Qian Zhou

Zimeng Li, Sa Xiao, Cheng Wang et al. · amazon-science

Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications. Deep learning has demonstrated great potential for accelerating MRI by reconstructing images from undersampled data. However, most existing deep conventional neural networks (CNN) directly apply square convolution to k-space data without considering the inherent properties of k-space sampling, limiting k-space learning efficiency and image reconstruction quality. In this work, we propose an encoding enhanced (EN2) complex CNN for highly undersampled pulmonary MRI reconstruction. EN2 employs convolution along either the frequency or phase-encoding direction, resembling the mechanisms of k-space sampling, to maximize the utilization of the encoding correlation and integrity within a row or column of k-space. We also employ complex convolution to learn rich representations from the complex k-space data. In addition, we develop a feature-strengthened modularized unit to further boost the reconstruction performance. Experiments demonstrate that our approach can accurately reconstruct hyperpolarized 129Xe and 1H lung MRI from 6-fold undersampled k-space data and provide lung function measurements with minimal biases compared with fully-sampled image. These results demonstrate the effectiveness of the proposed algorithmic components and indicate that the proposed approach could be used for accelerated pulmonary MRI in research and clinical lung disease patient care.

Ludwig Sidenmark, Qian Zhou, George Fitzmaurice et al.

Creating 3D character animations traditionally requires significant time and effort from the animator. Advancements in generative methods now enable easy creation of multiple character animation variations for use or further editing. However, this capability introduces a new challenge in comparing character animations to select the best animation, which is challenging due to temporal misalignment and the large amount of spatial data. We present AnimationDiff, a visual comparison tool for generated character animations. AnimationDiff enables contextual comparisons in the intended scene and camera angle, and embedding of spatial information by combining established animation visualization techniques and easy switching between overlaid and side-by-side comparisons. AnimationDiff also supports filtering to handle information overload, and Temporal Lenses that visualize entire animations over time for overview, alignment, and comparison. We evaluated AnimationDiff in a user study, showcasing its efficacy in animation comparison and providing design insights for comparing motion.

Yuqi Li, Qian Zhou, Huiran Duan et al.

Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice. Knowledge distillation (KD) offers a natural way to transfer knowledge from a powerful teacher to an efficient student; however, standard KD is often less effective for part-structured gait models, where supervision is formed from both part-wise classification logits and part-wise retrieval embeddings. In this paper, we propose GaitKD, a distillation framework that decouples gait knowledge transfer into two complementary components: decision-level distillation and boundary-level distillation. Specifically, GaitKD aligns the teacher and student through part-calibrated logit distillation to transfer inter-class decision relations, while preserving the teacher-induced partitioning of the embedding space through an activation-boundary objective instead of direct feature regression. With a simple aligned part-wise design, GaitKD supports heterogeneous teacher-student gait models without introducing additional inference cost. Experimental results across multiple gait recognition benchmarks and teacher-student configurations show consistent improvements over strong gait baselines. Our study demonstrates that the two transfer components are complementary, and boundary-preserving distillation provides more stable performance than direct feature regression. Source code is available at https://github.com/liyiersan/GaitKD/

Esen K. Tütüncü, Qian Zhou, Frederik Brudy et al.

Current AI writing tools, which rely on text prompts, poorly support the spatial and interactive nature of storytelling where ideas emerge from direct manipulation and play. We present PlayWrite, a mixed-reality system where users author stories by directly manipulating virtual characters and props. A multi-agent AI pipeline interprets these actions into Intent Frames -structured narrative beats visualized as rearrangeable story marbles on a timeline. A large language model then transforms the user's assembled sequence into a final narrative. A user study (N=13) with writers from varying domains found that PlayWrite fosters a highly improvisational and playful process. Users treated the AI as a collaborative partner, using its unexpected responses to spark new ideas and overcome creative blocks. PlayWrite demonstrates an approach for co-creative systems that move beyond text to embrace direct manipulation and play as core interaction modalities.

Lijun Guo, Qian Zhou, Zidi Shi et al.

Interactive segmentation is commonly used in medical image analysis to obtain precise, pixel-level labeling, typically involving iterative user input to correct mislabeled regions. However, existing approaches often fail to fully utilize user knowledge from interactive inputs and achieve comprehensive feature extraction. Specifically, these methods tend to treat all mislabeled regions equally, selecting them randomly for refinement without evaluating each region's potential impact on segmentation quality. Additionally, most models rely solely on spatial domain features, overlooking frequency domain information that could enhance feature extraction and improve performance. To address these limitations, we propose ActiveFreq, a novel interactive segmentation framework that integrates active learning and frequency domain analysis to minimize human intervention while achieving high-quality labeling. ActiveFreq introduces AcSelect, an autonomous module that prioritizes the most informative mislabeled regions, ensuring maximum performance gain from each click. Moreover, we develop FreqFormer, a segmentation backbone incorporating a Fourier transform module to map features from the spatial to the frequency domain, enabling richer feature extraction. Evaluations on the ISIC-2017 and OAI-ZIB datasets demonstrate that ActiveFreq achieves high performance with reduced user interaction, achieving 3.74 NoC@90 on ISIC-2017 and 9.27 NoC@90 on OAI-ZIB, with 23.5% and 12.8% improvements over previous best results, respectively. Under minimal input conditions, such as two clicks, ActiveFreq reaches mIoU scores of 85.29% and 75.76% on ISIC-2017 and OAI-ZIB, highlighting its efficiency and accuracy in interactive medical segmentation.

Jiahao Li, Xinhong Chen, Zhengmin Jiang et al.

Stereo matching achieves significant progress with iterative algorithms like RAFT-Stereo and IGEV-Stereo. However, these methods struggle in ill-posed regions with occlusions, textureless, or repetitive patterns, due to a lack of global context and geometric information for effective iterative refinement. To enable the existing iterative approaches to incorporate global context, we propose the Global Regulation and Excitation via Attention Tuning (GREAT) framework which encompasses three attention modules. Specifically, Spatial Attention (SA) captures the global context within the spatial dimension, Matching Attention (MA) extracts global context along epipolar lines, and Volume Attention (VA) works in conjunction with SA and MA to construct a more robust cost-volume excited by global context and geometric details. To verify the universality and effectiveness of this framework, we integrate it into several representative iterative stereo-matching methods and validate it through extensive experiments, collectively denoted as GREAT-Stereo. This framework demonstrates superior performance in challenging ill-posed regions. Applied to IGEV-Stereo, among all published methods, our GREAT-IGEV ranks first on the Scene Flow test set, KITTI 2015, and ETH3D leaderboards, and achieves second on the Middlebury benchmark. Code is available at https://github.com/JarvisLee0423/GREAT-Stereo.

Huiran Duan, Qian Zhou, Zhongliang Guo et al.

Conventional gait de-identification methods often encounter an inherent trade-off: they either provide insufficient identity suppression or introduce spatiotemporal distortions that impede structure-sensitive downstream applications. We propose GaitProtector, an impersonation-driven gait de-identification framework that formulates privacy protection as a unified objective with two tightly coupled components: (i) obfuscation, which repels the protected gait from the source identity, and (ii) impersonation, which attracts it toward a selected target identity. The target identity serves as a semantic anchor that biases optimization toward structurally plausible gait patterns under the pretrained diffusion prior, helping preserve dominant body shape and motion dynamics. We instantiate this idea through a training-free diffusion latent optimization pipeline. Instead of retraining a generator for each dataset, we invert each input silhouette sequence into the latent trajectory of a pretrained 3D video diffusion model and iteratively optimize latent codes with a differentiable adversarial objective to synthesize protected gaits. Experiments on the CASIA-B dataset show that GaitProtector achieves a 56.7% impersonation success rate under black-box gait recognition and reduces Rank-1 identification accuracy from 89.6% to 15.0%, while maintaining favorable visual and temporal quality. We further evaluate downstream utility on the Scoliosis1K dataset, where diagnostic accuracy decreases only from 91.4% to 74.2%. To the best of our knowledge, this work is the first to leverage pretrained 3D diffusion priors in a training-free manner for silhouette-based gait de-identification.

Kyzyl Monteiro, Evan Atherton, George Fitzmaurice et al.

Editing particle-system visual effects (VFX) is vital for digital storytelling, but achieving controllable, art-directable results remains challenging due to their multi-dimensional nature. Given a large collection of parameters, users must find the ones relevant to their creative goals -- a task that requires a systematic understanding of the particle system and how parameters map to high-level intents, such as making a fire look angry. Elemental Alchemist is a generative interface that transforms user intent into contextualized controls for semantic editing of particle systems. The system introduces two components: a contextual brush palette that generates tools based on scene context, and a generative control panel that surfaces relevant technical parameters and abstracts them to generate mid-level semantic attributes and high-level conceptual controls. An evaluation with 10 novice and 5 expert VFX practitioners shows the system supported users in translating high-level creative goals into particle system parameters.

Yi Wang, Qian Zhou, David Ledo

Automated plot generation for games enhances the player's experience by providing rich and immersive narrative experience that adapts to the player's actions. Traditional approaches adopt a symbolic narrative planning method which limits the scale and complexity of the generated plot by requiring extensive knowledge engineering work. Recent advancements use Large Language Models (LLMs) to drive the behavior of virtual characters, allowing plots to emerge from interactions between characters and their environments. However, the emergent nature of such decentralized plot generation makes it difficult for authors to direct plot progression. We propose a novel plot creation workflow that mediates between a writer's authorial intent and the emergent behaviors from LLM-driven character simulation, through a novel authorial structure called "abstract acts". The writers define high-level plot outlines that are later transformed into concrete character action sequences via an LLM-based narrative planning process, based on the game world state. The process creates "living stories" that dynamically adapt to various game world states, resulting in narratives co-created by the author, character simulation, and player. We present StoryVerse as a proof-of-concept system to demonstrate this plot creation workflow. We showcase the versatility of our approach with examples in different stories and game environments.

Peng Zheng, Qian Zhou

Spiking Neural Networks (SNNs) are well-suited for processing event streams from Dynamic Visual Sensors (DVSs) due to their use of sparse spike-based coding and asynchronous event-driven computation. To extract features from DVS objects, SNNs commonly use event-driven convolution with fixed kernel parameters. These filters respond strongly to features in specific orientations while disregarding others, leading to incomplete feature extraction. To improve the current event-driven convolution feature extraction capability of SNNs, we propose a DVS object recognition model that utilizes a trainable event-driven convolution and a spiking attention mechanism. The trainable event-driven convolution is proposed in this paper to update its convolution kernel through gradient descent. This method can extract local features of the event stream more efficiently than traditional event-driven convolution. Furthermore, the spiking attention mechanism is used to extract global dependence features. The classification performances of our model are better than the baseline methods on two neuromorphic datasets including MNIST-DVS and the more complex CIFAR10-DVS. Moreover, our model showed good classification ability for short event streams. It was shown that our model can improve the performance of event-driven convolutional SNNs for DVS objects.

Kang Min Yoo, Jaegeun Han, Sookyo In et al.

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs.

Zhuoran Lu, Qian Zhou, Yi Wang

Generative AI significantly enhances player agency in interactive narratives (IN) by enabling just-in-time content generation that adapts to player actions. While delegating generation to AI makes IN more interactive, it becomes challenging for authors to control the space of possible narratives - within which the final story experienced by the player emerges from their interaction with AI. In this paper, we present WhatELSE, an AI-bridged IN authoring system that creates narrative possibility spaces from example stories. WhatELSE provides three views (narrative pivot, outline, and variants) to help authors understand the narrative space and corresponding tools leveraging linguistic abstraction to control the boundaries of the narrative space. Taking innovative LLM-based narrative planning approaches, WhatELSE further unfolds the narrative space into executable game events. Through a user study (N=12) and technical evaluations, we found that WhatELSE enables authors to perceive and edit the narrative space and generates engaging interactive narratives at play-time.

Guang Wu, Yun Wang, Qian Zhou et al.

Accurate photovoltaic (PV) power forecasting is critical for integrating renewable energy sources into the grid, optimizing real-time energy management, and ensuring energy reliability amidst increasing demand. However, existing models often struggle with effectively capturing the complex relationships between target variables and covariates, as well as the interactions between temporal dynamics and multivariate data, leading to suboptimal forecasting accuracy. To address these challenges, we propose a novel model architecture that leverages the iTransformer for feature extraction from target variables and employs long short-term memory (LSTM) to extract features from covariates. A cross-attention mechanism is integrated to fuse the outputs of both models, followed by a Kolmogorov-Arnold network (KAN) mapping for enhanced representation. The effectiveness of the proposed model is validated using publicly available datasets from Australia, with experiments conducted across four seasons. Results demonstrate that the proposed model effectively capture seasonal variations in PV power generation and improve forecasting accuracy.

Qian Zhou, Yuanyun Zhang, Shi Li

Healthcare foundation models have largely followed paradigms from natural language processing and computer vision, emphasizing large scale pretraining and deterministic representations over heterogeneous clinical data. However, clinical observations are inherently incomplete, reflecting sparse, irregular, and modality dependent measurements of an underlying physiologic state. In this work, we propose a framework for uncertainty aware foundation modeling that represents each patient not as a point embedding, but as a distribution over plausible latent states. By learning set valued representations and enforcing consistency across partial views of the same patient, the model captures what is invariantly inferable while explicitly encoding epistemic uncertainty. We integrate this formulation with multimodal encoders and scalable self supervised objectives, combining reconstruction, contrastive alignment, and distributional regularization. Across diverse clinical tasks, our approach improves predictive performance, robustness under missing data, and uncertainty calibration relative to strong baselines. These results suggest that modeling what is not observed rather than only what is constitutes a critical inductive bias for healthcare foundation models.

Kuan-Ying Lee, Qian Zhou, Klara Nahrstedt

Multi-camera systems are indispensable in movies, TV shows, and other media. Selecting the appropriate camera at every timestamp has a decisive impact on production quality and audience preferences. Learning-based view recommendation frameworks can assist professionals in decision-making. However, they often struggle outside of their training domains. The scarcity of labeled multi-camera view recommendation datasets exacerbates the issue. Based on the insight that many videos are edited from the original multi-camera videos, we propose transforming regular videos into pseudo-labeled multi-camera view recommendation datasets. Promisingly, by training the model on pseudo-labeled datasets stemming from videos in the target domain, we achieve a 68% relative improvement in the model's accuracy in the target domain and bridge the accuracy gap between in-domain and never-before-seen domains.

Qian Zhou, Xianda Guo, Jilong Wang et al.

Generalized gait recognition remains challenging due to significant domain shifts in viewpoints, appearances, and environments. Mixed-dataset training has recently become a practical route to improve cross-domain robustness, but it introduces underexplored issues: 1) inter-dataset supervision conflicts, which distract identity learning, and 2) redundant or noisy samples, which reduce data efficiency and may reinforce dataset-specific patterns. To address these challenges, we introduce a unified paradigm for cross-dataset gait learning that simultaneously improves motion-signal quality and supervision consistency. We first increase the reliability of training data by suppressing sequences dominated by redundant gait cycles or unstable silhouettes, guided by representation redundancy and prediction uncertainty. This refinement concentrates learning on informative gait dynamics when mixing heterogeneous datasets. In parallel, we stabilize supervision by disentangling metric learning across datasets, forming triplets within each source to prevent destructive cross-domain gradients while preserving transferable identity cues. These components act in synergy to stabilize optimization and strengthen generalization without modifying network architectures or requiring extra annotations. Experiments on CASIA-B, OU-MVLP, Gait3D, and GREW with both GaitBase and DeepGaitV2 backbones consistently show improved cross-domain performance without sacrificing in-domain accuracy. These results demonstrate that data selection and aligning supervision effectively enables scalable mixed-dataset gait learning.

Hongpeng Guo, Shuochao Yao, Zhe Yang et al.

Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale video feeds in real time is data intensive and poses severe challenges to network and computation systems today. We present CrossRoI, a resource-efficient system that enables real time video analytics at scale via harnessing the videos content associations and redundancy across a fleet of cameras. CrossRoI exploits the intrinsic physical correlations of cross-camera viewing fields to drastically reduce the communication and computation costs. CrossRoI removes the repentant appearances of same objects in multiple cameras without harming comprehensive coverage of the scene. CrossRoI operates in two phases - an offline phase to establish cross-camera correlations, and an efficient online phase for real time video inference. Experiments on real-world video feeds show that CrossRoI achieves 42% - 65% reduction for network overhead and 25% - 34% reduction for response delay in real time video analytics applications with more than 99% query accuracy, when compared to baseline methods. If integrated with SotA frame filtering systems, the performance gains of CrossRoI reach 50% - 80% (network overhead) and 33% - 61% (end-to-end delay).

Zhe Yang, Klara Nahrstedt, Hongpeng Guo et al.

The ubiquity of smartphone cameras and IoT cameras, together with the recent boom of deep learning and deep neural networks, proliferate various computer vision driven mobile and IoT applications deployed on the edge. This paper focuses on applications which make soft real time requests to perform inference on their data - they desire prompt responses within designated deadlines, but occasional deadline misses are acceptable. Supporting soft real time applications on a multi-tenant edge server is not easy, since the requests sharing the limited GPU computing resources of an edge server interfere with each other. In order to tackle this problem, we comprehensively evaluate how latency and throughput respond to different GPU execution plans. Based on this analysis, we propose a GPU scheduler, DeepRT, which provides latency guarantee to the requests while maintaining high overall system throughput. The key component of DeepRT, DisBatcher, batches data from different requests as much as possible while it is proven to provide latency guarantee for requests admitted by an Admission Control Module. DeepRT also includes an Adaptation Module which tackles overruns. Our evaluation results show that DeepRT outperforms state-of-the-art works in terms of the number of deadline misses and throughput.