Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.14377v1 Announce Type: new Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background...
arXiv:2609.14469v1 Announce Type: new Abstract: Accurate 3D localization of unmanned aerial vehicles (UAVs) remains challenging for existing multimodal approaches due to sparse LiDAR geometry, modali...
arXiv:2609.15150v1 Announce Type: new Abstract: Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-...
arXiv:2609.15285v1 Announce Type: new Abstract: Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resou...
arXiv:2603.13966v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pi...
arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particu...
arXiv:2510.23224v2 Announce Type: replace Abstract: The rapid digitization of histopathology slides has opened new opportunities for computational tools in clinical and research workflows. Content-ba...
arXiv:2609.14145v1 Announce Type: cross Abstract: Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTR...
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception u...
arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data m...
arXiv:2605.27310v2 Announce Type: replace Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry t...
arXiv:2606.08906v2 Announce Type: replace Abstract: In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward deco...
arXiv:2609.13234v1 Announce Type: cross Abstract: Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In...
arXiv:2606.19100v4 Announce Type: replace Abstract: Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open...
arXiv:2609.14619v1 Announce Type: new Abstract: LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object d...
Dynamic Learning Solutions is an automated pipeline that transforms NCERT textbook PDFs into interactive video explanations. Users upload a PDF and ask a question; the system retrieves relevant content, generates a multi-scene script, creates images with Stable Diffusion, animates them with DynamiCrafter, and adds synchronized narration via Google Text‑to‑Speech. The result is a coherent, textbook‑aligned video that turns static material into an engaging learning experience.
TwinICL is a procedurally generated benchmark that pairs matched text and image versions of tasks to enable controlled comparison of in‑context learning (ICL) across modalities. Experiments on six open‑weight models and 38 tasks show that multimodal ICL consistently underperforms text‑only ICL, with varying gaps by task family. Interventions targeting visual access, task framing, and reasoning can recover strong multimodal performance on a diagnostic subset, yet a modality gap remains even when explicit task instructions are provided, highlighting the dual role of demonstrations as context and evidence.
The paper introduces Influpaint, a denoising diffusion probabilistic model adapted for forecasting influenza incidence. By representing influenza seasons as spatiotemporal images and training on a hybrid dataset of surveillance and simulated trajectories, the model learns a rich distribution of disease dynamics and performs forecasting as a conditional generation task. In retrospective and real‑time evaluations, Influpaint produces realistic, diverse epidemic trajectories and achieves forecast accuracy competitive with leading ensemble methods, especially when trained with 30% surveillance and 70% simulated data.
MoVT is a new framework for text‑to‑motion generation that uses a cross‑modal augmented motion tokenizer to project 3D motion tokens into 2D, enriching the motion codebook with real‑world video patterns. The enriched tokens are mapped back to 3D, creating aligned 3D and 2D codebooks that better capture intricate motions. These codebooks feed a generative masked transformer, which predicts masked motion tokens in a modality‑agnostic way, allowing text‑index pairs from the 2D codebook and annotated videos to further improve generation quality. Empirical tests show MoVT outperforms previous state‑of‑the‑art methods on several key metrics.
EventVL introduces the first generative event-based multimodal large language model (MLLM) designed for explicit semantic understanding of event streams. The framework leverages a newly annotated dataset of nearly 1.4 million event–image/video–text pairs and incorporates an Event Spatiotemporal Representation to capture comprehensive event information, along with Dynamic Semantic Alignment to refine sparse semantic spaces. Experiments demonstrate that EventVL outperforms existing MLLM baselines in event captioning and scene description generation tasks, advancing the field of event vision.