Knowledge catalogue
arXiv:2610.14031v1 Announce Type: cross Abstract: Modern data pipelines increasingly combine human-created and human-curated data with AI-generated data for model training and evaluation. As datasets
arXiv:2610.17605v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting (3DGS) codecs report reconstruction quality after compression, and give users little control over the distortion of indiv
arXiv:2605.24273v2 Announce Type: replace Abstract: Automated detection and masking of individual methane plumes from satellite imagery is important for operational emission attribution and quantifica
arXiv:2610.15548v1 Announce Type: new Abstract: Quadruped robots deployed for inspection and field missions must cross heterogeneous terrain, from stairs, slopes, and gaps to high platforms, stepping
arXiv:2610.15537v1 Announce Type: cross Abstract: Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating
arXiv:2610.17991v1 Announce Type: new Abstract: Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an
arXiv:2610.17409v1 Announce Type: new Abstract: We argue that cooperative multi-agent reinforcement learning (MARL) should treat test-time coordination as part of the problem definition rather than a
arXiv:2610.17788v1 Announce Type: new Abstract: Distributional critics model the full return distribution, providing richer signals for exploration and risk-sensitive control. Recent work has shown th
arXiv:2610.13994v1 Announce Type: cross Abstract: Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an int
arXiv:2610.14409v1 Announce Type: new Abstract: Generating an image with a diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That compu
arXiv:2509.19774v3 Announce Type: replace Abstract: Electrocardiography (ECG) is the clinical gold standard for cardiovascular disease (CVD) assessment, yet continuous monitoring is constrained by the
arXiv:2610.16980v1 Announce Type: cross Abstract: Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry profes
arXiv:2610.13991v1 Announce Type: new Abstract: Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only af
arXiv:2610.14864v1 Announce Type: new Abstract: Action chunking improves temporal coherence in visuomotor imitation learning by jointly predicting sequences of future actions. However, many existing p
arXiv:2610.16809v1 Announce Type: cross Abstract: This study addresses the prediction of audio popularity on an online sharing platform by leveraging both metadata and acoustic feature representations
arXiv:2610.16983v1 Announce Type: cross Abstract: Most prior work on predicting mental health help-seeking treats it as post-hoc classification of users already active in clinical communities, which c
arXiv:2404.16914v2 Announce Type: replace Abstract: MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing paramet
arXiv:2610.14904v1 Announce Type: new Abstract: We study prediction with expert advice over T rounds with K experts under heavy-tailed losses whose (1+epsilon)-moment is bounded by heta>0 for some eps
arXiv:2610.15709v1 Announce Type: new Abstract: Linear attention and recurrent models compress past tokens into a fixed-size state that is updated at every step. However, storing these states in high
arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning
arXiv:2610.13982v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have emerged as an effective paradigm for scaling large language models, yet their massive parameter footprint poses sev
arXiv:2610.14770v1 Announce Type: new Abstract: Multimodal contrastive learning typically relies on manually specified scoring functions, such as cosine similarity, to quantify the similarity between
arXiv:2610.18389v1 Announce Type: new Abstract: Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with h
arXiv:2610.14704v1 Announce Type: new Abstract: Coupling a pretrained vision-language model (VLM) with a diffusion or flow-matching action expert has become the mainstream vision-language-action (VLA)
arXiv:2610.14091v1 Announce Type: new Abstract: Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting t
arXiv:2610.18054v1 Announce Type: cross Abstract: Anti-money laundering (AML) in financial networks requires modeling transaction patterns that span multiple institutions. In practice, however, banks
arXiv:2610.14894v1 Announce Type: new Abstract: We present a robust deep generative framework for unsupervised image prototype discovery, built on a heavy-tailed Student's t mixture prior, that bridge
arXiv:2610.16967v1 Announce Type: new Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real
arXiv:2610.18683v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (
arXiv:2610.15983v1 Announce Type: new Abstract: In this work we present a probabilistic model for predicting the temporal evolution of wildfire size using conditional generative algorithms, namely flo
arXiv:2610.14942v1 Announce Type: new Abstract: Bilevel data selection is a fundamental task with numerous applications in machine learning and statistics. A common strategy for tackling this problem
arXiv:2610.16327v1 Announce Type: new Abstract: Bubbly flows involve strongly coupled bubble motion, deformation, and hydrodynamic interactions, making high-fidelity simulation computationally expensi
arXiv:2610.17016v1 Announce Type: new Abstract: Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional cla
arXiv:2601.13155v3 Announce Type: replace-cross Abstract: Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token
arXiv:2603.19844v3 Announce Type: replace Abstract: Multimodal MRI provides complementary information for brain tumor segmentation, but high accuracy alone does not reveal whether a model relies on cl
arXiv:2610.18331v1 Announce Type: cross Abstract: Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic? We decompose c
arXiv:2604.02341v2 Announce Type: replace Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers
arXiv:2610.16287v1 Announce Type: new Abstract: Automated visual inspection is essential for efficient repair and recycling of metallic components. AI-based defect detection is a strong fit. However,
arXiv:2610.15614v1 Announce Type: new Abstract: Multi-label learning typically pursues model construction through the joint optimization of label fitting, correlation modeling, and structural regulari
arXiv:2610.16134v1 Announce Type: new Abstract: Dataset distillation (DD) aims to retain the training utility of a large dataset in a much smaller set of examples. For skeleton-based action recognitio
arXiv:2602.21189v3 Announce Type: replace Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-a
arXiv:2610.16592v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) is commonly used to enhance the capabilities of large language models (LLMs) in solving complex multi-turn tasks.
arXiv:2610.14654v1 Announce Type: new Abstract: Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future.
arXiv:2610.15286v1 Announce Type: new Abstract: The accuracy of detecting protein crystals for fluorescence microscopy images is very critical for high throughput and automated systems. Although the t
arXiv:2610.17265v1 Announce Type: new Abstract: Federated learning allows hospitals to train a shared mortality model without pooling their records, but published comparisons of aggregation strategies
arXiv:2610.18481v1 Announce Type: new Abstract: Protein sequence, structure, and functional annotations each capture complementary aspects of protein biology, yet existing tokenizers encode each modal
arXiv:2610.15669v1 Announce Type: new Abstract: Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensi
arXiv:2509.13705v2 Announce Type: replace-cross Abstract: Machine learning (ML) holds great promise for extracting insights from complex quantum many-body data obtained in quantum experiments, potenti
arXiv:2610.15294v1 Announce Type: new Abstract: Evaluating robot manipulation policies through repeated physical trials is costly. We study whether an action-conditioned world model can serve as a clo
arXiv:2610.17667v1 Announce Type: new Abstract: Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the
arXiv:2610.13989v1 Announce Type: cross Abstract: Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-base
arXiv:2610.14737v1 Announce Type: new Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate a
arXiv:2610.17936v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics wit
arXiv:2610.14698v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models have achieved remarkable progress through large-scale training and strong learned priors. However, they remain fra
arXiv:2610.14840v1 Announce Type: new Abstract: We present a learning-based framework that enables a full-scale bipedal humanoid to sprint at over 7 m/s with motion-prior-guided gait and perform aggre
arXiv:2507.21437v3 Announce Type: replace Abstract: Physics-informed neural networks and physics-informed DeepONet excel at solving partial differential equations but often struggle with singularly pe
arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains
arXiv:2511.18825v3 Announce Type: replace Abstract: Evaluating AI-generated video (AIGV) quality hinges on three crucial dimensions: visual quality, dynamic quality, and text-video alignment. While nu
arXiv:2601.12936v2 Announce Type: replace Abstract: Slot Attention, an approach that binds different objects in a scene to a set of 'slots', has become a leading method in unsupervised object-centric
arXiv:2610.16390v1 Announce Type: cross Abstract: A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining ex