Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2511. 17649v4 Announce Type: replace-cross Abstract: Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments.
arXiv:2606. 28556v1 Announce Type: new Abstract: Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging.
arXiv:2606. 30313v1 Announce Type: cross Abstract: Longitudinal glioblastoma response assessment requires comparing subtle tumor changes across MRI time points using structured clinical criteria such as RANO.
arXiv:2606. 28357v1 Announce Type: cross Abstract: Recent advances in multimodal recommenders excel at feature fusion but remain opaque and inefficient decision-makers, lacking explicit reasoning and self-awareness of uncertainty.
arXiv:2606. 30374v1 Announce Type: cross Abstract: Multimodal MRI is essential for accurate brain tumor segmentation.
arXiv:2606. 28724v1 Announce Type: cross Abstract: Understanding and localizing subtle changes between paired images is critical for tasks such as surveillance and image editing.
arXiv:2606. 29400v1 Announce Type: cross Abstract: In computer graphics, visual content is continuously warped, zoomed and resampled.
arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.
arXiv:2606. 29667v1 Announce Type: cross Abstract: The materials science literature encodes decades of experimental knowledge in figures, yet this visual record remains locked away and inaccessible to AI at scale.
arXiv:2511. 14900v2 Announce Type: replace-cross Abstract: Vision--language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis.
arXiv:2606. 30111v1 Announce Type: cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv:2606. 30026v1 Announce Type: cross Abstract: Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.
arXiv:2606. 30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.
arXiv:2606. 30626v1 Announce Type: new Abstract: On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.
arXiv:2606. 29453v1 Announce Type: cross Abstract: Arbitrary-Scale Super-Resolution (ASR) reconstructs images at continuous magnification factors.
arXiv:2606. 29115v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) are increasingly deployed in urban environments, yet their safety frameworks remain primarily designed around collision avoidance and minimal risk condition (MRC) behaviors such as slowing or stopping when uncertainty arises.
arXiv:2606. 30190v1 Announce Type: cross Abstract: Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity.
Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion. Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale.
As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge. While prior methods aim to learn representations robust to missing inputs, representations from incomplete modalities inevitably deviate from their full-modality counterparts due to missing evidence.
Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion methods often treat text and structure as separate inputs in a shallow, one-way pipeline, which limits deep interaction between modalities and weakens performance under sparse connectivity or cross-graph generalisation.