Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2607. 10358v1 Announce Type: cross Abstract: Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear.
arXiv:2603. 22042v3 Announce Type: replace-cross Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios.
arXiv:2607. 11459v1 Announce Type: cross Abstract: This paper presents the mAIEnergy dataset, an open-access, multimodal corpus developed to support Large Language Model (LLM) applications in the energy sector.
arXiv:2607. 11594v1 Announce Type: new Abstract: Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files.
arXiv:2607. 10628v1 Announce Type: cross Abstract: We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models.
arXiv:2607. 09818v1 Announce Type: cross Abstract: Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents.
arXiv:2607. 11706v1 Announce Type: cross Abstract: Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks.
arXiv:2607. 11007v1 Announce Type: new Abstract: Few-shot multimodal classification commonly attaches a lightweight head, such as $k$-nearest neighbors, logistic regression, or a linear SVM, to a frozen pretrained encoder.
arXiv:2607. 10762v1 Announce Type: cross Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding.
arXiv:2607. 11560v1 Announce Type: cross Abstract: Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning.
arXiv:2607. 10023v1 Announce Type: cross Abstract: Understanding music requires understanding localized relationships across data modalities, e.
arXiv:2506. 22036v2 Announce Type: replace Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees.
arXiv:2607. 09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments.
arXiv:2607. 10098v1 Announce Type: cross Abstract: Modern satellite edge systems, including those performing remote sensing tasks such object detection and tracking, are characterized by severely limited bandwidth and intermittent connections, making continuous data transmission to the cloud impractical.
arXiv:2607. 10168v1 Announce Type: cross Abstract: It is still hard to find Alzheimer's disease (AD) early, especially when neuroimaging is expensive or tools that depend on language are not available.
arXiv:2607. 11656v1 Announce Type: cross Abstract: Accurate diagnostic classification and disease-severity prediction for Alzheimer's disease are hampered by the incompleteness and heterogeneity of real-world clinical data.
arXiv:2607. 10698v1 Announce Type: new Abstract: We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space.
A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1.
Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each pair without token-level supervision.
This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments. The proposed architecture combines parameter-efficient modality-specific adaptation with sequential fusion, enabling modalities to be integrated in stages without retraining previously learned components.