrated strong poten
arXiv:2510.01377v2 Announce Type: replace-cross Abstract: In this paper, we propose DeMuon, a method for decentralized matrix optimization over a given communication topology. DeMuon incorporates matr
arXiv:2606.03899v1 Announce Type: new Abstract: Muon has recently demonstrated strong empirical performance in large language model training, but the theoretical role of momentum in Muon remains uncle
arXiv:2606.03114v1 Announce Type: new Abstract: Remote sensing change detection for real-world monitoring often relies on imperfect heterogeneous observations, where pre- and post-event images may be
arXiv:2606.02920v1 Announce Type: new Abstract: Language-model unlearning updates a trained model to behave as if it had not seen selected training examples, while preserving utility and avoiding cost
arXiv:2606.03460v1 Announce Type: new Abstract: Underground coal mining requires personnel and heavy equipment to operate within shared, confined, and poorly illuminated spaces where hazards such as e
arXiv:2606.02764v1 Announce Type: new Abstract: Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coasta
arXiv:2606.02962v1 Announce Type: cross Abstract: Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-fo
arXiv:2606.03338v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard p
arXiv:2606.02914v1 Announce Type: new Abstract: Background: Oral diseases affect nearly 3.5 billion people worldwide, yet the comparative clinical potential of large-scale AI models in dentistry remai
arXiv:2606.02996v1 Announce Type: cross Abstract: Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR
arXiv:2606.03990v1 Announce Type: cross Abstract: We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables
arXiv:2606.02778v1 Announce Type: cross Abstract: I present EXOVEIL, a transit detection system that learns what a star's brightness should look like and flags when reality disagrees. Unlike existing
arXiv:2606.03943v1 Announce Type: new Abstract: Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generaliz
arXiv:2606.02823v1 Announce Type: new Abstract: Two-bit weight quantization is attractive for memory-efficient LLM inference, but the standard W2 level set {-2,-1,0,+1} often collapses under aggressiv
arXiv:2606.03201v1 Announce Type: cross Abstract: Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of dom
arXiv:2606.03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which molecular representation to use. We present a sys
arXiv:2606.03074v1 Announce Type: new Abstract: Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wirele
arXiv:2606.03359v1 Announce Type: cross Abstract: Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on l
arXiv:2606.03297v1 Announce Type: new Abstract: Humanoid loco-manipulation requires stable whole-body control under varying object masses and pickup/placement heights. This becomes particularly challe
arXiv:2606.03314v1 Announce Type: new Abstract: High-fidelity semantic 3D scene representations are crucial for numerous applications, including robotics, autonomous driving, and simulation. Beyond th
arXiv:2606.02911v1 Announce Type: new Abstract: Current research primarily focuses on model performance, while comparatively less attention has been devoted to uncertainty estimation, particularly in
arXiv:2606.03321v1 Announce Type: new Abstract: Artificial-intelligence surrogates can support second-by-second thermal-hydraulic forecasting, but models selected and frozen offline may become conditi
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing mergi
arXiv:2606.03837v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) and probing enable adaptation of foundation models using only a small number of trainable parameters, making it a
arXiv:2503.15639v2 Announce Type: replace-cross Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively exp
arXiv:2606.01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task. Recent multimodal vision-language models have produced systems that admit textual
arXiv:2508.10312v2 Announce Type: replace Abstract: Recommender systems in concert with Large Language Models (LLMs) present promising avenues for generating semantically-informed recommendations. How
arXiv:2602.02470v2 Announce Type: replace Abstract: Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical r
arXiv:2510.19496v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks. This inflates visua
arXiv:2606.01995v1 Announce Type: new Abstract: We introduce CARTE 1 (Culturally Anchored Regional-Territorial Evaluation), a multiplechoice benchmark for evaluating the ability of large language mode
arXiv:2506.22881v3 Announce Type: replace Abstract: Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weig
arXiv:2606.01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effe
arXiv:2606.02289v1 Announce Type: new Abstract: Existing hallucination taxonomies classify LLM errors by what is wrong with the output -- memorised misconceptions, reasoning failures, fluent fabricati
arXiv:2606.02002v1 Announce Type: new Abstract: Blind image quality assessment (BIQA) aims to predict perceived image quality without access to a reference image. Classical natural scene statistics (N