Knowledge catalogue
arXiv:2605.11644v1 Announce Type: cross Abstract: We study positive-data learning of bounded-fan-out linear multiple context-free grammars under a fixed explicit finite monoid homomorphism (h). The ma
arXiv:2605.11001v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) are a simple surrogate-modelling paradigm for partial differential equations, but their standard strong-form re
arXiv:2605.11869v1 Announce Type: new Abstract: While the overall inference latency of Video Diffusion Transformers (DiTs) can be substantially reduced through model distillation, per-step inference l
arXiv:2504.14707v3 Announce Type: replace Abstract: We introduce FLAME (FLemish Accounts of Momentary Experiences), a new corpus of nearly 25,000 daily personal narratives in Belgian-Dutch (Flemish),
arXiv:2511.14715v3 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who
arXiv:2512.07150v2 Announce Type: replace-cross Abstract: Deep generative models are powerful priors for imaging inverse problems, but training-free solvers for latent flow models face a practical fin
arXiv:2605.11756v1 Announce Type: new Abstract: Monocular depth foundation models generalize well across scenes, yet they are typically optimized with uniform pixel-wise objectives that do not disting
arXiv:2506.19417v2 Announce Type: replace Abstract: Cooperative multi-agent reinforcement learning (MARL) under sparse rewards remains fundamentally challenging because agents often fail to concentrat
arXiv:2605.11048v1 Announce Type: new Abstract: Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remai
arXiv:2605.11144v1 Announce Type: new Abstract: We introduce Forecast-aware Gaussian Splatting (Forecast-GS), a predictive 3D representation framework for language-conditioned robotic manipulation. Wh
arXiv:2505.11356v4 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) relies on semantically consistent graph augmentations, but common local perturbations provide limited control over
arXiv:2605.11416v1 Announce Type: new Abstract: Selective layer-wise updates are essential for low-cost continued pre-training of Large Language Models (LLMs), yet determining which layers to freeze o
arXiv:2605.11613v1 Announce Type: new Abstract: On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback
arXiv:2605.12259v1 Announce Type: new Abstract: Image hashing provides compact representations for efficient storage and retrieval but is inherently limited to global comparison and cannot reason abou
arXiv:2605.12167v1 Announce Type: cross Abstract: Video generation models offer a promising imagination mechanism for robot manipulation by predicting long-horizon future observations, but effectively
arXiv:2605.12358v1 Announce Type: new Abstract: Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of moder
arXiv:2605.12303v1 Announce Type: cross Abstract: High-quality labeled data is essential for training robust machine learning models, yet obtaining annotations at scale remains expensive. AI-assisted
arXiv:2602.00297v2 Announce Type: replace Abstract: Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Laten
arXiv:2511.15572v2 Announce Type: replace Abstract: Feature-map knowledge distillation (KD) transfers internal representations well between comparably sized Vision Transformers (ViTs), but it often fa
arXiv:2605.11176v1 Announce Type: cross Abstract: We present a neural-network-based data processing pipeline for Baikal-GVD, designed to improve event reconstruction quality and accelerate neutrino ca
arXiv:2605.11951v1 Announce Type: new Abstract: Although robotic manipulation has made significant progress, reliable execution remains challenging because task failures are inevitable in dynamic and
arXiv:2605.11774v1 Announce Type: new Abstract: By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction t
arXiv:2605.12497v1 Announce Type: new Abstract: Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for
arXiv:2502.19716v2 Announce Type: replace Abstract: Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source
arXiv:2605.12161v1 Announce Type: new Abstract: Fused Gromov-Wasserstein (FGW) distances provide a principled framework for comparing objects by jointly aligning structure and node features. However,
arXiv:2605.12451v1 Announce Type: new Abstract: Continual Panoptic Segmentation (CPS) requires methods that can quickly adapt to new categories over time. The nature of this dense prediction task mean
arXiv:2605.12309v1 Announce Type: new Abstract: The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. I
arXiv:2605.12431v1 Announce Type: new Abstract: Conventional gait de-identification methods often encounter an inherent trade-off: they either provide insufficient identity suppression or introduce sp
arXiv:2605.11863v1 Announce Type: new Abstract: Automated analysis of building facades from street-level imagery has great potential for urban analytics, energy assessment, and emergency planning. How
arXiv:2605.11853v1 Announce Type: cross Abstract: Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that pr
arXiv:2605.11276v1 Announce Type: new Abstract: Highway construction workers face a high risk of serious injury or death. Image-based training materials depicting hazardous scenarios are essential for
arXiv:2605.11531v1 Announce Type: cross Abstract: Physics-based climate projections using general circulation models are essential for assessing future risks, but their coarse resolution limits region
arXiv:2605.11414v1 Announce Type: new Abstract: While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial pre
arXiv:2602.17739v3 Announce Type: replace-cross Abstract: Long-context DNA models are limited by token-mixing cost and by how compression allocates representational budget across the genome. Existing
arXiv:2605.12426v1 Announce Type: new Abstract: How do transformer language models memorize factual associations? A common view casts internal weight matrices as associative memories over pairs of emb
arXiv:2605.11645v1 Announce Type: cross Abstract: Herding -- where agents align their behaviors and act collectively -- is a central driver of market fragility and systemic risk. Existing approaches t
arXiv:2605.12399v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to sever
arXiv:2605.11541v1 Announce Type: new Abstract: Geoscience intelligence is expected to understand, reason about, and predict earth system changes to support human decision-making in critical domains s
arXiv:2605.12299v1 Announce Type: new Abstract: Recent works have analyzed the impact of individual components of neural networks on gendered predictions, often with a focus on mitigating gender bias.
arXiv:2305.12678v3 Announce Type: replace Abstract: Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-
arXiv:2605.11838v1 Announce Type: new Abstract: Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat al
arXiv:2605.11347v1 Announce Type: cross Abstract: Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to determi
arXiv:2605.11117v1 Announce Type: new Abstract: Scientific discovery can be modeled as a sequence of probabilistic decisions that map physical problems to numerical solutions. Recent agentic AI system
arXiv:2605.11706v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This re
arXiv:2512.01675v2 Announce Type: replace Abstract: Text-to-image flow matching transformers degrade sharply in long-tail settings: tail-class outputs collapse in fidelity and diversity, limiting thei
arXiv:2605.12327v1 Announce Type: new Abstract: A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scal
arXiv:2605.06152v2 Announce Type: replace-cross Abstract: Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the 'Slingshot Mechanism.' Ex
arXiv:2605.11616v1 Announce Type: new Abstract: Functional affordance grounding requires more than recognizing an object: an agent must localize the specific region that supports an interaction, such
arXiv:2503.06139v2 Announce Type: replace Abstract: Pairwise LLM-as-a-judge evaluation asks the judge to identify the better of two candidate answers. We study a one-line modification that asks for th
arXiv:2605.12369v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Exist
arXiv:2605.11355v1 Announce Type: new Abstract: Inventory-policy comparisons are often difficult to interpret because performance depends on the evaluation contract as much as on the policy itself. Di
arXiv:2605.11871v1 Announce Type: new Abstract: Training-free camera control for pretrained flow-matching video generators is a partial-observation inverse problem: a depth-warped guidance video suppl
arXiv:2605.11967v1 Announce Type: new Abstract: Hierarchical 3D grouping aims to recover scene groups across multiple granularities, from fine object parts to complete objects, without relying on sema
arXiv:2605.12252v1 Announce Type: new Abstract: Metal artifacts in computed tomography (CT) severely degrade image quality, compromising diagnostic accuracy and radiotherapy planning, especially in ca
arXiv:2605.11383v1 Announce Type: new Abstract: In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural n
arXiv:2601.20255v2 Announce Type: replace-cross Abstract: SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabil
arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini
arXiv:2605.11130v1 Announce Type: new Abstract: Critical events in multivariate time series, from turbine failures to cardiac arrhythmias, demand accurate prediction, yet labeled data is scarce becaus
arXiv:2605.11208v1 Announce Type: new Abstract: Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain chall
arXiv:2605.11651v1 Announce Type: cross Abstract: Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the fi