ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual Querying

Chain-of-Thought (CoT) reasoning excels in language models but struggles in vision-language models due to premature visual-to-text conversion that discards continuous information such as geometry and spatial layout. While recent methods enhance CoT through static enumeration or attention-based selection, they remain passive, i.e., processing pre-computed inputs rather than actively seeking task-relevant details. Inspired by human active perception, we introduce ViThinker, a framework that enables vision-language models to autonomously generate decision (query) tokens triggering the synthesis of expert-aligned visual features on demand. ViThinker internalizes vision-expert capabilities during training, performing generative mental simulation during inference without external tool calls. Through a two-stage curriculum: first distilling frozen experts into model parameters, then learning task-driven querying via sparsity penalties, i.e., ViThinker discovers minimal sufficient perception for each reasoning step. Evaluations across vision-centric benchmarks demonstrate consistent improvements, validating that active query generation outperforms passive approaches in both perceptual grounding and reasoning accuracy.

Distribution Matching Distillation Meets Reinforcement Learning

Distribution Matching Distillation (DMD) distills a pre-trained multi-step diffusion model to a few-step one to improve inference efficiency. However, the performance of the latter is often capped by the former. To circumvent this dilemma, we propose DMDR, a novel framework that combines Reinforcement Learning (RL) techniques into the distillation process. We show that for the RL of the few-step generator, the DMD loss itself is a more effective regularization compared to the traditional ones. In turn, RL can help to guide the mode coverage process in DMD more effectively. These allow us to unlock the capacity of the few-step generator by conducting distillation and RL simultaneously. Meanwhile, we design the dynamic distribution guidance and dynamic renoise sampling training strategies to improve the initial distillation process. The experiments demonstrate that DMDR can achieve leading visual quality, prompt coherence among few-step methods, and even exhibit performance that exceeds the multi-step teacher.

Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data

Automated knee cartilage segmentation using point-of-care ultrasound devices and deep-learning networks has the potential to enhance the management of knee osteoarthritis. However, segmentation algorithms often struggle with domain shifts caused by variations in ultrasound devices and acquisition parameters, limiting their generalizability. In this paper, we propose Mono2D, a monogenic layer that extracts multi-scale, contrast- and intensity-invariant local phase features using trainable bandpass quadrature filters. This layer mitigates domain shifts, improving generalization to out-of-distribution domains. Mono2D is integrated before the first layer of a segmentation network, and its parameters jointly trained alongside the network's parameters. We evaluated Mono2D on a multi-domain 2D ultrasound knee cartilage dataset for single-source domain generalization (SSDG). Our results demonstrate that Mono2D outperforms other SSDG methods in terms of Dice score and mean average surface distance. To further assess its generalizability, we evaluate Mono2D on a multi-site prostate MRI dataset, where it continues to outperform other SSDG methods, highlighting its potential to improve domain generalization in medical imaging. Nevertheless, further evaluation on diverse datasets is still necessary to assess its clinical utility.

Re-visiting Skip-Gram Negative Sampling: Dimension Regularization for More Efficient Dissimilarity Preservation in Graph Embeddings

A wide range of graph embedding objectives decompose into two components: one that attracts the embeddings of nodes that are perceived as similar, and another that repels embeddings of nodes that are perceived as dissimilar. Because real-world graphs are sparse and the number of dissimilar pairs grows quadratically with the number of nodes, Skip-Gram Negative Sampling (SGNS) has emerged as a popular and efficient repulsion approach. SGNS repels each node from a sample of dissimilar nodes, as opposed to all dissimilar nodes. In this work, we show that node-wise repulsion is, in aggregate, an approximate re-centering of the node embedding dimensions. Such dimension operations are much more scalable than node operations. The dimension approach, in addition to being more efficient, yields a simpler geometric interpretation of the repulsion. Our result extends findings from the self-supervised learning literature to the skip-gram model, establishing a connection between skip-gram node contrast and dimension regularization. We show that in the limit of large graphs, under mild regularity conditions, the original node repulsion objective converges to optimization with dimension regularization. We use this observation to propose an algorithm augmentation framework that speeds up any existing algorithm, supervised or unsupervised, using SGNS. The framework prioritizes node attraction and replaces SGNS with dimension regularization. We instantiate this generic framework for LINE and node2vec and show that the augmented algorithms preserve downstream performance while dramatically increasing efficiency.

APP-RUSS: Automated Path Planning for Robotic Ultrasound System

Autonomous robotic ultrasound System (RUSS) has been extensively studied. However, fully automated ultrasound image acquisition is still challenging, partly due to the lack of study in combining two phases of path planning: guiding the ultrasound probe to the scan target and covering the scan surface or volume. This paper presents a system of Automated Path Planning for RUSS (APP-RUSS). Our focus is on the first phase of automation, which emphasizes directing the ultrasound probe's path toward the target over extended distances. Specifically, our APP-RUSS system consists of a RealSense D405 RGB-D camera that is employed for visual guidance of the UR5e robotic arm and a cubic Bezier curve path planning model that is customized for delivering the probe to the recognized target. APP-RUSS can contribute to understanding the integration of the two phases of path planning in robotic ultrasound imaging, paving the way for its clinical adoption.

DT/MARS-CycleGAN: Improved Object Detection for MARS Phenotyping Robot

Robotic crop phenotyping has emerged as a key technology to assess crops' morphological and physiological traits at scale. These phenotypical measurements are essential for developing new crop varieties with the aim of increasing productivity and dealing with environmental challenges such as climate change. However, developing and deploying crop phenotyping robots face many challenges such as complex and variable crop shapes that complicate robotic object detection, dynamic and unstructured environments that baffle robotic control, and real-time computing and managing big data that challenge robotic hardware/software. This work specifically tackles the first challenge by proposing a novel Digital-Twin(DT)MARS-CycleGAN model for image augmentation to improve our Modular Agricultural Robotic System (MARS)'s crop object detection from complex and variable backgrounds. Our core idea is that in addition to the cycle consistency losses in the CycleGAN model, we designed and enforced a new DT-MARS loss in the deep learning model to penalize the inconsistency between real crop images captured by MARS and synthesized images sensed by DT MARS. Therefore, the generated synthesized crop images closely mimic real images in terms of realism, and they are employed to fine-tune object detectors such as YOLOv8. Extensive experiments demonstrated that our new DT/MARS-CycleGAN framework significantly boosts our MARS' crop object/row detector's performance, contributing to the field of robotic crop phenotyping.

When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations

We study the fairness of dimensionality reduction methods for recommendations. We focus on the established method of principal component analysis (PCA), which identifies latent components and produces a low-rank approximation via the leading components while discarding the trailing components. Prior works have defined notions of "fair PCA"; however, these definitions do not answer the following question: what makes PCA unfair? We identify two underlying mechanisms of PCA that induce unfairness at the item level. The first negatively impacts less popular items, due to the fact that less popular items rely on trailing latent components to recover their values. The second negatively impacts the highly popular items, since the leading PCA components specialize in individual popular items instead of capturing similarities between items. To address these issues, we develop a polynomial-time algorithm, Item-Weighted PCA, a modification of PCA that uses item-specific weights in the objective. On a stylized class of matrices, we prove that Item-Weighted PCA using a specific set of weights minimizes a popularity-normalized error metric. Our evaluations on real-world datasets show that Item-Weighted PCA not only improves overall recommendation quality by up to $0.1$ item-level AUC-ROC but also improves on both popular and less popular items.

Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification

With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or understanding the meaning of neurons in middle layers. Nevertheless, these methods can only discover the patterns or rules that naturally exist in models. In this work, rather than relying on post-hoc schemes, we proactively instill knowledge to alter the representation of human-understandable concepts in hidden layers. Specifically, we use a hierarchical tree of semantic concepts to store the knowledge, which is leveraged to regularize the representations of image data instances while training deep models. The axes of the latent space are aligned with the semantic concepts, where the hierarchical relations between concepts are also preserved. Experiments on real-world image datasets show that our method improves model interpretability, showing better disentanglement of semantic concepts, without negatively affecting model classification performance.

MMViT: Multiscale Multiview Vision Transformers

We present Multiscale Multiview Vision Transformers (MMViT), which introduces multiscale feature maps and multiview encodings to transformer models. Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel. At each scale stage, we use a cross-attention block to fuse information across different views. This enables the MMViT model to acquire complex high-dimensional representations of the input at different resolutions. The proposed model can serve as a backbone model in multiple domains. We demonstrate the effectiveness of MMViT on audio and image classification tasks, achieving state-of-the-art results.

Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer

Purpose: In some proton therapy facilities, patient alignment relies on two 2D orthogonal kV images, taken at fixed, oblique angles, as no 3D on-the-bed imaging is available. The visibility of the tumor in kV images is limited since the patient's 3D anatomy is projected onto a 2D plane, especially when the tumor is behind high-density structures such as bones. This can lead to large patient setup errors. A solution is to reconstruct the 3D CT image from the kV images obtained at the treatment isocenter in the treatment position. Methods: An asymmetric autoencoder-like network built with vision-transformer blocks was developed. The data was collected from 1 head and neck patient: 2 orthogonal kV images (1024x1024 voxels), 1 3D CT with padding (512x512x512) acquired from the in-room CT-on-rails before kVs were taken and 2 digitally-reconstructed-radiograph (DRR) images (512x512) based on the CT. We resampled kV images every 8 voxels and DRR and CT every 4 voxels, thus formed a dataset consisting of 262,144 samples, in which the images have a dimension of 128 for each direction. In training, both kV and DRR images were utilized, and the encoder was encouraged to learn the jointed feature map from both kV and DRR images. In testing, only independent kV images were used. The full-size synthetic CT (sCT) was achieved by concatenating the sCTs generated by the model according to their spatial information. The image quality of the synthetic CT (sCT) was evaluated using mean absolute error (MAE) and per-voxel-absolute-CT-number-difference volume histogram (CDVH). Results: The model achieved a speed of 2.1s and a MAE of <40HU. The CDVH showed that <5% of the voxels had a per-voxel-absolute-CT-number-difference larger than 185 HU. Conclusion: A patient-specific vision-transformer-based network was developed and shown to be accurate and efficient to reconstruct 3D CT images from kV images.