Knowledge catalogue
arXiv:2606.23243v1 Announce Type: new Abstract: Clinical audio diagnosis in low-resource settings requires models that identify conditions from minimal examples without large annotated corpora. We pro
arXiv:2606.23204v1 Announce Type: new Abstract: Large-scale image-text datasets, such as LAION-5B, are foundational to modern AI systems, yet their vast scale and uncurated nature raise significant co
arXiv:2606.20755v1 Announce Type: new Abstract: Visual navigation in unknown environments remains a core challenge in mobile robotics, especially for resource-constrained platforms. Most existing appr
arXiv:2606.21385v1 Announce Type: new Abstract: This paper explores unsupervised disentangled representation learning from a functional perspective. We define latent concepts as factors that influence
arXiv:2606.21287v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) enables robust transfer of knowledge from simulated to real environments while exploiting a subset of unlabeled tar
arXiv:2606.21588v1 Announce Type: cross Abstract: Functional magnetic resonance imaging (fMRI) utilizes echo-planar imaging (EPI) to capture blood-oxygen-level-dependent (BOLD) signals with high tempo
arXiv:2606.21352v1 Announce Type: new Abstract: Understanding the complex topology and hierarchy of urban power grid is crucial for energy prognosis, power flow management, and system resilience analy
arXiv:2602.11944v2 Announce Type: replace Abstract: When building AI systems for decision support, one often encounters the phenomenon of predictive multiplicity: a single best model does not exist; i
arXiv:2606.22239v1 Announce Type: cross Abstract: Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a vari
arXiv:2512.11061v2 Announce Type: replace Abstract: Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack in
arXiv:2510.01022v3 Announce Type: replace Abstract: We introduce vector diffusion wavelets (VDWs), a novel family of wavelets inspired by the vector diffusion maps algorithm that was introduced to ana
arXiv:2602.08334v2 Announce Type: replace Abstract: Planning under uncertainty for real-world robotics tasks, such as autonomous driving, requires reasoning in enormous high-dimensional belief spaces,
arXiv:2606.21961v1 Announce Type: new Abstract: Vegetation monitoring under climate stress requires answering not only how it will evolve given the expected weather, but how it would respond to altern
arXiv:2606.22546v1 Announce Type: new Abstract: Modern Referring Image Segmentation (RIS) systems generate multiple candidate masks per expression but rely on a simple heuristic--typically the argmax
arXiv:2606.23610v1 Announce Type: new Abstract: Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existin
arXiv:2606.20740v1 Announce Type: cross Abstract: Process Reward Models (PRMs) provide step-level verification for Large Language Model (LLM) reasoning, yet their training data acquisition remains a b
arXiv:2606.23543v1 Announce Type: cross Abstract: Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labe
arXiv:2606.20905v1 Announce Type: new Abstract: Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While spec
arXiv:2606.20711v1 Announce Type: new Abstract: UI videos provide a natural input for generating interactive webpages, as they capture both webpage appearance and action-triggered state transitions. H
arXiv:2606.23327v1 Announce Type: new Abstract: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-speci
arXiv:2606.22870v1 Announce Type: new Abstract: Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video understanding and reasoning capabilities of multimodal lar
arXiv:2606.17710v2 Announce Type: replace Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That infe
arXiv:2606.22787v1 Announce Type: new Abstract: Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption: the scenes is entire di
arXiv:2606.21386v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) achieve state-of-the-art performance on many robotic manipulation tasks, yet they can still behave unpredictably
arXiv:2602.21445v2 Announce Type: replace Abstract: Action chunking has recently emerged as a standard practice in flow-based Vision-Language-Action (VLA) models. However, the effect and choice of the
arXiv:2606.23062v1 Announce Type: cross Abstract: We introduce VolHuMe, a dataset of high-quality 4D human scans captured with a state-of-the-art volumetric studio using 64 RGB and 32 depth cameras. V
arXiv:2606.21600v1 Announce Type: new Abstract: Multi-task robot manipulation policies are challenging to learn from demonstration because traditionally a single network must select among qualitativel
arXiv:2508.03058v2 Announce Type: replace Abstract: Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stabil
arXiv:2606.21700v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shif
arXiv:2606.20728v1 Announce Type: new Abstract: Vision foundation tools such as open-vocabulary detectors, segmentation models, and post-processing operators are powerful building blocks for computer
arXiv:2603.18581v2 Announce Type: replace-cross Abstract: With the advent of system-in-package (SiP) chiplet-based design and heterogeneous 2.5D/3D integration, thermal-induced warpage has become a cr
arXiv:2601.04687v2 Announce Type: replace Abstract: Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support shor
arXiv:2606.23145v1 Announce Type: new Abstract: Operational event-detection systems are rarely assessed by pointwise accuracy alone. In anomaly detection, changepoint detection, and warning systems, t
arXiv:2606.22136v1 Announce Type: new Abstract: Scaling dexterous manipulation requires generalization across objects, scenes, and tasks, yet existing data sources face a trade-off between scale and s
arXiv:2606.21126v1 Announce Type: new Abstract: Despite the success of deep learning, training deep networks in biologically plausible and hardware-efficient ways remains an open challenge. Feedback a
arXiv:2606.21790v1 Announce Type: new Abstract: We study what Lorentz-equivariant jet taggers learn internally, using equivariance tests, linear probes and grade ablations across five models including
arXiv:2606.22020v1 Announce Type: cross Abstract: Neural networks outperform classical GCC-PHAT for Time-Difference-of-Arrival (TDOA) estimation in noise and reverberation, yet their internal strategy
arXiv:2606.23443v1 Announce Type: new Abstract: Chemical language models (cLMs) are widely assumed to learn surface-level syntactic patterns rather than learning meaningful molecular semantics. Here,
arXiv:2603.06445v2 Announce Type: replace Abstract: Situated reasoning often relies on active exploration, yet in many real-world scenarios such exploration is infeasible due to physical constraints o
arXiv:2606.20814v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a phenomenon in which models generalize with narrow fine-tuning, leading to broad (yet uneven) misalignment across evalu
arXiv:2606.22864v1 Announce Type: new Abstract: Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for
arXiv:2606.20115v2 Announce Type: replace-cross Abstract: Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-o
arXiv:2606.16196v2 Announce Type: replace-cross Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributio
arXiv:2606.22043v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is increasingly applied to large vision-language models (LVLMs), yet outcome-only optimization c
arXiv:2606.21641v1 Announce Type: new Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that 'warm-start' search from prior knowledge, proposing s
arXiv:2606.23339v1 Announce Type: new Abstract: Human-robot interaction (HRI) evaluation relies almost exclusively on human-completed questionnaires, leaving the robot's perspective unexamined. We pro
arXiv:2606.20724v1 Announce Type: cross Abstract: Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate
arXiv:2606.22079v1 Announce Type: cross Abstract: Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine,
arXiv:2606.23057v1 Announce Type: cross Abstract: Large language models now mediate how buyers discover products and services, making the competitive structure of AI-generated recommendations a strate
arXiv:2603.28919v2 Announce Type: replace Abstract: As robots increasingly enter the workforce, human-robot interaction (HRI) must address how implicit social biases influence user preferences. This p
arXiv:2606.21309v1 Announce Type: new Abstract: We introduce WildBox, a dataset and benchmark for monocular 3D detection of wildlife from drone video, comprising 237,505 3D bounding box annotations ac
arXiv:2606.21868v1 Announce Type: new Abstract: Modern Mixture-of-Experts (MoE) models place most of their parameters in expert layers, yet only a small fraction of those experts are used for any toke
arXiv:2606.22430v1 Announce Type: cross Abstract: Because large language models (LLMs) are impressively successful in predicting text, it appears that they must have access to a 'world model' represen
arXiv:2606.19358v2 Announce Type: replace Abstract: We introduceWorkBenchMark, a LEGO Duplo-based robotic assembly benchmark motivated by the RoboCup Smart Manufacturing League. Robotic assembly coupl
arXiv:2606.20781v1 Announce Type: cross Abstract: World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large v
arXiv:2106.06998v4 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagat
arXiv:2606.20731v1 Announce Type: new Abstract: Large-scale human motion datasets are essential for training robust motion models for analysis, synthesis, and understanding. While marker-based motion
arXiv:2511.22699v4 Announce Type: replace Abstract: The landscape of high-performance image generation models is currently dominated by proprietary systems, such as Nano Banana Pro and Seedream 4.0. L
arXiv:2606.14970v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse dow
arXiv:2606.22145v1 Announce Type: new Abstract: Reinforcement learning (RL) is a powerful and convenient tool to modernize controller design. In this work, we study the zero-shot transfer of RL-based