Searcharxiv⌕ Search

arXiv subjects

Yujia Liu

Publications and source records attributed to Yujia Liu.

At least 19 recordsLinked to original sources

Embedded Arena: Iterative Optimization via Hardware Feedback

As AI moves into the physical world, from robots to environmental sensors to medical wearables, it increasingly relies on local inference to meet latency, communication, or privacy constraints. Optimizing models for heterogeneous edge hardware such as microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware by compiling, flashing, and measuring on real hardware, enabling closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with <3.3% accuracy loss and 400x for audio with <6% Feature Error Rate loss, enabling battery-free operation on a commercial MCU via solar harvesting. We demonstrate practical impact in two real-world systems: an elk-detection camera trap (96.7% accuracy) and a phonetic-transcription wearable (8.37% FER) for child development research.

cs.AR↗

High-dimensional covariate-assisted ranking

Ranking data in modern applications often involves covariate vectors whose dimension grows with the number of objects. Identifying relevant covariates and integrating them with item-specific utilities can yield better predictive performance. In this work, we study a Plackett--Luce model that incorporates both item-specific utilities and high-dimensional covariate effects. Under a sparsity assumption on the covariate coefficients, we establish a necessary and sufficient condition for identifiability in terms of the Kruskal rank of the restricted covariate design. We then propose an $\ell_1$-regularized maximum likelihood estimator for the covariate coefficients. Under suitable design and connectivity conditions, we establish the existence and uniqueness of the estimator with probability tending to one, as well as its uniform consistency. With an additional minimum-signal condition, we further establish exact support recovery. Our analysis combines a hypergraph-based chaining technique with a profile-likelihood perturbation analysis, yielding estimation rates that explicitly capture the effects of the comparison hypergraph's connectivity and the underlying sparsity level. Numerical experiments using synthetic data and a horse racing dataset corroborate our theoretical findings.

stat.ME↗

Shape Distribution Matters: Shape-Specific Mixture-of-Experts for Amodal Segmentation Under Diverse Occlusions

Amodal segmentation aims to predict complete object masks covering both visible and occluded regions, serving as a critical foundation for robust multimedia scene understanding and interactive media editing. This task poses significant challenges in complex visual media due to severe occlusions and extreme shape variation, ranging from rigid furniture to highly deformable clothing. Existing one-size-fits-all approaches struggle to reason about diverse amodal shapes in multimedia content due to limited representation capacity. While a mixture-of-experts framework is a natural solution, naively applying it without considering the underlying shape distribution leads to mismatched routing and redundant experts. To address these issues, we introduce ShapeMoE, a shape-specific sparse mixture-of-experts framework designed for complex visual scene parsing. The key idea is to learn a latent shape distribution space and dynamically route each object to a lightweight expert tailored to its geometric characteristics. Specifically, ShapeMoE encodes each object into a compact Gaussian embedding that captures key shape features. A Shape-Aware Sparse Router then maps the object to the most suitable expert, enabling precise shape-aware routing. Each expert is lightweight and specializes in recovering occluded regions for specific shape patterns. ShapeMoE is designed for shape-specific expert specialization while maintaining computational efficiency. Extensive experiments on three challenging benchmarks demonstrate that ShapeMoE consistently outperforms state-of-the-art methods. Beyond advancing fundamental visual reasoning, ShapeMoE provides a robust and efficient visual prior for downstream multimedia applications, particularly in occlusion-heavy immersive environments.

cs.CV↗

Asking What Matters: Disagreement-Guided Ambiguity Detection for Interactive Text-to-SQL

Interactive text-to-SQL requires an LLM agent not only to generate executable SQL, but also to decide which uncertainty to clarify within a limited interaction budget. However, current clarification policies have three limitations: (i) they target surface ambiguity without testing its SQL impact; (ii) they miss ambiguities implicit in schema routes or domain knowledge; and (iii) they spend limited turns on unfocused or redundant questions. These limitations expose a critical challenge: identifying SQL-impacting ambiguity before the intended SQL is known. In this paper, we propose DisGuAD, a Disagreement-Guided Ambiguity Detection framework that specializes clarification selection. DisGuAD treats disagreement among plausible SQL interpretations as direct evidence of which uncertainty matters to the final query. Specifically, it constructs a query-term inventory, elicits contrastive SQL interpretations through complementary probe families, compares their canonical SQL components, and attributes recurring differences to user-facing clarification targets. A lightweight prioritization and dialogue-state mechanism then selects one high-impact unresolved target for clarification. Experiments on BIRD-Interact Lite and Full with two LLM backbones demonstrate consistent improvements in task success and clarification quality. Compared with the original interaction policy, DisGuAD improves normalized Reward by 4.40--8.97 points and raises overall critical-ambiguity coverage from 48.62% to 82.75% and from 45.76% to 85.14%. Its clarification signals further improve two independently designed static text-to-SQL frameworks by up to 13.97 Reward points while keeping their SQL generators fixed. These results demonstrate that disagreement among plausible SQL queries provides actionable evidence for selecting clarification targets that matter to downstream generation.

cs.DB↗

Controllable Stochastic Quantization Encoding for Adversarially Robust Spiking Neural Networks

Spiking Neural Networks (SNNs) have attracted increasing attention due to their impressive temporal dynamics, energy efficiency, and brain-inspired mechanisms. Although SNNs have demonstrated promising performance in image classification tasks, recent studies have shown that they remain vulnerable to adversarial attacks, where imperceptible perturbations are added to input images to mislead model predictions. Existing defense methods mainly focus on training strategies, while the role of input encoding remains less explored. An observation is that the robustness advantage of Poisson encoding over direct encoding may benefit from its inherent randomness. Motivated by this, we propose a stochastic quantization encoding method that encodes the input image with controllable randomness adjusted by the quantization scale, thereby improving the adversarial robustness of SNNs. We further show that this method constitutes a general framework that reduces to both Poisson encoding and direct encoding under different choices of the quantization scale. Since it enhances robustness at the input encoding stage, it can be combined with existing training-based defenses for further gains. Experimental results on CIFAR-10 and CIFAR-100 demonstrate the effectiveness of the proposed stochastic quantization encoding method. To sum up, this work highlights the importance of input encoding for the adversarial robustness of SNNs, providing a new perspective for understanding and improving it.

cs.NE↗

Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation

Amodal segmentation aims to recover complete object shapes, including occluded regions, serving as an essential technique for user-centric multimedia authoring and object-level visual manipulation. Existing methods typically rely on informative prompts, such as bounding boxes or dense visible masks, which heavily degrade the user experience and interaction efficiency in real-world multimedia applications. While recent interactive paradigms (e.g., the Segment Anything Model) support lightweight point-based interactions, they often perform direct mask regression. Crucially, the opaque nature of these direct-regression models offers no visual explainability regarding how occluded structures are inferred, conflicting with the growing demand for interpretable multimedia systems. To address these limitations, we propose VELA, an end-to-end VElocity-driven Level-set Amodal segmentation method that enables explicit and transparent contour evolution driven by simple point clicks. VELA constructs an initial level set function from visual features and the user's point input, which then progressively evolves into the final amodal mask under the guidance of a shape-specific motion field predicted by a fully differentiable network. This mechanism learns to generate evolution dynamics at each step, ensuring that the spatial reasoning process is geometrically grounded, topologically flexible, and visually explainable to the user. Extensive experiments on COCOA-cls, D2SA, and KINS benchmarks demonstrate that VELA outperforms existing methods that use bounding-box or dense visible-mask prompts while requiring only a single-point prompt, validating the effectiveness of explainable geometric modeling for interactive multimedia tasks.

cs.CV↗

Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, often involving multiple turns of clarification and revision. However, existing benchmarks primarily evaluate execution accuracy, leaving the unfolding and shifting of user intent across turns largely uncovered. To address this, we introduce TIDE-Bench, a benchmark for conversational text-to-SQL under chain ambiguity and intent drift evaluation, targeting two recurring patterns: chain ambiguity, where an underspecified question triggers layered clarification with conditional dependencies, and intent drift, where the user retracts and replaces a previously committed request element. Built on 514 anchor SQLs from BIRD, TIDE-Bench comprises 1,542 samples and introduces dedicated metrics for chain identification and drift recognition-resolution beyond execution accuracy. Evaluating 12 advanced LLMs reveals a persistent chain identification bottleneck unaffected by clarification frequency, a wide drift recognition-resolution gap, and overlap between failure modes when jointly activated. The corresponding code of TIDE-Bench is released for further research.

cs.CL↗

Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL

Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions. Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search.

cs.CL↗

EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration

Container runtimes provide a stable operational interface for deploying, monitoring, and controlling modern workloads, while trusted execution environments (TEEs) provide hardware-enforced isolation for sensitive computation. Existing confidential-container systems often rely on VM-backed deployment stacks or TEE-specific execution substrates, which can separate confidential execution from the conventional OCI runtime lifecycle. This paper presents EBCC (Enclave-Backed Confidential Containers), an OCI-compatible runtime architecture for managing composite confidential-computing workloads. EBCC treats the REE-side anchor and TEE-side confidential stages as a single containerized confidential-computing composite, preserves standard OCI lifecycle operations, and keeps TEE-specific execution behind a backend adapter. It also maintains persistent per-instance state and per-stage artifacts for request handling, response generation, logging, and evidence binding. We implement EBCC on a Keystone backend and evaluate its correctness, performance, footprint, and concurrent execution behavior. The results show that EBCC introduces additional latency over native Keystone execution, mainly due to lifecycle mediation, request validation, EID allocation, backend dispatch, and artifact persistence, while keeping the added footprint concentrated on host-side management state. Cross-TEE case studies on SGX, TDX, and OP-TEE show that the same lifecycle and stage abstraction can be mapped to enclave-style, VM-style, and embedded-style TEEs. These results indicate that EBCC can make TEE-backed execution manageable through an OCI-style lifecycle without materially enlarging the protected-side TCB.

cs.CR↗

How GenAI Mentor Configurations Shape Early Collaborative Dynamics: A Classroom Comparison of Individual and Shared Agents

Generative artificial intelligence (GenAI) is increasingly embedded in computer-supported collaborative learning (CSCL), yet little empirical research has unpacked how different configurations of AI participation reshape collaborative processes. This study investigates how GenAI configuration shapes collaborative regulation in authentic classroom settings. Two eighth-grade classes engaged in small-group creative problem-solving under two conditions: a shared-AI configuration, in which each group interacted with a single AI mentor, and an individual-AI configuration, in which each student accessed a personal AI instance. Using multi-layer discourse coding combined with lag sequential analysis (LSA) and ordered network analysis (ONA), we examined interaction distribution, AI-student coupling, shared regulation processes, and teacher orchestration. Results reveal distinct regulatory dynamics across configurations. Shared AI access promoted convergence-oriented collaboration, with stronger alignment of shared regulatory states and more coordinated group-level reasoning. In contrast, individual AI access distributed support across learners, producing more exploratory and evaluative cycles but also more fragmented interaction patterns, accompanied by increased teacher intervention to manage divergence. These findings suggest that AI configuration functions as a structural design variable that reorganizes the regulatory ecology of classroom collaboration.

cs.HC↗

TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought

Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chinese medicine (TCM) clinical diagnosis and treatment, traditional RAG methods often exhibit poor performance in this domain. Objective: To address the limitations of conventional RAG approaches in TCM applications, this study aims to develop an improved RAG framework tailored to the characteristics of TCM reasoning. Methods: We developed TCM-DiffRAG, an innovative RAG framework that integrates knowledge graphs (KG) with chains of thought (CoT). TCM-DiffRAG was evaluated on three distinctive TCM test datasets. Results: The experimental results demonstrated that TCM-DiffRAG achieved significant performance improvements over native LLMs. For example, the qwen-plus model achieved scores of 0.927, 0.361, and 0.038, which were significantly enhanced to 0.952, 0.788, and 0.356 with TCM-DiffRAG. The improvements were even more pronounced for non-Chinese LLMs. Additionally, TCM-DiffRAG outperformed directly supervised fine-tuned (SFT) LLMs and other benchmark RAG methods. Conclusions: TCM-DiffRAG shows that integrating structured TCM knowledge graphs with Chain of Thought based reasoning substantially improves performance in individualized diagnostic tasks. The joint use of universal and personalized knowledge graphs enables effective alignment between general knowledge and clinical reasoning. These results highlight the potential of reasoning-aware RAG frameworks for advancing LLM applications in traditional Chinese medicine.

cs.CL↗

SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models

No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide valuable insights for revealing model vulnerabilities and guiding robust system design. Some effective attacks have been proposed against NR-IQA models in white-box settings, where the attacker has full access to the target model. However, these attacks often suffer from poor transferability to unknown target models in more realistic black-box scenarios, where the target model is inaccessible. This work makes the first attempt to address the challenge of low transferability in attacking NR-IQA models by proposing a transferable Signed Ensemble Gaussian black-box Attack (SEGA). The main idea is to approximate the gradient of the target model by applying Gaussian smoothing to source models and ensembling their smoothed gradients. To ensure the imperceptibility of adversarial perturbations, SEGA further removes inappropriate perturbations using a specially designed perturbation filter mask. Experimental results on the CLIVE dataset demonstrate the superior transferability of SEGA, validating its effectiveness in enabling successful transfer-based black-box attacks against NR-IQA models.

cs.CV↗

Arca: A Lightweight Confidential Container Architecture for Cloud-Native Environments

Confidential containers protect cloud-native workloads using trusted execution environments (TEEs). However, existing Container-in-TEE designs (e.g., Confidential Containers (CoCo)) encapsulate the entire runtime within the TEE, inflating the trusted computing base (TCB) and introducing redundant components and cross-layer overhead. We present Arca, a lightweight confidential container framework based on a TEE-in-Container architecture that isolates each workload in an independent, hardware-enforced trust domain while keeping orchestration logic outside the TEE. This design minimizes inter-layer dependencies, confines compromise to per-container boundaries, and restores the TEE's minimal trust principle. We implemented Arca on Intel SGX, Intel TDX, and AMD SEV. Experimental results show that Arca achieves near-native performance and outperforms CoCo in most benchmarks, while the reduced TCB significantly improves verifiability and resilience against host-level compromise. Arca emonstrates that efficient container management and strong runtime confidentiality can be achieved without sacrificing security assurance.

cs.CR↗

Multi-agent Self-triage System with Medical Flowcharts

Online health resources and large language models (LLMs) are increasingly used as a first point of contact for medical decision-making, yet their reliability in healthcare remains limited by low accuracy, lack of transparency, and susceptibility to unverified information. We introduce a proof-of-concept conversational self-triage system that guides LLMs with 100 clinically validated flowcharts from the American Medical Association, providing a structured and auditable framework for patient decision support. The system leverages a multi-agent framework consisting of a retrieval agent, a decision agent, and a chat agent to identify the most relevant flowchart, interpret patient responses, and deliver personalized, patient-friendly recommendations, respectively. Performance was evaluated at scale using synthetic datasets of simulated conversations. The system achieved 95.29% top-3 accuracy in flowchart retrieval (N=2,000) and 99.10% accuracy in flowchart navigation across varied conversational styles and conditions (N=37,200). By combining the flexibility of free-text interaction with the rigor of standardized clinical protocols, this approach demonstrates the feasibility of transparent, accurate, and generalizable AI-assisted self-triage, with potential to support informed patient decision-making while improving healthcare resource utilization.

cs.AI↗

BrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block Play

Block-building activities are crucial for developing children's spatial reasoning and mathematical skills, yet parents often lack the expertise to guide these activities effectively. BrickSmart, a pioneering system, addresses this gap by providing spatial language guidance through a structured three-step process: Discovery & Design, Build & Learn, and Explore & Expand. This system uniquely supports parents in 1) generating personalized block-building instructions, 2) guiding parents to teach spatial language during building and interactive play, and 3) tracking children's learning progress, altogether enhancing children's engagement and cognitive development. In a comparative study involving 12 parent-child pairs children aged 6-8 years) for both experimental and control groups, BrickSmart demonstrated improvements in supportiveness, efficiency, and innovation, with a significant increase in children's use of spatial vocabularies during block play, thereby offering an effective framework for fostering spatial language skills in children.

cs.HC↗

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model

Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in a more energy-efficient manner. However, despite previous efforts to optimize the learning algorithm of SNNs through various methods, SNNs still lag behind ANNs in terms of performance. The recently proposed multi-threshold model provides more possibilities for further enhancing the learning capability of SNNs. In this paper, we rigorously analyze the relationship among the multi-threshold model, vanilla spiking model and quantized ANNs from a mathematical perspective, then propose a novel LM-HT model, which is an equidistant multi-threshold model that can dynamically regulate the global input current and membrane potential leakage on the time dimension. The LM-HT model can also be transformed into a vanilla single threshold model through reparameterization, thereby achieving more flexible hardware deployment. In addition, we note that the LM-HT model can seamlessly integrate with ANN-SNN Conversion framework under special initialization. This novel hybrid learning framework can effectively improve the relatively poor performance of converted SNNs under low time latency. Extensive experimental results have demonstrated that our model can outperform previous state-of-the-art works on various types of datasets, which promote SNNs to achieve a brand-new level of performance comparable to quantized ANNs. Code is available at https://github.com/hzc1208/LMHT_SNN.

cs.NE↗

Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving Process

With the increasing integration of large lauguage models (LLMs) in education, there is growing interest in using AI agents to support student learning in creative tasks. This study presents an interactive Mentor Agent system named Mentigo, which is designed to assist middle school students in the creative problem solving (CPS) process. We created a comprehensive dataset of real classroom interactions between students and mentors, which include the structured CPS task management, diverse guidance techniques, personalized feedback mechanisms. Based on this dataset, we create agentic workflow for the Mentigo system. The system's effectiveness was evaluated through a comparative experiment with 12 students and reviewed by five expert teachers. The Mentigo system demonstrated significant improvements in student engagement and creative outcomes. The findings provide design implications for leveraging LLMs to support CPS and offer insights into the application of AI mentor agents in educational contexts.

cs.HC↗

Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds

We present a learning-based approach to reconstruct buildings as 3D polygonal meshes from airborne LiDAR point clouds. What makes 3D building reconstruction from airborne LiDAR hard is the large diversity of building designs and especially roof shapes, the low and varying point density across the scene, and the often incomplete coverage of building facades due to occlusions by vegetation or to the viewing angle of the sensor. To cope with the diversity of shapes and inhomogeneous and incomplete object coverage, we introduce a generative model that directly predicts 3D polygonal meshes from input point clouds. Our autoregressive model, called Point2Building, iteratively builds up the mesh by generating sequences of vertices and faces. This approach enables our model to adapt flexibly to diverse geometries and building structures. Unlike many existing methods that rely heavily on pre-processing steps like exhaustive plane detection, our model learns directly from the point cloud data, thereby reducing error propagation and increasing the fidelity of the reconstruction. We experimentally validate our method on a collection of airborne LiDAR data of Zurich, Berlin and Tallinn. Our method shows good generalization to diverse urban styles.

cs.CV↗