arXiv subjects

Jian Zhao

Publications and source records attributed to Jian Zhao.

At least 145 records · Page 8Linked to original sources

arXiv2025

Physics-inspired Energy Transition Neural Network for Sequence Learning

Recently, the superior performance of Transformers has made them a more robust and scalable solution for sequence modeling than traditional recurrent neural networks (RNNs). However, the effectiveness of Transformer in capturing long-term dependencies is primarily attributed to their comprehensive pair-modeling process rather than inherent inductive biases toward sequence semantics. In this study, we explore the capabilities of pure RNNs and reassess their long-term learning mechanisms. Inspired by the physics energy transition models that track energy changes over time, we propose a effective recurrent structure called the``Physics-inspired Energy Transition Neural Network" (PETNN). We demonstrate that PETNN's memory mechanism effectively stores information over long-term dependencies. Experimental results indicate that PETNN outperforms transformer-based methods across various sequence tasks. Furthermore, owing to its recurrent nature, PETNN exhibits significantly lower complexity. Our study presents an optimal foundational recurrent architecture and highlights the potential for developing effective recurrent neural networks in fields currently dominated by Transformer.

cs.LG↗

arXiv2025

ClassComet: Exploring and Designing AI-generated Danmaku in Educational Videos to Enhance Online Learning

Danmaku, users' live comments synchronized with, and overlaying on videos, has recently shown potential in promoting online video-based learning. However, user-generated danmaku can be scarce-especially in newer or less viewed videos and its quality is unpredictable, limiting its educational impact. This paper explores how large multimodal models (LMM) can be leveraged to automatically generate effective, high-quality danmaku. We first conducted a formative study to identify the desirable characteristics of content- and emotion-related danmaku in educational videos. Based on the obtained insights, we developed ClassComet, an educational video platform with novel LMM-driven techniques for generating relevant types of danmaku to enhance video-based learning. Through user studies, we examined the quality of generated danmaku and their influence on learning experiences. The results indicate that our generated danmaku is comparable to human-created ones, and videos with both content- and emotion-related danmaku showed significant improvement in viewers' engagement and learning outcome.

cs.HC↗

arXiv2025

MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing

Deep visual odometry has demonstrated great advancements by learning-to-optimize technology. This approach heavily relies on the visual matching across frames. However, ambiguous matching in challenging scenarios leads to significant errors in geometric modeling and bundle adjustment optimization, which undermines the accuracy and robustness of pose estimation. To address this challenge, this paper proposes MambaVO, which conducts robust initialization, Mamba-based sequential matching refinement, and smoothed training to enhance the matching quality and improve the pose estimation. Specifically, the new frame is matched with the closest keyframe in the maintained Point-Frame Graph (PFG) via the semi-dense based Geometric Initialization Module (GIM). Then the initialized PFG is processed by a proposed Geometric Mamba Module (GMM), which exploits the matching features to refine the overall inter-frame matching. The refined PFG is finally processed by differentiable BA to optimize the poses and the map. To deal with the gradient variance, a Trending-Aware Penalty (TAP) is proposed to smooth training and enhance convergence and stability. A loop closure module is finally applied to enable MambaVO++. On public benchmarks, MambaVO and MambaVO++ demonstrate SOTA performance, while ensuring real-time running.

cs.CV↗

arXiv2025

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning

Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence on scalar value prediction without leveraging the generative abilities of LLMs, and (3) inability to scale the test-time compute of PRMs. In this work, we introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification before providing judgment for each reasoning step. To obtain high-quality process supervision labels and rationale data, we propose Relative Progress Estimation (RPE) and a rationale synthesis framework that incorporates code verification. Experimental results on ProcessBench and several mathematical reasoning tasks show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset. Through test-time scaling, a 1.5B GenPRM outperforms GPT-4o, and a 7B GenPRM surpasses Qwen2.5-Math-PRM-72B on ProcessBench. Additionally, GenPRM demonstrates strong abilities to serve as a critic model for policy model refinement. This work establishes a new paradigm for process supervision that bridges the gap between PRMs and critic models in LLMs. Our code, model, and data will be available in https://ryanliu112.github.io/GenPRM.

cs.CL↗

arXiv2025

Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model

Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that are excessively customized and devoid of causal connections further undermine the generalizability and interpretability. To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Going beyond this process, we utilize the back-door adjustment to specifically address the sub-regions identified as non-causal in the upstream phase. Specifically, we employ a novel image inpainting technique. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts, offering the possibility of reliable extrapolation for potential data distributions. CaPaint overcomes the high complexity dilemma of optimal ST causal discovery models by reducing the data generation complexity from exponential to quasi-linear levels. Extensive experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%. Moreover, compared to traditional mainstream ST augmenters, CaPaint underscores the potential of diffusion models in ST enhancement, offering a novel paradigm for this field. Our project is available at https://anonymous.4open.science/r/12345-DFCC.

cs.CV↗

arXiv2025

UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation

Vision-and-Language Navigation (VLN), where an agent follows instructions to reach a target destination, has recently seen significant advancements. In contrast to navigation in discrete environments with predefined trajectories, VLN in Continuous Environments (VLN-CE) presents greater challenges, as the agent is free to navigate any unobstructed location and is more vulnerable to visual occlusions or blind spots. Recent approaches have attempted to address this by imagining future environments, either through predicted future visual images or semantic features, rather than relying solely on current observations. However, these RGB-based and feature-based methods lack intuitive appearance-level information or high-level semantic complexity crucial for effective navigation. To overcome these limitations, we introduce a novel, generalizable 3DGS-based pre-training paradigm, called UnitedVLN, which enables agents to better explore future environments by unitedly rendering high-fidelity 360 visual images and semantic features. UnitedVLN employs two key schemes: search-then-query sampling and separate-then-united rendering, which facilitate efficient exploitation of neural primitives, helping to integrate both appearance and semantic information for more robust navigation. Extensive experiments demonstrate that UnitedVLN outperforms state-of-the-art methods on existing VLN-CE benchmarks.

cs.CV↗

arXiv2025

SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks

StarCraft Multi-Agent Challenge (SMAC) has been one of the most commonly used experimental environments in multi-agent reinforcement learning (MARL), where the specific task is to control a set number of allied units to defeat enemy forces. Traditional MARL algorithms often require interacting with the environment for millions of steps to train a parametric model, of which the resulting policies are typically non-interpretable with weak transferability. In this paper, we introduce SMAC-R1 which is based on the Qwen2.5-7B-Base LLM distilled from DeepSeek-Coder-v2.5-236B. Similar to online reinforcement learning after behavior cloning in offline learning process, in our pipeline, agents leverage the DeepSeek LLM to generate decision tree code by providing task descriptions, and the agents are further self-reflected using feedback from the rewards provided by the environment. Based on that, we augment the generated scripts to fine-tune a small LLM, Qwen2.5-7B-Base, to distill the decision-making ability via Supervised Fine-Tuning (SFT) and enhance the script generation ability by the Group Relative Policy Optimization (GRPO) algorithm. We conduct experiments in the original 23 SMAC tasks and 10 newly-designed tasks to demonstrate that our method can produce high-quality, interpretable decision trees with minimal environmental exploration. Moreover, these scripts exhibit strong transferability, successfully applying to homogeneous SMAC environments without modification. We believe this approach offers a new direction for solving decision-making tasks and domain-specific LLM training pipelines in the future.

cs.AI↗

arXiv2025

Eggly: Designing Mobile Augmented Reality Neurofeedback Training Games for Children with Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that affects how children communicate and relate to other people and the world around them. Emerging studies have shown that neurofeedback training (NFT) games are an effective and playful intervention to enhance social and attentional capabilities for autistic children. However, NFT is primarily available in a clinical setting that is hard to scale. Also, the intervention demands deliberately-designed gamified feedback with fun and enjoyment, where little knowledge has been acquired in the HCI community. Through a ten-month iterative design process with four domain experts, we developed Eggly, a mobile NFT game based on a consumer-grade EEG headband and a tablet. Eggly uses novel augmented reality (AR) techniques to offer engagement and personalization, enhancing their training experience. We conducted two field studies (a single-session study and a three-week multi-session study) with a total of five autistic children to assess Eggly in practice at a special education center. Both quantitative and qualitative results indicate the effectiveness of the approach as well as contribute to the design knowledge of creating mobile AR NFT games.

cs.HC↗

arXiv2025

StickMotion: Generating 3D Human Motions by Drawing a Stickman

Text-to-motion generation, which translates textual descriptions into human motions, has been challenging in accurately capturing detailed user-imagined motions from simple text inputs. This paper introduces StickMotion, an efficient diffusion-based network designed for multi-condition scenarios, which generates desired motions based on traditional text and our proposed stickman conditions for global and local control of these motions, respectively. We address the challenges introduced by the user-friendly stickman from three perspectives: 1) Data generation. We develop an algorithm to generate hand-drawn stickmen automatically across different dataset formats. 2) Multi-condition fusion. We propose a multi-condition module that integrates into the diffusion process and obtains outputs of all possible condition combinations, reducing computational complexity and enhancing StickMotion's performance compared to conventional approaches with the self-attention module. 3) Dynamic supervision. We empower StickMotion to make minor adjustments to the stickman's position within the output sequences, generating more natural movements through our proposed dynamic supervision strategy. Through quantitative experiments and user studies, sketching stickmen saves users about 51.5% of their time generating motions consistent with their imagination. Our codes, demos, and relevant data will be released to facilitate further research and validation within the scientific community.

cs.CV↗

arXiv2025

DiffBrush:Just Painting the Art by Your Hands

The rapid development of image generation and editing algorithms in recent years has enabled ordinary user to produce realistic images. However, the current AI painting ecosystem predominantly relies on text-driven diffusion models (T2I), which pose challenges in accurately capturing user requirements. Furthermore, achieving compatibility with other modalities incurs substantial training costs. To this end, we introduce DiffBrush, which is compatible with T2I models and allows users to draw and edit images. By manipulating and adapting the internal representation of the diffusion model, DiffBrush guides the model-generated images to converge towards the user's hand-drawn sketches for user's specific needs without additional training. DiffBrush achieves control over the color, semantic, and instance of objects in images by continuously guiding the latent and instance-level attention map during the denoising process of the diffusion model. Besides, we propose a latent regeneration, which refines the randomly sampled noise in the diffusion model, obtaining a better image generation layout. Finally, users only need to roughly draw the mask of the instance (acceptable colors) on the canvas, DiffBrush can naturally generate the corresponding instance at the corresponding location.

cs.CV↗

arXiv2025

Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design Tokens

Expressing design intent using natural language prompts requires designers to verbalize the ambiguous visual details concisely, which can be challenging or even impossible. To address this, we introduce Brickify, a visual-centric interaction paradigm -- expressing design intent through direct manipulation on design tokens. Brickify extracts visual elements (e.g., subject, style, and color) from reference images and converts them into interactive and reusable design tokens that can be directly manipulated (e.g., resize, group, link, etc.) to form the visual lexicon. The lexicon reflects users' intent for both what visual elements are desired and how to construct them into a whole. We developed Brickify to demonstrate how AI models can interpret and execute the visual lexicon through an end-to-end pipeline. In a user study, experienced designers found Brickify more efficient and intuitive than text-based prompts, allowing them to describe visual details, explore alternatives, and refine complex designs with greater ease and control.

cs.HC↗

arXiv2025

AccessFixer: Enhancing GUI Accessibility for Low Vision Users With R-GCN Model

The Graphical User Interface (GUI) plays a critical role in the interaction between users and mobile applications (apps), aiming at facilitating the operation process. However, due to the variety of functions and non-standardized design, GUIs might have many accessibility issues, like the size of components being too small or their intervals being narrow. These issues would hinder the operation of low vision users, preventing them from obtaining information accurately and conveniently. Although several technologies and methods have been proposed to address these issues, they are typically confined to issue identification, leaving the resolution in the hands of developers. Moreover, it can be challenging to ensure that the color, size, and interval of the fixed GUIs are appropriately compared to the original ones. In this work, we propose a novel approach named AccessFixer, which utilizes the Relational-Graph Convolutional Neural Network (R-GCN) to simultaneously fix three kinds of accessibility issues, including small sizes, narrow intervals, and low color contrast in GUIs. With AccessFixer, the fixed GUIs would have a consistent color palette, uniform intervals, and adequate size changes achieved through coordinated adjustments to the attributes of related components. Our experiments demonstrate the effectiveness and usefulness of AccessFixer in fixing GUI accessibility issues. After fixing 30 real-world apps, our approach solves an average of 81.2% of their accessibility issues. Also, we apply AccessFixer to 10 open-source apps by submitting the fixed results with pull requests (PRs) on GitHub. The results demonstrate that developers approve of our submitted fixed GUIs, with 8 PRs being merged or under fixing. A user study examines that low vision users host a positive attitude toward the GUIs fixed by our method.

cs.SE↗

arXiv2025

Don't Confuse! Redrawing GUI Navigation Flow in Mobile Apps for Visually Impaired Users

Mobile applications (apps) are integral to our daily lives, offering diverse services and functionalities. They enable sighted users to access information coherently in an extremely convenient manner. However, it remains unclear if visually impaired users, who rely solely on the screen readers (e.g., Talkback) to navigate and access app information, can do so in the correct and reasonable order. This may result in significant information bias and operational errors. Considering these issues, in this work, we proposed a method named RGNF (Re-draw GUI Navigation Flow). It aimed to enhance the understandability and coherence of accessing the content of each component within the Graphical User Interface (GUI), together with assisting developers in creating well-designed GUI navigation flow (GNF). This method was inspired by the characteristics identified in our preliminary study, where visually impaired users expected navigation to be associated with close position and similar shape of GUI components that were read consecutively. Thus, our method relied on the principles derived from the Gestalt psychological model, aiming to group GUI components into different regions according to the laws of proximity and similarity, thereby redrawing the GNFs. To evaluate the effectiveness of our method, we calculated sequence similarity values before and after redrawing the GNF, and further employed the tools proposed by Alotaibi et al. to measure the reachability of GUI components. Our results demonstrated a substantial improvement in similarity (0.921) compared to the baseline (0.624), together with the reachability (90.31%) compared to the baseline GNF (74.35%). Furthermore, a qualitative user study revealed that our method had a positive effect on providing visually impaired users with an improved user experience.

cs.SE↗

arXiv2025

TherAIssist: Assisting Art Therapy Homework and Client-Practitioner Collaboration through Human-AI Interaction

Art therapy homework is essential for fostering clients' reflection on daily experiences between sessions. However, current practices present challenges: clients often lack guidance for completing tasks that combine art-making and verbal expression, while therapists find it difficult to track and tailor homework. How HCI systems might support art therapy homework remains underexplored. To address this, we present TherAIssist, comprising a client-facing application leveraging human-AI co-creative art-making and conversational agents to facilitate homework, and a therapist-facing application enabling customization of homework agents and AI-compiled homework history. A 30-day field study with 24 clients and 5 therapists showed how TherAIssist supported clients' homework and reflection in their everyday settings. Results also revealed how therapists infused their practice principles and personal touch into the agents to offer tailored homework, and how AI-compiled homework history became a meaningful resource for in-session interactions. Implications for designing human-AI systems to facilitate asynchronous client-practitioner collaboration are discussed.

cs.HC↗

arXiv2025

Are your apps accessible? A GCN-based accessibility checker for low vision users

Context: Accessibility issues (e.g., small size and narrow interval) in mobile applications (apps) lead to obstacles for billions of low vision users in interacting with Graphical User Interfaces (GUIs). Although GUI accessibility scanning tools exist, most of them perform rule-based check relying on complex GUI hierarchies. This might make them detect invisible redundant information, cannot handle small deviations, omit similar components, and is hard to extend. Objective: In this paper, we propose a novel approach, named ALVIN (Accessibility Checker for Low Vision), which represents the GUI as a graph and adopts the Graph Convolutional Neural Networks (GCN) to label inaccessible components. Method: ALVIN removes invisible views to prevent detecting redundancy and uses annotations from low vision users to handle small deviations. Also, the GCN model could consider the relations between GUI components, connecting similar components and reducing the possibility of omission. ALVIN only requires users to annotate the relevant dataset when detecting new kinds of issues. Results: Our experiments on 48 apps demonstrate the effectiveness of ALVIN, with precision of 83.5%, recall of 78.9%, and F1-score of 81.2%, outperforming baseline methods. In RQ2, the usefulness is verified through 20 issues submitted to open-source apps. The RQ3 also illustrates the GCN model is better than other models. Conclusion: To summarize, our proposed approach can effectively detect accessibility issues in GUIs for low vision users, thereby guiding developers in fixing them efficiently.

cs.SE↗

arXiv2025

BIG-AOME: Designing Bodily Interaction Gamification towards Anti-sedentary Online Meeting Environments

Online meetings have become an integral part of daily life, but prolonged screen time poses significant health risks. While various interventions address sedentary lifestyles, few focus on mitigating sedentary behavior during online meetings. Design opportunities in this context remain underexplored. This study investigates the design of gamified bodily interactions as anti-sedentary measures during online meetings using a research through design approach. In collaboration with 11 users, we co-designed and iterated three prototypes, resulting in the BIG-AOME (Bodily Interaction Gamification towards Anti-sedentary Online Meeting Environments) framework. User studies with 15 participants across three groups evaluated these prototypes through semi-structured interviews analyzed using Hsieh's qualitative content analysis. Findings show that gamified bodily interactions encourage physical movement while reducing awkwardness during online meetings. Participants valued the social engagement fostered by cooperative and competitive elements in these games, enhancing social dynamics while encouraging physical movement. Such games can also serve as online icebreakers or playful decision-making tools. This study offers a comprehensive analysis of design dimensions within the BIG-AOME framework, including body engagement, attention, bodily interplay, timeliness, and virtual/physical environments, highlighting the potential of anti-sedentary bodily interactions to mitigate sedentary behavior and enhance social connections in online meetings.

cs.HC↗

arXiv2025

Leader and Follower: Interactive Motion Generation under Trajectory Constraints

With the rapid advancement of game and film production, generating interactive motion from texts has garnered significant attention due to its potential to revolutionize content creation processes. In many practical applications, there is a need to impose strict constraints on the motion range or trajectory of virtual characters. However, existing methods that rely solely on textual input face substantial challenges in accurately capturing the user's intent, particularly in specifying the desired trajectory. As a result, the generated motions often lack plausibility and accuracy. Moreover, existing trajectory - based methods for customized motion generation rely on retraining for single - actor scenarios, which limits flexibility and adaptability to different datasets, as well as interactivity in two-actor motions. To generate interactive motion following specified trajectories, this paper decouples complex motion into a Leader - Follower dynamic, inspired by role allocation in partner dancing. Based on this framework, this paper explores the motion range refinement process in interactive motion generation and proposes a training-free approach, integrating a Pace Controller and a Kinematic Synchronization Adapter. The framework enhances the ability of existing models to generate motion that adheres to trajectory by controlling the leader's movement and correcting the follower's motion to align with the leader. Experimental results show that the proposed approach, by better leveraging trajectory information, outperforms existing methods in both realism and accuracy.

cs.RO↗

arXiv2025

"You'll Be Alice Adventuring in Wonderland!" Processes, Challenges, and Opportunities of Creating Animated Virtual Reality Stories

Animated virtual reality (VR) stories, combining the presence of VR and the artistry of computer animation, offer a compelling way to deliver messages and evoke emotions. Motivated by the growing demand for immersive narrative experiences, more creators are creating animated VR stories. However, a holistic understanding of their creation processes and challenges involved in crafting these stories is still limited. Based on semi-structured interviews with 21 animated VR story creators, we identify ten common stages in their end-to-end creation processes, ranging from idea generation to evaluation, which form diverse workflows that are story-driven or visual-driven. Additionally, we highlight nine unique issues that arise during the creation process, such as a lack of reference material for multi-element plots, the absence of specific functionalities for story integration, and inadequate support for audience evaluation. We compare the creation of animated VR stories to general XR applications and distill several future research opportunities.

cs.HC↗