We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture differences, and covariate corruptions -- through a multi-encoder fusion of per-encoder representation-space diffusion models (RDMs). We statistically identify each encoder's sensitivity to specific shift types from ID data alone and introduce EncMin2L -- an encoder-agnostic two-level $\min(\cdot)$-gate that combines and calibrates per-encoder diffusion-based likelihood detectors without OOD labels, outperforming monolithic multi-encoder baselines at $2.3\times$ lower parameter cost. Two ID-data diagnostics: $η^2$ (class-conditional F-test) and $Δμ$ (log-likelihood shift under synthetic corruptions) -- quantify encoder specialization, while a Tippett minimum $p$-value combination aggregates per-encoder scores into a single, calibration-stable OOD signal. EncMin2L achieves $\geq 0.94$ AUROC across all four shift types simultaneously, outperforming the state-of-the-art representation-space diffusion OOD detectors across overlapping benchmarks.

Our objective in this paper is to probe large vision models to determine to what extent they'understand' different physical properties of the 3D scene depicted in an image. To this end, we make the following contributions: (i) We introduce a general and lightweight protocol to evaluate whether features of an off-the-shelf large vision model encode a number of physical'properties' of the 3D scene, by training discriminative classifiers on the features for these properties. The probes are applied on datasets of real images with annotations for the property.

CLIP struggles with representing [ 17 ].

Abstract--Vision Foundation Models (VFMs) and Vision Language Models (VLMs) have revolutionized computer vision by providing rich semantic and geometric representations. This paper presents a comprehensive visual comparison between CLIP based and DINOv2 based approaches for 3D pose estimation in hand object grasping scenarios. We evaluate both models on the task of 6D object pose estimation and demonstrate their complementary strengths: CLIP excels in semantic understanding through language grounding, while DINOv2 provides superior dense geometric features. Through extensive experiments on benchmark datasets, we show that CLIP based methods achieve better semantic consistency, while DINOv2 based approaches demonstrate competitive performance with enhanced geometric precision. Our analysis provides insights for selecting appropriate vision models for robotic manipulation and grasping, picking applications.

Existing foundation models (FMs) in the medical domain often require extensive fine-tuning or rely on training resource-intensive decoders, while many existing encoders are pretrained with objectives biased toward specific tasks. This illustrates a need for a strong, task-agnostic foundation model that requires minimal fine-tuning beyond feature extraction. In this work, we introduce a suite of task-agnostic pretraining of CT foundation models (TAP-CT): a simple yet effective adaptation of Vision Transformers (ViTs) and DINOv2 for volumetric data, enabling scalable self-supervised pretraining directly on 3D CT volumes. Our approach incorporates targeted modifications to patch embeddings, positional encodings, and volumetric augmentations, making the architecture depth-aware while preserving the simplicity of the underlying architectures. We show that large-scale 3D pretraining on an extensive in-house CT dataset (105K volumes) yields stable, robust frozen representations that generalize strongly across downstream tasks. To promote transparency and reproducibility, and to establish a powerful, low-resource baseline for future research in medical imaging, we will release all pretrained models, experimental configurations, and downstream benchmark code at https://huggingface.co/fomofo/tap-ct-b-3d.

Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and inference costs, as well as challenges in extracting visual details, effectively bridging across modalities. In this work, we propose a novel visual framework, MoCHA, to address these issues. Our framework integrates four vision backbones (i.e., CLIP, SigLIP, DINOv2 and ConvNeXt) to extract complementary visual features and is equipped with a sparse Mixture of Experts Connectors (MoECs) module to dynamically select experts tailored to different visual dimensions. To mitigate redundant or insufficient use of the visual information encoded by the MoECs module, we further design a Hierarchical Group Attention (HGA) with intra- and inter-group operations and an adaptive gating strategy for encoded visual features. We train MoCHA on two mainstream LLMs (e.g., Phi2-2.7B and Vicuna-7B) and evaluate their performance across various benchmarks. Notably, MoCHA outperforms state-of-the-art open-weight models on various tasks. For example, compared to CuMo (Mistral-7B), our MoCHA (Phi2-2.7B) presents outstanding abilities to mitigate hallucination by showing improvements of 3.25% in POPE and to follow visual instructions by raising 153 points on MME. Finally, ablation studies further confirm the effectiveness and robustness of the proposed MoECs and HGA in improving the overall performance of MoCHA.

The primary challenge in computer vision is precisely calculating the pose of 6D objects, however many current approaches are still fragile and have trouble generalizing from synthetic data to real-world situations with fluctuating lighting, textureless objects, and significant occlusions. To address these limitations, VLM6D, a novel dual-stream architecture that leverages the distinct strengths of visual and geometric data from RGB-D input for robust and precise pose estimation. Our framework uniquely integrates two specialized encoders: a powerful, self-supervised Vision Transformer (DINOv2) processes the RGB modality, harnessing its rich, pre-trained understanding of visual grammar to achieve remarkable resilience against texture and lighting variations. Concurrently, a PointNet++ encoder processes the 3D point cloud derived from depth data, enabling robust geometric reasoning that excels even with the sparse, fragmented data typical of severe occlusion. These complementary feature streams are effectively fused to inform a multi task prediction head. We demonstrate through comprehensive experiments that VLM6D obtained new SOTA performance on the challenging Occluded-LineMOD, validating its superior robustness and accuracy.

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications.

State-of-the-art embeddings often capture distinct yet complementary discriminative features: For instance, one image embedding model may excel at distinguishing fine-grained textures, while another focuses on object-level structure. Motivated by this observation, we propose a principled approach to fuse such complementary representations through kernel multiplication. Multiplying the kernel similarity functions of two embeddings allows their discriminative structures to interact, producing a fused representation whose kernel encodes the union of the clusters identified by each parent embedding. This formulation also provides a natural way to construct joint kernels for paired multi-modal data (e.g., image-text tuples), where the product of modality-specific kernels inherits structure from both domains. We highlight that this kernel product is mathematically realized via the Kronecker product of the embedding feature maps, yielding our proposed KrossFuse framework for embedding fusion. To address the computational cost of the resulting high-dimensional Kronecker space, we further develop RP-KrossFuse, a scalable variant that leverages random projections for efficient approximation. As a key application, we use this framework to bridge the performance gap between cross-modal embeddings (e.g., CLIP, BLIP) and unimodal experts (e.g., DINOv2, E5). Experiments show that RP-KrossFuse effectively integrates these models, enhancing modality-specific performance while preserving cross-modal alignment. The project code is available at https://github.com/yokiwuuu/KrossFuse.