Anatomically Guided Latent Diffusion for Brain MRI Progression Modeling

Accurately modeling longitudinal brain MRI progression is crucial for understanding neurodegenerative diseases and predicting individualized structural changes. Existing state-of-the-art approaches, such as Brain Latent Progression (BrLP), often use multi-stage training pipelines with auxiliary conditioning modules but suffer from architectural complexity, suboptimal use of conditional clinical covariates, and limited guarantees of anatomical consistency. We propose Anatomically Guided Latent Diffusion Model (AG-LDM), a segmentation-guided framework that enforces anatomically consistent progression while substantially simplifying the training pipeline. AG-LDM conditions latent diffusion by directly fusing baseline anatomy, noisy follow-up states, and clinical covariates at the input level, a strategy that avoids auxiliary control networks by learning a unified, end-to-end model that represents both anatomy and progression. A lightweight 3D tissue segmentation model (WarpSeg) provides explicit anatomical supervision during both autoencoder fine-tuning and diffusion model training, ensuring consistent brain tissue boundaries and morphometric fidelity. Experiments on 31,713 ADNI longitudinal pairs and zero-shot evaluation on OASIS-3 demonstrate that AG-LDM matches or surpasses more complex diffusion models, achieving state-of-the-art image quality and 15-20\% reduction in volumetric errors in generated images. AG-LDM also exhibits markedly stronger utilization of temporal and clinical covariates (up to 31.5x higher sensitivity than BrLP) and generates biologically plausible counterfactual trajectories, accurately capturing hallmarks of Alzheimer's progression such as limbic atrophy and ventricular expansion. These results highlight AG-LDM as an efficient, anatomically grounded framework for reliable brain MRI progression modeling.

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (VideoMaMa) that converts coarse segmentation masks into pixel accurate alpha mattes, by leveraging pretrained video diffusion models. VideoMaMa demonstrates strong zero-shot generalization to real-world footage, even though it is trained solely on synthetic data. Building on this capability, we develop a scalable pseudo-labeling pipeline for large-scale video matting and construct the Matting Anything in Video (MA-V) dataset, which offers high-quality matting annotations for more than 50K real-world videos spanning diverse scenes and motions. To validate the effectiveness of this dataset, we fine-tune the SAM2 model on MA-V to obtain SAM2-Matte, which outperforms the same model trained on existing matting datasets in terms of robustness on in-the-wild videos. These findings emphasize the importance of large-scale pseudo-labeled video matting and showcase how generative priors and accessible segmentation cues can drive scalable progress in video matting research.

Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation

Vision-Language Models (VLMs), particularly CLIP, have revolutionized anomaly detection by enabling zero-shot and few-shot defect identification without extensive labeled datasets. By learning aligned representations of images and text, VLMs facilitate anomaly classification and segmentation through natural language descriptions of normal and abnormal states, eliminating traditional requirements for task-specific training or defect examples. This project presents a comprehensive analysis of VLM-based approaches for anomaly classification (AC) and anomaly segmentation (AS). We systematically investigate key architectural paradigms including sliding window-based dense feature extraction (WinCLIP), multi-stage feature alignment with learnable projections (AprilLab framework), and compositional prompt ensemble strategies. Our analysis evaluates these methods across critical dimensions: feature extraction mechanisms, text-visual alignment strategies, prompt engineering techniques, zero-shot versus few-shot trade-offs, computational efficiency, and cross-domain generalization. Through rigorous experimentation on benchmarks such as MVTec AD and VisA, we compare classification accuracy, segmentation precision, and inference efficiency. The primary contribution is a foundational understanding of how and why VLMs succeed in anomaly detection, synthesizing practical insights for method selection and identifying current limitations. This work aims to facilitate informed adoption of VLM-based methods in industrial quality control and guide future research directions.

Synthetic Volumetric Data Generation Enables Zero-Shot Generalization of Foundation Models in 3D Medical Image Segmentation

Foundation models such as Segment Anything Model 2 (SAM 2) exhibit strong generalization on natural images and videos but perform poorly on medical data due to differences in appearance statistics, imaging physics, and three-dimensional structure. To address this gap, we introduce SynthFM-3D, an analytical framework that mathematically models 3D variability in anatomy, contrast, boundary definition, and noise to generate synthetic data for training promptable segmentation models without real annotations. We fine-tuned SAM 2 on 10,000 SynthFM-3D volumes and evaluated it on eleven anatomical structures across three medical imaging modalities (CT, MR, ultrasound) from five public datasets. SynthFM-3D training led to consistent and statistically significant Dice score improvements over the pretrained SAM 2 baseline, demonstrating stronger zero-shot generalization across modalities. When compared with the supervised SAM-Med3D model on unseen cardiac ultrasound data, SynthFM-3D achieved 2-3x higher Dice scores, establishing analytical 3D data modeling as an effective pathway to modality-agnostic medical segmentation.

Seeing Radio: From Zero RF Priors to Explainable Modulation Recognition with Vision Language Models

The rise of vision language models (VLMs) paves a new path for radio frequency (RF) perception. Rather than designing task-specific neural receivers, we ask if VLMs can learn to recognize modulations when RF waveforms are expressed as images. In this work, we find that they can. In specific, in this paper, we introduce a practical pipeline for converting complex IQ streams into visually interpretable inputs, hence, enabling general-purpose VLMs to classify modulation schemes without changing their underlying design. Building on this, we construct an RF visual question answering (VQA) benchmark framework that covers 57 classes across major families of analog/digital modulations with three complementary image modes, namely, (i) short \emph{time-series} IQ segments represented as real/imaginary traces, (ii) magnitude-only \emph{spectrograms}, and (iii) \emph{joint} representations that pair spectrograms with a synchronized time-series waveforms. We design uniform zero-shot and few-shot prompts for both class-level and family-level evaluations. Our finetuned VLMs with these images achieve competitive accuracy of $90\%$ compared to $10\%$ of the base models. Furthermore, the fine-tuned VLMs show robust performance under noise and demonstrate high generalization performance to unseen modulation types, without relying on RF-domain priors or specialized architectures. The obtained results show that combining RF-to-image conversion with promptable VLMs provides a scalable and practical foundation for RF-aware AI systems in future 6G networks.

Segment and Matte Anything in a Unified Model

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls short of the precision required in real-world applications. While several refinement modules have been proposed to boost SAM's segmentation quality, achieving highly accurate object delineation within a single, unified framework remains an open challenge. Furthermore, interactive image matting, which aims to generate fine-grained alpha mattes guided by diverse user hints, has not yet been explored in the context of SAM. Insights from recent studies highlight strong correlations between segmentation and matting, suggesting the feasibility of a unified model capable of both tasks. In this paper, we introduce Segment And Matte Anything (SAMA), a lightweight extension of SAM that delivers high-quality interactive image segmentation and matting with minimal extra parameters. Our Multi-View Localization Encoder (MVLE) captures detailed features from local views, while the Localization Adapter (Local-Adapter) refines mask outputs by recovering subtle boundary details. We also incorporate two prediction heads for each task into the architecture to generate segmentation and matting masks, simultaneously. Trained on a diverse dataset aggregated from publicly available sources, SAMA achieves state-of-the-art performance across multiple segmentation and matting benchmarks, showcasing its adaptability and effectiveness in a wide range of downstream tasks.

Shapelets-Enriched Selective Forecasting using Time Series Foundation Models

Time series foundation models have recently gained a lot of attention due to their ability to model complex time series data encompassing different domains including traffic, energy, and weather. Although they exhibit strong average zero-shot performance on forecasting tasks, their predictions on certain critical regions of the data are not always reliable, limiting their usability in real-world applications, especially when data exhibits unique trends. In this paper, we propose a selective forecasting framework to identify these critical segments of time series using shapelets. We learn shapelets using shift-invariant dictionary learning on the validation split of the target domain dataset. Utilizing distance-based similarity to these shapelets, we facilitate the user to selectively discard unreliable predictions and be informed of the model's realistic capabilities. Empirical results on diverse benchmark time series datasets demonstrate that our approach leveraging both zero-shot and full-shot fine-tuned models reduces the overall error by an average of 22.17% for zero-shot and 22.62% for full-shot fine-tuned model. Furthermore, our approach using zero-shot and full-shot fine-tuned models, also outperforms its random selection counterparts by up to 21.41% and 21.43% on one of the datasets.

Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence

Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.

Action100M: A Large-scale Video Action Dataset

Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this requires large-scale, open-vocabulary video action datasets that span broad domains. We introduce Action100M, a large-scale dataset constructed from 1.2M Internet instructional videos (14.6 years of duration), yielding O(100 million) temporally localized segments with open-vocabulary action supervision and rich captions. Action100M is generated by a fully automated pipeline that (i) performs hierarchical temporal segmentation using V-JEPA 2 embeddings, (ii) produces multi-level frame and segment captions organized as a Tree-of-Captions, and (iii) aggregates evidence with a reasoning model (GPT-OSS-120B) under a multi-round Self-Refine procedure to output structured annotations (brief/detailed action, actor, brief/detailed caption). Training VL-JEPA on Action100M demonstrates consistent data-scaling improvements and strong zero-shot performance across diverse action recognition benchmarks, establishing Action100M as a new foundation for scalable research in video understanding and world modeling.

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

As hubs of human activity, urban surfaces consist of a wealth of semantic entities. Segmenting these various entities from satellite imagery is crucial for a range of downstream applications. Current advanced segmentation models can reliably segment entities defined by physical attributes (e.g., buildings, water bodies) but still struggle with socially defined categories (e.g., schools, parks). In this work, we achieve socio-semantic segmentation by vision-language model reasoning. To facilitate this, we introduce the Urban Socio-Semantic Segmentation dataset named SocioSeg, a new resource comprising satellite imagery, digital maps, and pixel-level labels of social semantic entities organized in a hierarchical structure. Additionally, we propose a novel vision-language reasoning framework called SocioReasoner that simulates the human process of identifying and annotating social semantic entities via cross-modal recognition and multi-stage reasoning. We employ reinforcement learning to optimize this non-differentiable process and elicit the reasoning capabilities of the vision-language model. Experiments demonstrate our approach's gains over state-of-the-art models and strong zero-shot generalization. Our dataset and code are available in https://github.com/AMAP-ML/SocioReasoner.