arXiv subjects

Jiale Li

Publications and source records attributed to Jiale Li.

At least 19 recordsLinked to original sources

arXiv2026

TeachUp: Facilitating Early-Stage Teachers to Learn Instructional Strategies from Classroom Videos with Reflective Support

Recorded videos of offline open classes provide good examples for early-stage teachers to learn instructional strategies, e.g., how to organize cooperative learning. However, learning by watching these videos is challenging, as these strategies are implicitly performed, and it lacks in-situ reflective support. In this paper, via a formative study (N=9), we design TeachUp to support the learning of instructional strategies from classroom teaching videos. TeachUp adopts an LLM-powered pipeline to detect nine instructional strategies in videos (precision = 63.4%), provides reflective questions and hints while watching, and generates customized practices with reflective feedback. A within-subjects study (N=16) shows that compared to a traditional video-playing and self-practicing baseline, early-stage teachers with TeachUp are more engaged in learning and perform better in applying learned strategies to new tasks. Interviews with four in-service teachers further generalize our findings and TeachUp's use cases. We discuss practical implications for fostering video-based learning of instructional strategies.

cs.HC↗

arXiv2026

MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models

Video Large Language Models (VideoLLMs) have shown strong progress in video understanding, yet they still suffer from hallucinations that are inconsistent with visual evidence. Existing benchmarks mainly focus on object hallucination or coarse action perception, leaving a key video-specific problem underexplored: motion hallucination, in which models infer human motions that are absent from the video. We present MoHallBench, a benchmark for diagnosing motion hallucination in VideoLLMs. MoHallBench systematically evaluates three major sources of hallucination: co-occurrence priors, sequential inference, and similarity confusion. It contains 11,306 video clips and 40,493 question-answer pairs, covering binary-choice, multiple-choice, and generative settings. We further introduce a bi-directional questioning protocol with bias-aware metrics to reduce affirmation bias in binary evaluation. Experiments on ten recent open-source VideoLLMs reveal a clear decoupling between action recognition and hallucination resistance, as models that perform well on positive action recognition often fail on adversarial negatives. Among all settings, sequential inference hallucination is the most severe, showing that current models tend to over-infer expected outcomes from partial motion cues. Our analyses further confirm that stronger priors and finer-grained similarity substantially amplify hallucination. We hope MoHallBench can facilitate future evaluation and mitigation of motion hallucination in VideoLLMs.

cs.CV↗

arXiv2026

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally static in enterprise deployment. The LLM weights, system prompts, tool repertoires, and in-context harnesses are frozen at deployment time, and any improvement requires a manual loop of human-curated data collection, offline fine-tuning, modification of the agentic paradigm, and re-deployment. Recent work on self-evolving agents, such as OpenClaw for individual users, indicates that the next leap in agent capability will come from agents that continually learn from their own experience. In this paper, we argue that this vision for self-evolving agent deployment is being held back for enterprise-level large-scale agentic service not by reinforcement learning (RL) algorithms but by agentic online RL systems. Specifically, current agentic RL systems and the surrounding observability software stack are inadequate along three essential aspects: (i) there is no standardized agent trajectory data protocol capable of carrying RL learning signals at step granularity across heterogeneous agent paradigms; (ii) there is no enterprise-grade comprehensive data proxy that converts real workloads into governed learning substrates; and (iii) there is no unified agent evolution control plane that automatically decides, based on trajectory statistics, when to update policy weights or evolve the in-context harness. The next generation of agentic RL systems must be co-designed around these three pillars, and we sketch concrete architectures, case studies, and counter-arguments. We instantiate one branch through AReaL2.0, reorganizing existing RL infrastructure into an agent-oriented online RL loop for policy weight updates from deployed workloads.

cs.DC↗

arXiv2026

Cloaking of Arbitrarily Shaped Large-Scale Objects Through the Injection of Electromagnetic Invisibility Genes

Full-space electromagnetic invisibility mainly includes light-bending and scattering-cancellation cloaking. Light-bending cloaking causes double-blind phenomenon and is incompatible with sensing, while scattering-cancellation cloaking allows signal interaction and is more suitable for sensors and communication systems. However, traditional scattering-cancellation cloaking depends highly on target shape and size, making it difficult to realize cloaking for irregular, inhomogeneous and electrically large objects. To solve these problems, this work proposes an electromagnetic invisibility gene injection strategy inspired by biological camouflage. Objects are decomposed into subwavelength units, and customized invisibility genes are injected into each unit according to electromagnetic parameters to achieve overall scattering cancellation. Simulations and microwave experiments verify that this method can realize efficient cloaking for objects with arbitrary shapes, dielectric constants from 2 to 10, and different unit morphologies. This strategy breaks the limits of traditional cloaking and provides a universal, flexible scheme for practical applications such as antenna supports and electromagnetic transparent covers.

physics.optics↗

arXiv2026

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative ridge-and-crease textures. However, the robustness of deep palmprint recognition systems against physically realizable attacks remains insufficiently understood. Existing studies are largely confined to the digital setting and do not adequately account for the texture-dominant nature of palmprint recognition or the distortions introduced during physical acquisition. To address this gap, we propose CAAP, a capture-aware adversarial patch framework for palmprint recognition. CAAP learns a universal patch that can be reused across inputs while remaining effective under realistic acquisition variation. To match the structural characteristics of palmprints, the framework adopts a cross-shaped patch topology, which enlarges spatial coverage under a fixed pixel budget and more effectively disrupts long-range texture continuity. CAAP further integrates three modules: ASIT for input-conditioned patch rendering, RaS for stochastic capture-aware simulation, and MS-DIFE for feature-level identity-disruptive guidance. We evaluate CAAP on the Tongji, IITD, and AISEC datasets against generic CNN backbones and palmprint-specific recognition models. Experiments show that CAAP achieves strong untargeted and targeted attack performance with favorable cross-model and cross-dataset transferability. The results further show that, although adversarial training can partially reduce the attack success rate, substantial residual vulnerability remains. These findings indicate that deep palmprint recognition systems remain vulnerable to physically realizable, capture-aware adversarial patch attacks, underscoring the need for more effective defenses in practice. Code available at https://github.com/ryliu68/CAAP.

cs.CV↗

arXiv2026

MemoAct: Atkinson-Shiffrin-Inspired Hierarchical Memory-Augmented Policy for Robotic Manipulation

Memory-augmented robotic policies are essential in handling memory-dependent tasks. However, existing approaches typically rely on simply extending the observation window, struggling to simultaneously achieve precise task-state tracking and robust long-horizon retention. To overcome these challenges, inspired by the Atkinson--Shiffrin memory model, we propose MemoAct, a hierarchical memory-augmented policy that leverages distinct memory tiers to tackle specific bottlenecks. Specifically, sensory memory filters immediate perceptual inputs, lossless short-term memory supports precise task-state tracking, and compressed long-term memory facilitates robust long-horizon retention. To enrich the evaluation landscape, we construct MemoryRTBench based on RoboTwin 2.0, comprising 6 manipulation tasks that systematically evaluate policy memory capabilities across three dimensions: sequential, spatial, and episodic memory. Extensive experiments across simulated and real-world scenarios demonstrate that MemoAct achieves superior performance compared to both existing Markovian baselines and history-aware policies. The project page is available at https://tlf-tlf.github.io/MemoActPage/.

cs.RO↗

arXiv2025

Non-Rival Data as Rival Products: An Encapsulation-Forging Approach for Data Synthesis

The non-rival nature of data creates a dilemma for firms: sharing data unlocks value but risks eroding competitive advantage. Existing data synthesis methods often exacerbate this problem by creating data with symmetric utility, allowing any party to extract its value. This paper introduces the Encapsulation-Forging (EnFo) framework, a novel approach to generate rival synthetic data with asymmetric utility. EnFo operates in two stages: it first encapsulates predictive knowledge from the original data into a designated ``key'' model, and then forges a synthetic dataset by optimizing the data to intentionally overfit this key model. This process transforms non-rival data into a rival product, ensuring its value is accessible only to the intended model, thereby preventing unauthorized use and preserving the data owner's competitive edge. Our framework demonstrates remarkable sample efficiency, matching the original data's performance with a fraction of its size, while providing robust privacy protection and resistance to misuse. EnFo offers a practical solution for firms to collaborate strategically without compromising their core analytical advantage.

cs.LG↗

arXiv2025

MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models

Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this gap, we conduct the first systematic study of hallucinations in multi-image MLLMs and propose MIHBench, a benchmark specifically tailored for evaluating object-related hallucinations across multiple images. MIHBench comprises three core tasks: Multi-Image Object Existence Hallucination, Multi-Image Object Count Hallucination, and Object Identity Consistency Hallucination, targeting semantic understanding across object existence, quantity reasoning, and cross-view identity consistency. Through extensive evaluation, we identify key factors associated with the occurrence of multi-image hallucinations, including: a progressive relationship between the number of image inputs and the likelihood of hallucination occurrences; a strong correlation between single-image hallucination tendencies and those observed in multi-image contexts; and the influence of same-object image ratios and the positional placement of negative samples within image sequences on the occurrence of object identity consistency hallucination. To address these challenges, we propose a Dynamic Attention Balancing mechanism that adjusts inter-image attention distributions while preserving the overall visual attention proportion. Experiments across multiple state-of-the-art MLLMs demonstrate that our method effectively reduces hallucination occurrences and enhances semantic integration and reasoning stability in multi-image scenarios.

cs.CV↗

arXiv2025

An alternative method of adjusting for multiple comparison in medical research

Background Most methods of adjusting for multiplicity focus primarily on controlling type I errors and rarely consider type II errors. We propose a new method that considers controlling for false-positive findings while ensuring sufficient statistical power. Methods We proposed a new method for multiple corrections called (Beta-exponential Adjustment, BEA) that considered the statistical power to control for type I errors while also considering the probability of type II errors. We conducted simulation studies to evaluate the performance characteristic of multiple testing correction procedures. We calculated sensitivity, specificity, and power separately for different sample sizes and number of biomarkers and compared them with the Bonferroni, Holm, and Benjamini-Hochberg (BH) correction methods. Results The results demonstrated that our proposed BEA correction method exhibited the highest sensitivity at different sample sizes and biomarkers (e.g., sensitivity: BEA 0.8 versus BH 0.62 at sample size at 1000, tested biomarkers at 1000 and positive rate at 30%). With different sample sizes and number of biomarkers, the BEA correction method demonstrated comparable specificity compared with traditional methods. Moreover, we observed that the BEA-corrected had the highest statistical power than other methods, when the outcome was relatively rare. Conclusion We proposed the BEA multiple correction method to adjust for multiple comparisons while considering statistical power. The BEA method demonstrated a higher sensitivity, comparable specificity, and higher statistical power, compared with traditional correction methods in different conditions. The BEA correction method can be an alternative of traditional methods of adjusting for multiplicity, especially in studies with small sample size, rare outcomes, or substantial number of biomarkers.

stat.AP↗

arXiv2025

SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion

Panel discussion allows the audience to learn different perspectives through interactive discussions among experts moderated by a host and a Q&A session with the audience. Despite its benefits, panel discussion in the real world is inaccessible to many who do not have the privilege to participate due to geographical, financial, and time constraints. We present SimuPanel, which simulates panel discussions among academic experts through LLM-based multi-agent interaction. It enables users to define topics of interest for the panel, observe the expert discussion, engage in Q&A, and take notes. SimuPanel employs a host-expert architecture where each panel member is simulated by an agent with specialized expertise, and the panel is visualized in an immersive 3D environment to enhance engagement. Traditional dialogue generation struggles to capture the depth and interactivity of real-world panel discussions. To address this limitation, we propose a novel multi-agent interaction framework that simulates authentic panel dynamics by modeling reasoning strategies and personas of experts grounded in multimedia sources. This framework enables agents to dynamically recall and contribute to the discussion based on past experiences from diverse perspectives. Our technical evaluation and the user study with university students show that SimuPanel was able to simulate more in-depth discussions and engage participants to interact with and reflect on the discussions. As a first step in this direction, we offer design implications for future avenues to improve and harness the power of panel discussion for multimedia learning.

cs.HC↗

arXiv2025

Implementation of ultra-broadband optical null media via space-folding

Optical null medium (ONM) has garnered significant attention in electromagnetic wave manipulation. However, existing ONM implementations suffer from either narrow operational bandwidths or low efficiency. Here, we demonstrate an ultra-broadband ONM design that simultaneously addresses both challenges - achieving broad bandwidth while preserving perfect impedance matching with air for near-unity transmittance. The proposed space-folding ONM is realized by introducing precisely engineered folds into a metal channel array, creating an effective dispersion-free medium that enables independent phase control in each channel. The design incorporates optimized boundary layers implemented through gradually tapered folding structures, achieving perfect impedance matching with the surrounding medium. Beam bending effect and broadband beam focusing effect are experimentally verified using the proposed space-folding ONM. Due to its simple material requirements, broadband characteristics, and high transmittance, the proposed space-folding ONM shows potential for applications in electromagnetic camouflage, beam steering devices and ultra-compact microwave components.

physics.optics↗

arXiv2024

TraDiffusion: Trajectory-Based Training-Free Image Generation

In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion. This novel method allows users to effortlessly guide image generation via mouse trajectories. To achieve precise control, we design a distance awareness energy function to effectively guide latent variables, ensuring that the focus of generation is within the areas defined by the trajectory. The energy function encompasses a control function to draw the generation closer to the specified trajectory and a movement function to diminish activity in areas distant from the trajectory. Through extensive experiments and qualitative assessments on the COCO dataset, the results reveal that TraDiffusion facilitates simpler, more natural image control. Moreover, it showcases the ability to manipulate salient regions, attributes, and relationships within the generated images, alongside visual input based on arbitrary or enhanced trajectories.

cs.CV↗

arXiv2024

An Edge AI System Based on FPGA Platform for Railway Fault Detection

As the demands for railway transportation safety increase, traditional methods of rail track inspection no longer meet the needs of modern railway systems. To address the issues of automation and efficiency in rail fault detection, this study introduces a railway inspection system based on Field Programmable Gate Array (FPGA). This edge AI system collects track images via cameras and uses Convolutional Neural Networks (CNN) to perform real-time detection of track defects and automatically reports fault information. The innovation of this system lies in its high level of automation and detection efficiency. The neural network approach employed by this system achieves a detection accuracy of 88.9%, significantly enhancing the reliability and efficiency of detection. Experimental results demonstrate that this FPGA-based system is 1.39* and 4.67* better in energy efficiency than peer implementation on the GPU and CPU platform, respectively.

cs.CV↗

arXiv2024

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through test-time optimization of a learnable latent variable. We observe that attention, as the core module of MLLMs, connects text prompt tokens and visual tokens, ultimately determining the final results. Our approach involves adjusting visual tokens from the MLP output at test time, controlling the attention response to ensure text prompt tokens attend to visual tokens in referring regions. We optimize a learnable latent variable based on an energy function, enhancing the strength of referring regions in the attention map. This enables detailed region description and reasoning without the need for substantial training costs or model retraining. Our method offers a promising direction for integrating referring abilities into MLLMs, and supports referring with box, mask, scribble and point. The results demonstrate that our method exhibits out-of-domain generalization and interpretability.

cs.CV↗

arXiv2024

Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models

The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by introducing object detectors. However, these efforts neglect hallucinations in inter-object relationships, which is essential for visual comprehension. In this work, we introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination. R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension. We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object. The visual instruction tuning dataset's long-tail distribution significantly impacts LVLMs' understanding of visual relationships. Furthermore, our analysis reveals that current LVLMs tend to disregard visual content and overly rely on the common sense knowledge of Large Language Models. They also struggle with reasoning about spatial relationships based on contextual information.

cs.CV↗

arXiv2024

A Map of Exploring Human Interaction patterns with LLM: Insights into Collaboration and Creativity

The outstanding performance capabilities of large language model have driven the evolution of current AI system interaction patterns. This has led to considerable discussion within the Human-AI Interaction (HAII) community. Numerous studies explore this interaction from technical, design, and empirical perspectives. However, the majority of current literature reviews concentrate on interactions across the wider spectrum of AI, with limited attention given to the specific realm of interaction with LLM. We searched for articles on human interaction with LLM, selecting 110 relevant publications meeting consensus definition of Human-AI interaction. Subsequently, we developed a comprehensive Mapping Procedure, structured in five distinct stages, to systematically analyze and categorize the collected publications. Applying this methodical approach, we meticulously mapped the chosen studies, culminating in a detailed and insightful representation of the research landscape. Overall, our review presents an novel approach, introducing a distinctive mapping method, specifically tailored to evaluate human-LLM interaction patterns. We conducted a comprehensive analysis of the current research in related fields, employing clustering techniques for categorization, which enabled us to clearly delineate the status and challenges prevalent in each identified area.

cs.HC↗

arXiv2024

Evolving Agents: Interactive Simulation of Dynamic and Diverse Human Personalities

Human-like Agents with diverse and dynamic personalities could serve as an essential design probe in the process of user-centered design, thereby enabling designers to enhance the user experience of interactive applications. In this article, we introduce Evolving Agents, a novel agent architecture that consists of two systems: Personality and Behavior. The Personality system includes Cognition, Emotion, and Character Growth modules. The Behavior system comprises two modules: Planning and Action. We also build a simulation platform that enables agents to interact with the environment and other agents. Evolving Agents can simulate the human personality evolution process. Compared to its initial state, agents' personality and behavior patterns undergo believable development after several days of simulation. Agents reflect on their behavior to reason and develop new personality traits. These traits, in turn, generate new behavior patterns, forming a feedback loop-like personality evolution. Our experiment utilized a simulation platform with ten agents for evaluation. During the assessment, these agents experienced believable and inspirational personality evolution. Through ablation and control experiments, we demonstrated the effectiveness of agent personality evolution, and all of our agent architecture modules contribute to creating believable human-like agents with diverse and dynamic personalities. We also demonstrated through workshops how Evolving Agents could inspire designers.

cs.HC↗

arXiv2024

A Novel Computing Paradigm for MobileNetV3 using Memristor

The increasing computational demands of deep learning models pose significant challenges for edge devices. To address this, we propose a memristor-based circuit design for MobileNetV3, specifically for image classification tasks. Our design leverages the low power consumption and high integration density of memristors, making it suitable for edge computing. The architecture includes optimized memristive convolutional modules, batch normalization modules, activation function modules, global average pooling modules, and fully connected modules. Experimental results on the CIFAR-10 dataset show that our memristor-based MobileNetV3 achieves over 90% accuracy while significantly reducing inference time and energy consumption compared to traditional implementations. This work demonstrates the potential of memristor-based designs for efficient deployment of deep learning models in resource-constrained environments.

cs.AR↗