Showing 1–50 of 165 results for author: Qiu, T

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Authors: Xuyang Liu, Yibin Han, Zhenwei Zhang, Kai Chang, Zhiwei Xu, Tian Qiu, Weixian Deng, Jiabao Gao, Xiaolin Peng, Hai Wan, Xibin Zhao

Abstract: Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how errors arise and propagate across intermediate reasoning stages. We present DiagChain, a diagnostic b… ▽ More Large Language Model (LLM) agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how errors arise and propagate across intermediate reasoning stages. We present DiagChain, a diagnostic benchmark for evidence-grounded attack chain reconstruction that enables stage-wise evaluation of LLM agents. DiagChain includes MAIN-69, a suite of 69 scenarios spanning multiple operating systems, evidence noise levels, and chain lengths. It further introduces Evidence-Centric Retrieval-Augmented Generation (ECRAG), which couples evidence retrieval with an evolving structured representation of the reconstructed chain. Five complementary metrics are introduced to assess distinct stages of the reconstruction process and support systematic failure diagnosis. Based on evaluations using 6 LLMs, DiagChain reveals that even the strongest configuration succeeds on only 39.6% of the 849 reference steps in MAIN-69. Our analysis further shows that smaller models struggle with the more basic task of incorporating retrieved evidence into their outputs, whereas larger models can proceed to later steps, where correctly ordering that evidence becomes the main bottleneck. These results validate the importance of diagnostic evaluation beyond end-to-end accuracy and provide actionable insights for improving evidence-grounded cybersecurity agents. △ Less

Submitted 4 August, 2026; originally announced August 2026.

TRUST-ESD: A Risk-Calibrated and Governance-Aware AI Framework for Enterprise Strategic Decision Support Under Uncertainty

Authors: Tian Qiu, Li Yan, Mahabubur Rahman Miraj, Shanqin Yi, Md Intekhab Rahman Galib, Jahid Hasan

Abstract: Enterprise strategic decision support requires AI systems that are not only accurate, but also uncertainty-aware, risk-calibrated, explainable, and governance-compliant. This paper proposes TRUST-ESD, a risk-calibrated and governance-aware framework for enterprise decision support under uncertainty. TRUST-ESD evaluates feasible counterfactual strategies through predictive utility estimation, confo… ▽ More Enterprise strategic decision support requires AI systems that are not only accurate, but also uncertainty-aware, risk-calibrated, explainable, and governance-compliant. This paper proposes TRUST-ESD, a risk-calibrated and governance-aware framework for enterprise decision support under uncertainty. TRUST-ESD evaluates feasible counterfactual strategies through predictive utility estimation, conformal uncertainty calibration, CVaR-based downside-risk scoring, risk-memory retrieval, policy-as-code governance, explainability, and human oversight. Unlike prediction-only methods that select actions by maximum expected utility, TRUST-ESD recommends strategies that balance value, reliability, risk exposure, and compliance. Experimental results show that TRUST-ESD improves risk-adjusted utility by 7.95%, reduces risk exposure by 23.22%, reduces CVaR by 23.78%, lowers calibration error by 13.89%, improves explanation fidelity by 10.90%, and increases governance compliance by 9.76% compared with strong uncertainty-aware baselines, while maintaining competitive predictive accuracy. Ablation and case-study analyses further confirm that uncertainty calibration, downside-risk scoring, risk memory, explainability, and governance validation jointly improve trustworthy enterprise decision-making. △ Less

Submitted 22 July, 2026; originally announced July 2026.

Comments: 15 pages, 7 figures, 4 tables. Submitted to APWeb-WAIM 2026, Danang, Vietnam, September 7-9, 2026

AcadGIS: A Single-Import Python Package for Reproducible, Publication-Ready Academic Maps

Authors: Ripon Chandra Malo, Shatabdi Roy, Tong Qiu

Abstract: Academic and project maps are often produced through a fragmented workflow: researchers locate boundaries, manage shapefiles, join tabular data, assemble locator insets, add cartographic decorations, and export figures through desktop GIS or multi-package Python scripts. This creates an accessibility barrier for non-GIS users and a reproducibility problem when data sources, styling choices, and ma… ▽ More Academic and project maps are often produced through a fragmented workflow: researchers locate boundaries, manage shapefiles, join tabular data, assemble locator insets, add cartographic decorations, and export figures through desktop GIS or multi-package Python scripts. This creates an accessibility barrier for non-GIS users and a reproducibility problem when data sources, styling choices, and manual edits are not captured in executable form. We present AcadGIS, a free and open-source Python package that creates publication-oriented research maps from high-level commands under one namespace, import acadgis as agis. AcadGIS provides place-name boundary access, automated study-area locator layouts, thematic cartography, raster and vector layers, curated Earth-observation products, terrain and hydrology context, and configurable PNG, PDF, and SVG export without requiring desktop GIS expertise or hand-managed shapefiles. Its design combines one-import access to the scientific-Python stack, publication-oriented defaults with progressive control, local caching, source attribution, and figure specifications based on code, named data, and a pinned package version. Through three representative use cases, we demonstrate how common paper, thesis, and project maps can be expressed as compact, inspectable scripts. Source code: https://github.com/riponcm/AcadGIS. △ Less

Submitted 10 July, 2026; originally announced July 2026.

Comments: 19 pages, 8 figures, 2 tables, and 6 code listings. AcadGIS v0.2.0: https://github.com/riponcm/AcadGIS/releases/tag/v0.2.0

RoboVista: Evaluating Vision Language Models for Diverse Robot Applications

Authors: Shuangyu Xie, Kaiyuan Chen, Ziyang Chen, Simeon Adebola, Yixuan Huang, Zehan Ma, Tianshuang Qiu, Wentao Yuan, Dhruv Shah, Pannag R. Sanketi, Ken Goldberg

Abstract: Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision-Language Models (VLMs) offer a promising foundation for general-purpose and interpretable robotic reasoning. Aligning VLMs with diverse robot applications requires a modular understanding of the individual decision compo… ▽ More Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision-Language Models (VLMs) offer a promising foundation for general-purpose and interpretable robotic reasoning. Aligning VLMs with diverse robot applications requires a modular understanding of the individual decision components that underlie robotic behavior. Capturing such structure is challenging for conventional robot benchmarks that are primarily based on teleoperated, end-to-end datasets. We propose Robot Question Answering (RQA), a modular evaluation framework and RoboVista, a benchmark curated from real robotic systems, research papers, and expert annotations. RoboVista contains 474 Visual Question Answering (VQA) instances with human annotated reasoning and covers 39 unique task types in agricultural, industrial, domestic, surgical robotics, autonomous driving, and open robot datasets. Experiments on RoboVista show that state-of-the-art VLMs exhibit substantial gaps. Physical robot experiments suggest strong correlation between RoboVista performance and real-world task execution. △ Less

Submitted 5 July, 2026; originally announced July 2026.

Comments: Accepted to RSS 2026. Project website: https://berkeleyautomation.github.io/robovista/

DLGStream: Dynamic Language-embedded Guassian Splatting for Open-vocabulary Enabled Free-viewpoint Video Streaming

Authors: Zhihui Ke, Yuyang Liu, Xiaobo Zhou, Tie Qiu

Abstract: 3D Gaussian Splatting~(3DGS) has emerged as a promising paradigm for reconstructing streamable free-viewpoint video~(FVV) from multi-view videos. However, 3DGS-based FVVs typically lack user interaction and editing capabilities, which diminishes the immersive experience. Recent research has integrated language features from CLIP into 3DGS via distillation, enabling open-vocabulary queries and supp… ▽ More 3D Gaussian Splatting~(3DGS) has emerged as a promising paradigm for reconstructing streamable free-viewpoint video~(FVV) from multi-view videos. However, 3DGS-based FVVs typically lack user interaction and editing capabilities, which diminishes the immersive experience. Recent research has integrated language features from CLIP into 3DGS via distillation, enabling open-vocabulary queries and supporting many downstream applications. Nevertheless, the stringent requirements of FVV, low frame size and high FPS, make current language Gaussian representations unsuitable for language-embedded FVV. In this paper, we propose DLGStream, a novel language-embedded FVV representation that streams time-varying language features alongside Gaussian attributes to support 4D environment interaction, scene editing, and spatial intelligence. Specifically, we propose a dual-opacity dynamic language Gaussian representation, which maintains two opacity attributes for color and language features to deal with performance degradation that occurs when colors and features are jointly optimized. Furthermore, we introduce an interpolation-based deformation field to reduce temporal redundancy. This deformation field can also be used for 4D frame interpolation, boosting FVV sequences from low to high FPS. Experimental results demonstrate that DLGStream achieves superior performance in both on open-vocabulary segmentation and reconstruction quality with an average frame size of merely 43 KB. The code is available on \href{https://github.com/kkkzh/DLGStream}{https://github.com/kkkzh/DLGStream}. △ Less

Submitted 27 June, 2026; originally announced June 2026.

Comments: ECCV 2026

Semantic Code Clone Detection: Are We There Yet?

Authors: Zhiwei Xu, Weixian Deng, Xuyang Liu, Xiaolin Peng, Jiabao Gao, Tian Qiu, Hai Wan, Xibin Zhao

Abstract: Code clone detection has been extensively studied for decades, and recent approaches have begun reporting remarkably high performance for semantic (Type-4) clones on benchmark datasets. However, it remains unclear whether these results reflect a genuine ability to capture semantic equivalence between programs, or simply an ability to exploit dataset-specific patterns. In this paper, we present t… ▽ More Code clone detection has been extensively studied for decades, and recent approaches have begun reporting remarkably high performance for semantic (Type-4) clones on benchmark datasets. However, it remains unclear whether these results reflect a genuine ability to capture semantic equivalence between programs, or simply an ability to exploit dataset-specific patterns. In this paper, we present the first systematic empirical study investigating the generalizability of state-of-the-art (SOTA) semantic code clone detectors beyond benchmark evaluation settings. Inspired by the inherent inclusion relationship among clone types, we propose a clone operator framework consisting of eight transformation operators derived from Type-2 and Type-3 clone variations. Using these operators, we construct distribution-shifted yet semantically equivalent Type-4 clone instances and evaluate 11 representative detectors spanning token-based, tree-based, and graph-based paradigms on the real-world BigCloneBench dataset. Our results reveal substantial performance degradation across all evaluated approaches, despite their strong benchmark performance. Further analyses show that existing detectors heavily rely on shortcut learning based on lexical and structural cues rather than robust semantic understanding. Our findings suggest that current SOTA semantic code clone detectors exhibit limited generalizability in real-world scenarios, highlighting important avenues for future research. △ Less

Submitted 23 June, 2026; originally announced June 2026.

Comments: 12 pages

Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection

Authors: Tian Qiu, Jifeng Shen, Xin Zuo

Abstract: Effective cross-modal feature alignment and interaction are central challenges in multispectral object detection. Although global cross-attention provides strong long-range modeling ability, its quadratic complexity with respect to feature size limits deployment on resource-constrained platforms. We therefore propose Progressive Pixel-Neighborhood Deformable Cross-Attention for multispectral featu… ▽ More Effective cross-modal feature alignment and interaction are central challenges in multispectral object detection. Although global cross-attention provides strong long-range modeling ability, its quadratic complexity with respect to feature size limits deployment on resource-constrained platforms. We therefore propose Progressive Pixel-Neighborhood Deformable Cross-Attention for multispectral feature fusion, termed PNAFusion. The proposed framework is motivated by two observations: weak misalignment between visible and thermal images is usually concentrated around local neighborhoods, and semantic correspondence across modalities often follows non-linear spatial mappings that fixed receptive fields cannot model well. To address these issues, PNAFusion incorporates local spatial priors into its architectural design to concentrate feature interaction and alignment on the most relevant neighborhoods. Specifically, a Pixel-Neighborhood Cross-Attention (PNCA) module is introduced to avoid redundant global feature matching and suppress background noise. Meanwhile, an Adaptive Deformable Alignment (ADA) module captures non-linear spatial correspondences through learned pixel-wise offsets. These components are further integrated through an iterative feedback mechanism to progressively refine cross-modal feature alignment. Experiments on FLIR, M3FD, and DroneVehicle show that PNAFusion achieves 84.2, 90.5, and 85.5 mAP@0.5, respectively, under the YOLOv5 detector, and further reaches 86.8 mAP@0.5 on FLIR and 90.8 mAP@0.5 on M3FD when transferred to Co-DETR. Efficiency analysis indicates that PNAFusion reduces allocated GPU memory by 33.0\% compared with ICAFusion and reduces theoretical FLOPs from 194.8 G to 156.4 G, although the deformable sampling and iterative refinement introduce additional latency. Our code will be available at https://github.com/DanielQiuTian/PNAFusion. △ Less

Submitted 22 June, 2026; originally announced June 2026.

Comments: Accepted by Sensors

PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

Authors: Ripon Chandra Malo, Tong Qiu

Abstract: AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is… ▽ More AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Comments: 12 pages, 5 figures, 1 table. Code: https://github.com/riponcm/projectmem

Task-Focused Memorization for Multimodal Agents

Authors: Tao Zou, Yichen He, Tian Qiu, Yuan Lin, Hang Li

Abstract: Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memorize. Multimodal agents, such as embodied agents, continuously perceive, reason, a… ▽ More Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memorize. Multimodal agents, such as embodied agents, continuously perceive, reason, and act in real or virtual environments, receiving an unbounded stream of multimodal observations. From this combinatorial explosion of information, an agent must selectively retain content that is relevant to its role in the environment and valuable for future tasks. To bridge this gap, we frame memory generation as a learnable memorization policy and introduce TaskMem (Task-focused Memorization Policy Learning), a reinforcement-learning-based framework that enables the policy to dynamically adjust its focus to the demands of real tasks encountered in the environment. TaskMem adopts a two-phase training paradigm: Phase One learns how to memorize by optimizing memory quality under fundamental fidelity requirements; Phase Two occurs after deployment, where the agent learns what to memorize by tuning an adapter on its base MLLM, using recent environment tasks to define a reward model that guides the memorization policy toward task-relevant content. To evaluate our approach, we reformulate VideoMME, EgoLife, and EgoTempo into streaming benchmarks that simulate a realistic setting in which an agent processes streaming observations and handles tasks arriving online. To isolate memory assessment, the questions must be answered using only the agent's memory, without access to raw video. Built on Qwen3-VL-30B-A3B, TaskMem improves VQA accuracy by 6.3%, 7.0%, and 5.3% on these benchmarks, respectively. △ Less

Submitted 29 May, 2026; originally announced May 2026.

Knowledge Distillation for Low-Resource Open-source Text-to-SQL Model

Authors: Tianhao Qiu, Xiaojun Chen

Abstract: Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained by low-resource settings, where high-quality annotated \texttt{<question, SQL>} pairs are scarce, particularly for domain-specific databases. Additional challen… ▽ More Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained by low-resource settings, where high-quality annotated \texttt{<question, SQL>} pairs are scarce, particularly for domain-specific databases. Additional challenges include opaque schema definitions, abbreviations, and implicit business logic that are not explicitly encoded in the schema. Existing data synthesis and prompting techniques improve coverage but often fail to produce task-specific, semantically grounded examples aligned with database constraints. To address these challenges, we propose a knowledge-aware Text-to-SQL framework that constructs task-specific knowledge base including schema semantics, abbreviations, business logic, and query patterns, and injects them into both training and inference. This framework generates diverse, contextually grounded synthetic training data and enhances inference through targeted knowledge retrieval. Experiments on seven benchmarks, covering both general and domain-specific datasets, demonstrate that our approach substantially improves the performance of open-source and closed-source large language models in Text-to-SQL tasks, especially in low-resource domain-specific settings, enhancing generalization, robustness, and adaptability. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: 17ages, 5 figures

MSC Class: 68T50; 68P15 ACM Class: H.2.3; I.2.7; I.2.6

FingerEye: Learning Dexterous Manipulation with Continuous Vision-Tactile Sensing

Authors: Zhixuan Xu, Yichen Li, Xuanye Wu, Tianyu Qiu, Lin Shao

Abstract: Dexterous robotic manipulation requires perception that remains informative from pre-contact approach to contact initiation and post-contact control. We introduce FingerEye, a sensing and learning framework that strengthens robotic dexterity through continuous vision-tactile feedback throughout interaction. On the sensing side, FingerEye integrates binocular RGB cameras with a compliant contact in… ▽ More Dexterous robotic manipulation requires perception that remains informative from pre-contact approach to contact initiation and post-contact control. We introduce FingerEye, a sensing and learning framework that strengthens robotic dexterity through continuous vision-tactile feedback throughout interaction. On the sensing side, FingerEye integrates binocular RGB cameras with a compliant contact interface to support perception both before and after contact. Before contact, the fingertip cameras provide close-range visual cues and implicit stereo for precise approach and object localization. After contact, marker-tracked deformation of the compliant ring provides a proxy for contact wrench sensing. On the learning side, we build real-and-sim infrastructure for data collection and evaluation, systematically study policy-interface designs for learning with multiple FingerEye sensors, and develop FingerEye Policy, which applies group-structured modality fusion to reduce modality shortcuts and better exploit distributed fingertip feedback. Across seven contact-sensitive task settings, FingerEye improves wrist-only policy by over 30 percentage points in mean success rate in both simulation and the real world. △ Less

Submitted 6 June, 2026; v1 submitted 22 April, 2026; originally announced April 2026.

Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration

Authors: Zhijun Zheng, Tian Qiu, Yuheng Zhao, Siming Chen

Abstract: In visual analytics, applying filters to drill-down and extract higher-value insights is a common and important data analysis method. When the drill-down space becomes excessively large, analysts may lose orientation, leading to decreased efficiency in the drill-down process. To tackle these challenges, we propose the Intelligent Drill-Down Framework, in which a large language model (LLM) facilita… ▽ More In visual analytics, applying filters to drill-down and extract higher-value insights is a common and important data analysis method. When the drill-down space becomes excessively large, analysts may lose orientation, leading to decreased efficiency in the drill-down process. To tackle these challenges, we propose the Intelligent Drill-Down Framework, in which a large language model (LLM) facilitates the generation of visual insights, leverages user interaction data to interpret user intent, and generates appropriate drill-down paths. Our method is designed to assist users in identifying valuable drill-down paths when exploring multidimensional data, thereby reducing the cognitive burden of data interpretation and facilitating the generation of insights. Specifically, we propose a drill-down path recommendation method, in which the LLM is trained to approximate a validated greedy algorithm. Secondly, we analyze the user's intent to construct a drill-down chart. Finally, we design a branch management method. Building upon this framework, we designed a system that includes a hybrid interface providing hierarchical navigation to monitor users and manage parallel branches, a visualization panel for interactive data exploration, and an insight panel to present analytical findings and generate drill-down recommendations. We evaluated the effectiveness of our method through a demonstrative use case and a user study. △ Less

Submitted 18 April, 2026; originally announced April 2026.

Comments: 11 pages, 6 figures. Accepted to IEEE PacificVis 2026

AIDABench: AI Data Analytics Benchmark

Authors: Yibo Yang, Fei Lei, Yixuan Sun, Yantao Zeng, Chengguang Lv, Jiancao Hong, Jiaojiao Tian, Tianyu Qiu, Xin Wang, Yanbing Chen, Yanjie Li, Zheng Pan, Xiaochen Zhou, Guanzhou Chen, Haoran Lv, Yuning Xu, Yue Ou, Haodong Liu, Shiqi He, Anya Jia, Yulei Xin, Huan Wu, Liang Liu, Jiaye Ge, Jianxin Dong , et al. (2 additional authors not shown)

Abstract: As AI-driven document understanding and processing tools become increasingly prevalent in real-world applications, the need for rigorous evaluation standards has grown increasingly urgent. Existing benchmarks and evaluations often focus on isolated capabilities or simplified scenarios, failing to capture the end-to-end task effectiveness required in practical settings. To address this gap, we intr… ▽ More As AI-driven document understanding and processing tools become increasingly prevalent in real-world applications, the need for rigorous evaluation standards has grown increasingly urgent. Existing benchmarks and evaluations often focus on isolated capabilities or simplified scenarios, failing to capture the end-to-end task effectiveness required in practical settings. To address this gap, we introduce AIDABench, a comprehensive benchmark for evaluating AI systems on complex data analytics tasks in an end-to-end manner. AIDABench encompasses 600+ diverse document analysis tasks across three core capability dimensions: question answering, data visualization, and file generation. These tasks are grounded in realistic scenarios involving heterogeneous data types, including spreadsheets, databases, financial reports, and operational records, and reflect analytical demands across diverse industries and job functions. Notably, the tasks in AIDABench are sufficiently challenging that even human experts require 1-2 hours per question when assisted by AI tools, underscoring the benchmark's difficulty and real-world complexity. We evaluate 11 state-of-the-art models on AIDABench, spanning both proprietary (e.g., Claude Sonnet 4.5, Gemini 3 Pro Preview) and open-source (e.g., Qwen3-Max-2026-01-23-Thinking) families. Our results reveal that complex, real-world data analytics tasks remain a significant challenge for current AI systems, with the best-performing model achieving only 59.43% pass-at-1. We provide a detailed analysis of failure modes across each capability dimension and identify key challenges for future research. AIDABench offers a principled reference for enterprise procurement, tool selection, and model optimization, and is publicly available at https://github.com/MichaelYang-lyx/AIDABench. △ Less

Submitted 27 March, 2026; v1 submitted 27 February, 2026; originally announced March 2026.

Comments: 22 pages (including appendix), 9 figures, 4 tables. Code: https://github.com/MichaelYang-lyx/AIDABench. Dataset: https://huggingface.co/datasets/MichaelYang-lyx/AIDA

You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents

Authors: Ching-Yu Kao, Xinfeng Li, Shenyu Dai, Tianze Qiu, Pengcheng Zhou, Eric Hanchen Jiang, Philip Sperl

Abstract: High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound network connectivity with minimal security oversight. We identify and systematically measure a fundamental vulnerability in this trust model, which we term the \emp… ▽ More High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound network connectivity with minimal security oversight. We identify and systematically measure a fundamental vulnerability in this trust model, which we term the \emph{Trusted Executor Dilemma}: agents execute documentation-embedded instructions, including adversarial ones, at high rates because they cannot distinguish malicious directives from legitimate setup guidance. This vulnerability is a structural consequence of the instruction-following design paradigm, not an implementation bug. To structure our measurement, we formalize a three-dimensional taxonomy covering linguistic disguise, structural obfuscation, and semantic abstraction, and construct \textbf{ReadSecBench}, a benchmark of 500 real-world README files enabling reproducible evaluation. Experiments on the commercially deployed computer-use agent show end-to-end exfiltration success rates up to 85\%, consistent across five programming languages and three injection positions. Cross-model evaluation on four LLM families in a simulation environment confirms that semantic compliance with injected instructions is consistent across model families. A 15-participant user study yields a 0\% detection rate across all participants, and evaluation of 12 rule-based and 6 LLM-based defenses shows neither category achieves reliable detection without unacceptable false-positive rates. Together, these results quantify a persistent \emph{Semantic-Safety Gap} between agents' functional compliance and their security awareness, establishing that documentation-embedded instruction injection is a persistent and currently unmitigated threat to high-privilege LLM agent deployments. △ Less

Submitted 12 March, 2026; originally announced March 2026.

Comments: 14 pages

Edge-Assisted Multi-Robot Visual-Inertial SLAM with Efficient Communication

Authors: Xin Liu, Shuhuan Wen, Jing Zhao, Tony Z. Qiu, Hong Zhang

Abstract: The integration of cloud computing and edge computing is an effective way to achieve global consistent and real-time multi-robot Simultaneous Localization and Mapping (SLAM). Cloud computing effectively solves the problem of limited computing, communication and storage capacity of terminal equipment. However, limited bandwidth and extremely long communication links between terminal devices and the… ▽ More The integration of cloud computing and edge computing is an effective way to achieve global consistent and real-time multi-robot Simultaneous Localization and Mapping (SLAM). Cloud computing effectively solves the problem of limited computing, communication and storage capacity of terminal equipment. However, limited bandwidth and extremely long communication links between terminal devices and the cloud result in serious performance degradation of multi-robot SLAM systems. To reduce the computational cost of feature tracking and improve the real-time performance of the robot, a lightweight SLAM method of optical flow tracking based on pyramid IMU prediction is proposed. On this basis, a centralized multi-robot SLAM system based on a robot-edge-cloud layered architecture is proposed to realize real-time collaborative SLAM. It avoids the problems of limited on-board computing resources and low execution efficiency of single robot. In this framework, only the feature points and keyframe descriptors are transmitted and lossless encoding and compression are carried out to realize real-time remote information transmission with limited bandwidth resources. This design reduces the actual bandwidth occupied in the process of data transmission, and does not cause the loss of SLAM accuracy caused by data compression. Through experimental verification on the EuRoC dataset, compared with the current most advanced local feature compression method, our method can achieve lower data volume feature transmission, and compared with the current advanced centralized multi-robot SLAM scheme, it can achieve the same or better positioning accuracy under low computational load. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Comments: 13 pages, 18 figures

ACM Class: I.2.9

Journal ref: IEEE Transactions on Automation Science and Engineering, 22 (2025) 2186-2198

You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases

Authors: Isaia Gisler, Zhonghao He, Tianyi Qiu

Abstract: When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a student model via training on data unrelated to those traits. Prior work demonstrated this in the training domains of number sequences, code, and math Chain-of-Tho… ▽ More When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a student model via training on data unrelated to those traits. Prior work demonstrated this in the training domains of number sequences, code, and math Chain-of-Thought traces including transmission of misaligned behaviors. We investigate whether transmission occurs through natural language paraphrases with fixed semantic content, and whether content explicitly contradicting the teacher's preference can block it. We find that training on paraphrases from a teacher system-prompted to love a particular animal increases a student's preference for that animal by up to 19 percentage points. This occurs when paraphrased content is semantically unrelated to the animal, or even when it explicitly expresses dislike. The transmission succeeds despite aggressive filtering to ensure paraphrase fidelity. This raises concerns for pipelines where models generate their own training data: content-based inspection cannot detect such transmission, and even preference-contradicting content fails to prevent it. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Comments: Accepted for Spotlight presentation at EACL 2026 SRW. 5 pages, 2 figures, plus appendix. Equal supervision by Zhonghao He and Tianyi Qiu

Efficiently Solving Mixed-Hierarchy Games with Quasi-Policy Approximations

Authors: Hamzah Khan, Dong Ho Lee, Jingqi Li, Tianyu Qiu, Christian Ellis, Jesse Milzman, Wesley Suttle, David Fridovich-Keil

Abstract: Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. While game theory provides a principled framework for such interactions, existing solvers struggle to handle mixed information structures that combine simultaneous (Nash) and hierarchical (Stackelberg) decision-making. We study N-robot forest-structured mixed-hi… ▽ More Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. While game theory provides a principled framework for such interactions, existing solvers struggle to handle mixed information structures that combine simultaneous (Nash) and hierarchical (Stackelberg) decision-making. We study N-robot forest-structured mixed-hierarchy games, in which each robot acts as a Stackelberg leader over its subtree while robots in different branches interact via Nash equilibria. We derive the Karush-Kuhn-Tucker (KKT) first-order optimality conditions for this class of games and show that they involve increasingly high-order derivatives of robots' best-response policies as the hierarchy depth grows, rendering a direct solution intractable. To overcome this challenge, we introduce a quasi-policy approximation that removes higher-order policy derivatives and develop an inexact Newton method for efficiently solving the resulting approximated KKT systems. We prove local exponential convergence of the proposed algorithm for games with non-quadratic objectives and nonlinear constraints. The approach is implemented in a highly optimized Julia library (MixedHierarchyGames.jl) and evaluated in hardware and simulated multi-agent experiments, demonstrating real-time convergence for complex mixed-hierarchy information structures. △ Less

Submitted 14 May, 2026; v1 submitted 1 February, 2026; originally announced February 2026.

Ensuring Semantics in Weights of Implicit Neural Representations through the Implicit Function Theorem

Authors: Tianming Qiu, Christos Sonis, Hao Shen

Abstract: Weight Space Learning (WSL), which frames neural network weights as a data modality, is an emerging field with potential for tasks like meta-learning or transfer learning. Particularly, Implicit Neural Representations (INRs) provide a convenient testbed, where each set of weights determines the corresponding individual data sample as a mapping from coordinates to contextual values. So far, a preci… ▽ More Weight Space Learning (WSL), which frames neural network weights as a data modality, is an emerging field with potential for tasks like meta-learning or transfer learning. Particularly, Implicit Neural Representations (INRs) provide a convenient testbed, where each set of weights determines the corresponding individual data sample as a mapping from coordinates to contextual values. So far, a precise theoretical explanation for the mechanism of encoding semantics of data into network weights is still missing. In this work, we deploy the Implicit Function Theorem (IFT) to establish a rigorous mapping between the data space and its latent weight representation space. We analyze a framework that maps instance-specific embeddings to INR weights via a shared hypernetwork, achieving performance competitive with existing baselines on downstream classification tasks across 2D and 3D datasets. These findings offer a theoretical lens for future investigations into network weights. △ Less

Submitted 30 January, 2026; originally announced January 2026.

Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction

Authors: Tianyi Alex Qiu, Micah Carroll, Cameron Allen

Abstract: The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to exploit evaluations built on such imperfect supervision, leading to deceptive results. However, underutilized in LLM research, a wealth of mechanism design researc… ▽ More The evaluation and post-training of large language models (LLMs) rely on supervision, but strong supervision for difficult tasks is often unavailable, especially when evaluating frontier models. In such cases, models are demonstrated to exploit evaluations built on such imperfect supervision, leading to deceptive results. However, underutilized in LLM research, a wealth of mechanism design research focuses on game-theoretic incentive compatibility, i.e., eliciting honest and informative answers with weak supervision. Drawing from this literature, we introduce the peer prediction method for model evaluation and post-training. It rewards honest and informative answers over deceptive and uninformative ones, using a metric based on mutual predictability and without requiring ground truth labels. We demonstrate the method's effectiveness and resistance to deception, with both theoretical guarantees and empirical validation on models with up to 405B parameters. We show that training an 8B model with peer prediction-based reward recovers most of the drop in truthfulness due to prior malicious finetuning, even when the reward is produced by a 0.135B language model with no finetuning. On the evaluation front, in contrast to LLM-as-a-Judge which requires strong and trusted judges, we discover an inverse scaling property in peer prediction, where, surprisingly, resistance to deception is strengthened as the capability gap between the experts and participants widens, enabling reliable evaluation of strong models with weak supervision. In particular, LLM-as-a-Judge become worse than random guess when facing deceptive models 5-20x the judge's size, while peer prediction thrives when such gaps are large, including in cases with over 100x size difference. △ Less

Submitted 28 January, 2026; originally announced January 2026.

Comments: ICLR 2026

Self-Improvement as Coherence Optimization: A Theoretical Account

Authors: Tianyi Qiu, Ahmed Hani Ismail, Zhonghao He, Shi Feng

Abstract: Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finetuning performance. Yet why they work remains theoretically unclear. We show that they are all special cases of coherence optimization: finding a context-to-behavior mapping that's most compressible an… ▽ More Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finetuning performance. Yet why they work remains theoretically unclear. We show that they are all special cases of coherence optimization: finding a context-to-behavior mapping that's most compressible and jointly predictable. We prove that coherence optimization is equivalent to description-length regularization, and that among all such regularization schemes, it is optimal for semi-supervised learning when the regularizer is derived from a pretrained model. Our theory, supported by preliminary experiments, explains why feedback-free self-improvement works and predicts when it should succeed or fail. △ Less

Submitted 19 January, 2026; originally announced January 2026.

Comments: 39 pages

Heterogeneity in Multi-Agent Reinforcement Learning

Authors: Tianyi Hu, Zhiqiang Pu, Yuan Wang, Tenghai Qiu, Min Chen, Xin Yu

Abstract: Heterogeneity is a fundamental property in multi-agent reinforcement learning (MARL), which is closely related not only to the functional differences of agents, but also to policy diversity and environmental interactions. However, the MARL field currently lacks a rigorous definition and deeper understanding of heterogeneity. This paper systematically discusses heterogeneity in MARL from the perspe… ▽ More Heterogeneity is a fundamental property in multi-agent reinforcement learning (MARL), which is closely related not only to the functional differences of agents, but also to policy diversity and environmental interactions. However, the MARL field currently lacks a rigorous definition and deeper understanding of heterogeneity. This paper systematically discusses heterogeneity in MARL from the perspectives of definition, quantification, and utilization. First, based on an agent-level modeling of MARL, we categorize heterogeneity into five types and provide mathematical definitions. Second, we define the concept of heterogeneity distance and propose a practical quantification method. Third, we design a heterogeneity-based multi-agent dynamic parameter sharing algorithm as an example of the application of our methodology. Case studies demonstrate that our method can effectively identify and quantify various types of agent heterogeneity. Experimental results show that the proposed algorithm, compared to other parameter sharing baselines, has better interpretability and stronger adaptability. The proposed methodology will help the MARL community gain a more comprehensive and profound understanding of heterogeneity, and further promote the development of practical algorithms. △ Less

Submitted 28 December, 2025; originally announced December 2025.

Trajectory Densification and Depth from Perspective-based Blur

Authors: Tianchen Qiu, Qirun Zhang, Jiajian He, Zhengyue Zhuge, Jiahui Xu, Yueting Chen

Abstract: In the absence of a mechanical stabilizer, the camera undergoes inevitable rotational dynamics during capturing, which induces perspective-based blur especially under long-exposure scenarios. From an optical standpoint, perspective-based blur is depth-position-dependent: objects residing at distinct spatial locations incur different blur levels even under the same imaging settings. Inspired by thi… ▽ More In the absence of a mechanical stabilizer, the camera undergoes inevitable rotational dynamics during capturing, which induces perspective-based blur especially under long-exposure scenarios. From an optical standpoint, perspective-based blur is depth-position-dependent: objects residing at distinct spatial locations incur different blur levels even under the same imaging settings. Inspired by this, we propose a novel method that estimate metric depth by examining the blur pattern of a video stream and dense trajectory via joint optical design algorithm. Specifically, we employ off-the-shelf vision encoder and point tracker to extract video information. Then, we estimate depth map via windowed embedding and multi-window aggregation, and densify the sparse trajectory from the optical algorithm using a vision-language model. Evaluations on multiple depth datasets demonstrate that our method attains strong performance over large depth range, while maintaining favorable generalization. Relative to the real trajectory in handheld shooting settings, our optical algorithm achieves superior precision and the dense reconstruction maintains strong accuracy. △ Less

Submitted 9 December, 2025; originally announced December 2025.

Are Your Agents Upward Deceivers?

Authors: Dadi Guo, Qingyu Liu, Dongrui Liu, Qihan Ren, Shuai Shao, Tianyi Qiu, Haoran Li, Yi R. Fung, Zhongjie Ba, Juntao Dai, Jiaming Ji, Zhikai Chen, Jialing Tao, Yaodong Yang, Jing Shao, Xia Hu

Abstract: Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment. We observe and define agentic upward deception, a phenomenon in which an agent facing environment… ▽ More Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment. We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting. To assess its prevalence, we construct a benchmark of 200 tasks covering five task types and eight realistic scenarios in a constrained environment, such as broken tools or mismatched information sources. Evaluations of 11 popular LLMs reveal that these agents typically exhibit action-based deceptive behaviors, such as guessing results, performing unsupported simulations, substituting unavailable information sources, and fabricating local files. We further test prompt-based mitigation and find only limited reductions, suggesting that it is difficult to eliminate and highlighting the need for stronger mitigation strategies to ensure the safety of LLM-based agents. △ Less

Submitted 4 December, 2025; originally announced December 2025.

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning

Authors: Zhonghao He, Tianyi Qiu, Hirokazu Shirado, Maarten Sap

Abstract: Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information. However, emerging evidence suggests that iterative reasoning may foster belief entrenchment and confirmation bias, rather than enhancing truth-seeking behavior. In this study, we propose… ▽ More Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information. However, emerging evidence suggests that iterative reasoning may foster belief entrenchment and confirmation bias, rather than enhancing truth-seeking behavior. In this study, we propose a systematic evaluation framework for belief entrenchment in LLM reasoning by leveraging the Martingale property from Bayesian statistics. This property implies that, under rational belief updating, the expected value of future beliefs should remain equal to the current belief, i.e., belief updates are unpredictable from the current belief. We propose the unsupervised, regression-based Martingale Score to measure violations of this property, which signal deviation from the Bayesian ability of updating on new evidence. In open-ended problem domains including event forecasting, value-laden questions, and academic paper review, we find such violations to be widespread across models and setups, where the current belief positively predicts future belief updates, a phenomenon which we term belief entrenchment. We identify the models, reasoning techniques, and domains more prone to belief entrenchment. Finally, we validate the Martingale Score by showing that it predicts ground-truth accuracy on problem domains where ground truth labels are available. This indicates that, while designed as an unsupervised metric that operates even in domains without access to ground truth, the Martingale Score is a useful proxy of the truth-seeking ability of a reasoning process. △ Less

Submitted 2 December, 2025; originally announced December 2025.

Comments: NeurIPS 2025

CircleFlow: Flow-Guided Camera Blur Estimation using a Circle Grid Target

Authors: Jiajian He, Enjie Hu, Shiqi Chen, Tianchen Qiu, Huajun Feng, Zhihai Xu, Yueting Chen

Abstract: The point spread function (PSF) serves as a fundamental descriptor linking the real-world scene to the captured signal, manifesting as camera blur. Accurate PSF estimation is crucial for both optical characterization and computational vision, yet remains challenging due to the inherent ambiguity and the ill-posed nature of intensity-based deconvolution. We introduce CircleFlow, a high-fidelity PSF… ▽ More The point spread function (PSF) serves as a fundamental descriptor linking the real-world scene to the captured signal, manifesting as camera blur. Accurate PSF estimation is crucial for both optical characterization and computational vision, yet remains challenging due to the inherent ambiguity and the ill-posed nature of intensity-based deconvolution. We introduce CircleFlow, a high-fidelity PSF estimation framework that employs flow-guided edge localization for precise blur characterization. CircleFlow begins with a structured capture that encodes locally anisotropic and spatially varying PSFs by imaging a circle grid target, while leveraging the target's binary luminance prior to decouple image and kernel estimation. The latent sharp image is then reconstructed through subpixel alignment of an initialized binary structure guided by optical flow, whereas the PSF is modeled as an energy-constrained implicit neural representation. Both components are jointly optimized within a demosaicing-aware differentiable framework, ensuring physically consistent and robust PSF estimation enabled by accurate edge localization. Extensive experiments on simulated and real-world data demonstrate that CircleFlow achieves state-of-the-art accuracy and reliability, validating its effectiveness for practical PSF calibration. △ Less

Submitted 30 November, 2025; originally announced December 2025.

Efficient Optimization of a Permanent Magnet Array for a Stable 2D Trap

Authors: Ann-Sophia Müller, Moonkwang Jeong, Jiyuan Tian, Meng Zhang, Tian Qiu

Abstract: Untethered magnetic manipulation of biomedical millirobots has a high potential for minimally invasive surgical applications. However, it is still challenging to exert high actuation forces on the small robots over a large distance. Permanent magnets offer stronger magnetic torques and forces than electromagnetic coils, however, feedback control is more difficult. As proven by Earnshaw's theorem,… ▽ More Untethered magnetic manipulation of biomedical millirobots has a high potential for minimally invasive surgical applications. However, it is still challenging to exert high actuation forces on the small robots over a large distance. Permanent magnets offer stronger magnetic torques and forces than electromagnetic coils, however, feedback control is more difficult. As proven by Earnshaw's theorem, it is not possible to achieve a stable magnetic trap in 3D by static permanent magnets. Here, we report a stable 2D magnetic force trap by an array of permanent magnets to control a millirobot. The trap is located in an open space with a tunable distance to the magnet array in the range of 20 - 120mm, which is relevant to human anatomical scales. The design is achieved by a novel GPU-accelerated optimization algorithm that uses mean squared error (MSE) and Adam optimizer to efficiently compute the optimal angles for any number of magnets in the array. The algorithm is verified using numerical simulation and physical experiments with an array of two magnets. A millirobot is successfully trapped and controlled to follow a complex trajectory. The algorithm demonstrates high scalability by optimizing the angles for 100 magnets in under three seconds. Moreover, the optimization workflow can be adapted to optimize a permanent magnet array to achieve the desired force vector fields. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: 6 pages, 6 figures, IEEE International Conference on Robotics and Automation (ICRA)

Journal ref: In 2025 IEEE International Conference on Robotics and Automation (ICRA) (pp. 6666-6671). IEEE

Three-Dimensional Anatomical Data Generation Based on Artificial Neural Networks

Authors: Ann-Sophia Müller, Moonkwang Jeong, Meng Zhang, Jiyuan Tian, Arkadiusz Miernik, Stefanie Speidel, Tian Qiu

Abstract: Surgical planning and training based on machine learning requires a large amount of 3D anatomical models reconstructed from medical imaging, which is currently one of the major bottlenecks. Obtaining these data from real patients and during surgery is very demanding, if even possible, due to legal, ethical, and technical challenges. It is especially difficult for soft tissue organs with poor imagi… ▽ More Surgical planning and training based on machine learning requires a large amount of 3D anatomical models reconstructed from medical imaging, which is currently one of the major bottlenecks. Obtaining these data from real patients and during surgery is very demanding, if even possible, due to legal, ethical, and technical challenges. It is especially difficult for soft tissue organs with poor imaging contrast, such as the prostate. To overcome these challenges, we present a novel workflow for automated 3D anatomical data generation using data obtained from physical organ models. We additionally use a 3D Generative Adversarial Network (GAN) to obtain a manifold of 3D models useful for other downstream machine learning tasks that rely on 3D data. We demonstrate our workflow using an artificial prostate model made of biomimetic hydrogels with imaging contrast in multiple zones. This is used to physically simulate endoscopic surgery. For evaluation and 3D data generation, we place it into a customized ultrasound scanner that records the prostate before and after the procedure. A neural network is trained to segment the recorded ultrasound images, which outperforms conventional, non-learning-based computer vision techniques in terms of intersection over union (IoU). Based on the segmentations, a 3D mesh model is reconstructed, and performance feedback is provided. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: 6 pages, 4 figures, 1 table, IEEE International Conference on Intelligent Robots and Systems (IROS)

CometNet: Contextual Motif-guided Long-term Time Series Forecasting

Authors: Weixu Wang, Xiaobo Zhou, Xin Qiao, Lei Wang, Tie Qiu

Abstract: Long-term Time Series Forecasting is crucial across numerous critical domains, yet its accuracy remains fundamentally constrained by the receptive field bottleneck in existing models. Mainstream Transformer- and Multi-layer Perceptron (MLP)-based methods mainly rely on finite look-back windows, limiting their ability to model long-term dependencies and hurting forecasting performance. Naively exte… ▽ More Long-term Time Series Forecasting is crucial across numerous critical domains, yet its accuracy remains fundamentally constrained by the receptive field bottleneck in existing models. Mainstream Transformer- and Multi-layer Perceptron (MLP)-based methods mainly rely on finite look-back windows, limiting their ability to model long-term dependencies and hurting forecasting performance. Naively extending the look-back window proves ineffective, as it not only introduces prohibitive computational complexity, but also drowns vital long-term dependencies in historical noise. To address these challenges, we propose CometNet, a novel Contextual Motif-guided Long-term Time Series Forecasting framework. CometNet first introduces a Contextual Motif Extraction module that identifies recurrent, dominant contextual motifs from complex historical sequences, providing extensive temporal dependencies far exceeding limited look-back windows; Subsequently, a Motif-guided Forecasting module is proposed, which integrates the extracted dominant motifs into forecasting. By dynamically mapping the look-back window to its relevant motifs, CometNet effectively harnesses their contextual information to strengthen long-term forecasting capability. Extensive experimental results on eight real-world datasets have demonstrated that CometNet significantly outperforms current state-of-the-art (SOTA) methods, particularly on extended forecast horizons. △ Less

Submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026

StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint Video

Authors: Zhihui Ke, Yuyang Liu, Xiaobo Zhou, Tie Qiu

Abstract: Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering. However, the storage requirements of these methods can reach up to $10$MB per frame,… ▽ More Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering. However, the storage requirements of these methods can reach up to $10$MB per frame, making stream FVV in real-time impossible. To address this problem, we propose a novel FVV representation, dubbed StreamSTGS, designed for real-time streaming. StreamSTGS represents a dynamic scene using canonical 3D Gaussians, temporal features, and a deformation field. For high compression efficiency, we encode canonical Gaussian attributes as 2D images and temporal features as a video. This design not only enables real-time streaming, but also inherently supports adaptive bitrate control based on network condition without any extra training. Moreover, we propose a sliding window scheme to aggregate adjacent temporal features to learn local motions, and then introduce a transformer-guided auxiliary training module to learn global motions. On diverse FVV benchmarks, StreamSTGS demonstrates competitive performance on all metrics compared to state-of-the-art methods. Notably, StreamSTGS increases the PSNR by an average of $1$dB while reducing the average frame size to just $170$KB. The code is publicly available on https://github.com/kkkzh/StreamSTGS. △ Less

Submitted 8 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026. Code will be released at https://www.github.com/kkkzh/StreamSTGS

PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization

Authors: Zehui Feng, Tian Qiu, Tong Wu, Junxuan Li, Huayuan Xu, Ting Han

Abstract: Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on supervised fine-tuning or rank-only objectives, resulting in shallow reasoning, poor score calibration, and limited cross-domain generalization. We propose Pre… ▽ More Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on supervised fine-tuning or rank-only objectives, resulting in shallow reasoning, poor score calibration, and limited cross-domain generalization. We propose PreResQ-R1, a Preference-Response Disentangled Reinforcement Learning framework that unifies absolute score regression and relative ranking consistency within a single reasoning-driven optimization scheme. Unlike prior QA methods, PreResQ-R1 introduces a dual-branch reward formulation that separately models intra-sample response coherence and inter-sample preference alignment, optimized via Group Relative Policy Optimization (GRPO). This design encourages fine-grained, stable, and interpretable chain-of-thought reasoning about perceptual quality. To extend beyond static imagery, we further design a global-temporal and local-spatial data flow strategy for Video Quality Assessment. Remarkably, with reinforcement fine-tuning on only 6K images and 28K videos, PreResQ-R1 achieves state-of-the-art results across 10 IQA and 5 VQA benchmarks under both SRCC and PLCC metrics, surpassing by margins of 5.30% and textbf2.15% in IQA task, respectively. Beyond quantitative gains, it produces human-aligned reasoning traces that reveal the perceptual cues underlying quality judgments. Code and model are available. △ Less

Submitted 7 November, 2025; originally announced November 2025.

Comments: 27 pages, 14 figures, under review as a conference paper

Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements

Authors: Xiaolong Li, Zhi-Qin John Xu, Yan Ren, Tianming Qiu, Xiaowen Wang

Abstract: Accurate segmentation of pediatric brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is critical for diagnosis, treatment planning, and monitoring, yet faces unique challenges due to limited data, high anatomical variability, and heterogeneous imaging across institutions. In this work, we present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest publ… ▽ More Accurate segmentation of pediatric brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is critical for diagnosis, treatment planning, and monitoring, yet faces unique challenges due to limited data, high anatomical variability, and heterogeneous imaging across institutions. In this work, we present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest public dataset of pre-treatment pediatric high-grade gliomas. Our contributions include: (1) a widened residual encoder with squeeze-and-excitation (SE) attention; (2) 3D depthwise separable convolutions; (3) a specificity-driven regularization term; and (4) small-scale Gaussian weight initialization. We further refine predictions with two postprocessing steps. Our models achieved first place on the Task-6 validation leaderboard, attaining lesion-wise Dice scores of 0.759 (CC), 0.967 (ED), 0.826 (ET), 0.910 (NET), 0.928 (TC) and 0.928 (WT). △ Less

Submitted 1 November, 2025; originally announced November 2025.

InsightQL: Advancing Human-Assisted Fuzzing with a Unified Code Database and Parameterized Query Interface

Authors: Wentao Gao, Renata Borovica-Gajic, Sang Kil Cha, Tian Qiu, Van-Thuan Pham

Abstract: Fuzzing is a highly effective automated testing method for uncovering software vulnerabilities. Despite advances in fuzzing techniques, such as coverage-guided greybox fuzzing, many fuzzers struggle with coverage plateaus caused by fuzz blockers, limiting their ability to find deeper vulnerabilities. Human expertise can address these challenges, but analyzing fuzzing results to guide this support… ▽ More Fuzzing is a highly effective automated testing method for uncovering software vulnerabilities. Despite advances in fuzzing techniques, such as coverage-guided greybox fuzzing, many fuzzers struggle with coverage plateaus caused by fuzz blockers, limiting their ability to find deeper vulnerabilities. Human expertise can address these challenges, but analyzing fuzzing results to guide this support remains labor-intensive. To tackle this, we introduce InsightQL, the first human-assisting framework for fuzz blocker analysis. Powered by a unified database and an intuitive parameterized query interface, InsightQL aids developers in systematically extracting insights and efficiently unblocking fuzz blockers. Our experiments on 14 popular real-world libraries from the FuzzBench benchmark demonstrate the effectiveness of InsightQL, leading to the unblocking of many fuzz blockers and considerable improvements in code coverage (up to 13.90%). △ Less

Submitted 6 October, 2025; originally announced October 2025.

Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation

Authors: Yuxiao Yi, Qingyao Zhuang, Zhi-Qin John Xu, Xiaowen Wang, Yan Ren, Tianming Qiu

Abstract: Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net c… ▽ More Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net complexity control, transfer learning from BraTS 2021 pre-trained models to enhance Swin UNETR's generalization on pediatric dataset, and frequency domain decomposition for HFF-Net to separate low-frequency tissue contours from high-frequency texture details. Our final ensemble framework combines nnU-Net ($γ=0.7$), fine-tuned Swin UNETR, and HFF-Net, achieving Dice scores of 62.7% (CC), 83.2% (ED), 72.9% (ET), 85.7% (NET), 91.8% (TC), and 92.6% (WT) on the unseen test dataset, respectively. Our proposed method achieves first place (rank 1st) in the BraTS 2025 Pediatric Brain Tumor Segmentation Challenge. △ Less

Submitted 10 October, 2025; v1 submitted 17 September, 2025; originally announced September 2025.

Comments: 11 pages, 3 figures, conference, miccai brats challenge

A Graph-Neural-Network-Entropy model of vital node identification on network attack and propagation

Authors: Huaizhi Liao, Tian Qiu, Guang Chen

Abstract: Vital nodes usually play a key role in complex networks. Uncovering these nodes is an important task in protecting the network, especially when the network suffers intentional attack. Many existing methods have not fully integrated the node feature, interaction and state. In this article, we propose a novel method (GNNE) based on graph neural networks and information entropy. The method employs a… ▽ More Vital nodes usually play a key role in complex networks. Uncovering these nodes is an important task in protecting the network, especially when the network suffers intentional attack. Many existing methods have not fully integrated the node feature, interaction and state. In this article, we propose a novel method (GNNE) based on graph neural networks and information entropy. The method employs a Graph Convolutional Network (GCN) to learn the nodes' features, which are input into a Graph Attention Network (GAT) to obtain the influence factor of nodes, and the node influence factors are used to calculate the nodes' entropy to evaluate the node importance. The GNNE takes advantage of the GCN and GAT, with the GCN well extracting the nodes' features and the GAT aggregating the features of the nodes' neighbors by using the attention mechanism to assign different weights to the neighbors with different importance, and the nodes' entropy quantifies the nodes' state in the network. The proposed method is trained on a synthetic Barabasi-Albert network, and tested on six real datasets. Compared with eight traditional topology-based methods and four graph-machine-learning-based methods, the GNNE shows an advantage for the vital node identification in the perspectives of network attack and propagation. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Towards scalable organ level 3D plant segmentation: Bridging the data algorithm computing gap

Authors: Ruiming Du, Guangxun Zhai, Tian Qiu, Yu Jiang

Abstract: The precise characterization of plant morphology provides valuable insights into plant environment interactions and genetic evolution. A key technology for extracting this information is 3D segmentation, which delineates individual plant organs from complex point clouds. Despite significant progress in general 3D computer vision domains, the adoption of 3D segmentation for plant phenotyping remain… ▽ More The precise characterization of plant morphology provides valuable insights into plant environment interactions and genetic evolution. A key technology for extracting this information is 3D segmentation, which delineates individual plant organs from complex point clouds. Despite significant progress in general 3D computer vision domains, the adoption of 3D segmentation for plant phenotyping remains limited by three major challenges: i) the scarcity of large-scale annotated datasets, ii) technical difficulties in adapting advanced deep neural networks to plant point clouds, and iii) the lack of standardized benchmarks and evaluation protocols tailored to plant science. This review systematically addresses these barriers by: i) providing an overview of existing 3D plant datasets in the context of general 3D segmentation domains, ii) systematically summarizing deep learning-based methods for point cloud semantic and instance segmentation, iii) introducing Plant Segmentation Studio (PSS), an open-source framework for reproducible benchmarking, and iv) conducting extensive quantitative experiments to evaluate representative networks and sim-to-real learning strategies. Our findings highlight the efficacy of sparse convolutional backbones and transformer-based instance segmentation, while also emphasizing the complementary role of modeling-based and augmentation-based synthetic data generation for sim-to-real learning in reducing annotation demands. In general, this study bridges the gap between algorithmic advances and practical deployment, providing immediate tools for researchers and a roadmap for developing data-efficient and generalizable deep learning solutions in 3D plant phenotyping. Data and code are available at https://github.com/perrydoremi/PlantSegStudio. △ Less

Submitted 8 September, 2025; originally announced September 2025.

DATR: Diffusion-based 3D Apple Tree Reconstruction Framework with Sparse-View

Authors: Tian Qiu, Alan Zoubi, Yiyuan Lin, Ruiming Du, Lailiang Cheng, Yu Jiang

Abstract: Digital twin applications offered transformative potential by enabling real-time monitoring and robotic simulation through accurate virtual replicas of physical assets. The key to these systems is 3D reconstruction with high geometrical fidelity. However, existing methods struggled under field conditions, especially with sparse and occluded views. This study developed a two-stage framework (DATR)… ▽ More Digital twin applications offered transformative potential by enabling real-time monitoring and robotic simulation through accurate virtual replicas of physical assets. The key to these systems is 3D reconstruction with high geometrical fidelity. However, existing methods struggled under field conditions, especially with sparse and occluded views. This study developed a two-stage framework (DATR) for the reconstruction of apple trees from sparse views. The first stage leverages onboard sensors and foundation models to semi-automatically generate tree masks from complex field images. Tree masks are used to filter out background information in multi-modal data for the single-image-to-3D reconstruction at the second stage. This stage consists of a diffusion model and a large reconstruction model for respective multi view and implicit neural field generation. The training of the diffusion model and LRM was achieved by using realistic synthetic apple trees generated by a Real2Sim data generator. The framework was evaluated on both field and synthetic datasets. The field dataset includes six apple trees with field-measured ground truth, while the synthetic dataset featured structurally diverse trees. Evaluation results showed that our DATR framework outperformed existing 3D reconstruction methods across both datasets and achieved domain-trait estimation comparable to industrial-grade stationary laser scanners while improving the throughput by $\sim$360 times, demonstrating strong potential for scalable agricultural digital twin systems. △ Less

Submitted 26 August, 2025; originally announced August 2025.

Omni-Scan: Creating Visually-Accurate Digital Twin Object Models Using a Bimanual Robot with Handover and Gaussian Splat Merging

Authors: Tianshuang Qiu, Zehan Ma, Karim El-Refai, Hiya Shah, Chung Min Kim, Justin Kerr, Ken Goldberg

Abstract: 3D Gaussian Splats (3DGSs) are 3D object models derived from multi-view images. Such "digital twins" are useful for simulations, virtual reality, marketing, robot policy fine-tuning, and part inspection. 3D object scanning usually requires multi-camera arrays, precise laser scanners, or robot wrist-mounted cameras, which have restricted workspaces. We propose Omni-Scan, a pipeline for producing hi… ▽ More 3D Gaussian Splats (3DGSs) are 3D object models derived from multi-view images. Such "digital twins" are useful for simulations, virtual reality, marketing, robot policy fine-tuning, and part inspection. 3D object scanning usually requires multi-camera arrays, precise laser scanners, or robot wrist-mounted cameras, which have restricted workspaces. We propose Omni-Scan, a pipeline for producing high-quality 3D Gaussian Splat models using a bi-manual robot that grasps an object with one gripper and rotates the object with respect to a stationary camera. The object is then re-grasped by a second gripper to expose surfaces that were occluded by the first gripper. We present the Omni-Scan robot pipeline using DepthAny-thing, Segment Anything, as well as RAFT optical flow models to identify and isolate objects held by a robot gripper while removing the gripper and the background. We then modify the 3DGS training pipeline to support concatenated datasets with gripper occlusion, producing an omni-directional (360 degree view) model of the object. We apply Omni-Scan to part defect inspection, finding that it can identify visual or geometric defects in 12 different industrial and household objects with an average accuracy of 83%. Interactive videos of Omni-Scan 3DGS models can be found at https://berkeleyautomation.github.io/omni-scan/ △ Less

Submitted 1 August, 2025; originally announced August 2025.

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning

Authors: Benedikt Roth, Stephan Rappensperger, Tianming Qiu, Hamza Imamović, Julian Wörmann, Hao Shen

Abstract: Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling these vectors into a text embedding discards crucial information. Nevertheless, many non-generative downstream tasks, such as clustering, classification, or retriev… ▽ More Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling these vectors into a text embedding discards crucial information. Nevertheless, many non-generative downstream tasks, such as clustering, classification, or retrieval, still depend on accurate and controllable sentence- or document-level embeddings. We explore several adaptation strategies for pre-trained, decoder-only LLMs: (i) various aggregation techniques for token embeddings, (ii) task-specific prompt engineering, and (iii) text-level augmentation via contrastive fine-tuning. Combining these components yields competitive performance on the English clustering track of the Massive Text Embedding Benchmark (MTEB). An analysis of the attention map further shows that fine-tuning shifts focus from prompt tokens to semantically relevant words, indicating more effective compression of meaning into the final hidden state. Our experiments demonstrate that LLMs can be effectively adapted as text embedding models through a combination of prompt engineering and resource-efficient contrastive fine-tuning on synthetically generated positive pairs. △ Less

Submitted 24 September, 2025; v1 submitted 30 July, 2025; originally announced July 2025.

IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning

Authors: Tianheng Qiu, Jingchun Gao, Jingyu Li, Huiyi Leong, Xuan Huang, Xi Wang, Xiaocheng Zhang, Kele Xu, Lan Zhang

Abstract: Intent-oriented controlled video captioning aims to generate targeted descriptions for specific targets in a video based on customized user intent. Current Large Visual Language Models (LVLMs) have gained strong instruction following and visual comprehension capabilities. Although the LVLMs demonstrated proficiency in spatial and temporal understanding respectively, it was not able to perform fine… ▽ More Intent-oriented controlled video captioning aims to generate targeted descriptions for specific targets in a video based on customized user intent. Current Large Visual Language Models (LVLMs) have gained strong instruction following and visual comprehension capabilities. Although the LVLMs demonstrated proficiency in spatial and temporal understanding respectively, it was not able to perform fine-grained spatial control in time sequences in direct response to instructions. This substantial spatio-temporal gap complicates efforts to achieve fine-grained intention-oriented control in video. Towards this end, we propose a novel IntentVCNet that unifies the temporal and spatial understanding knowledge inherent in LVLMs to bridge the spatio-temporal gap from both prompting and model perspectives. Specifically, we first propose a prompt combination strategy designed to enable LLM to model the implicit relationship between prompts that characterize user intent and video sequences. We then propose a parameter efficient box adapter that augments the object semantic information in the global visual context so that the visual token has a priori information about the user intent. The final experiment proves that the combination of the two strategies can further enhance the LVLM's ability to model spatial details in video sequences, and facilitate the LVLMs to accurately generate controlled intent-oriented captions. Our proposed method achieved state-of-the-art results in several open source LVLMs and was the runner-up in the IntentVC challenge. Our code is available on https://github.com/thqiu0419/IntentVCNet. △ Less

Submitted 24 July, 2025; originally announced July 2025.

Modeling the Economic Impacts of AI Openness Regulation

Authors: Tori Qiu, Benjamin Laufer, Jon Kleinberg, Hoda Heidari

Abstract: Regulatory frameworks, such as the EU AI Act, encourage openness of general-purpose AI models by offering legal exemptions for "open-source" models. Despite this legislative attention on openness, the definition of open-source foundation models remains ambiguous. This paper models the strategic interactions among the creator of a general-purpose model (the generalist) and the entity that fine-tune… ▽ More Regulatory frameworks, such as the EU AI Act, encourage openness of general-purpose AI models by offering legal exemptions for "open-source" models. Despite this legislative attention on openness, the definition of open-source foundation models remains ambiguous. This paper models the strategic interactions among the creator of a general-purpose model (the generalist) and the entity that fine-tunes the general-purpose model to a specialized domain or task (the specialist), in response to regulatory requirements on model openness. We present a stylized model of the regulator's choice of an open-source definition to evaluate which AI openness standards will establish appropriate economic incentives for developers. Our results characterize market equilibria -- specifically, upstream model release decisions and downstream fine-tuning efforts -- under various openness regulations and present a range of effective regulatory penalties and open-source thresholds. Overall, we find the model's baseline performance determines when increasing the regulatory penalty vs. the open-source threshold will significantly alter the generalist's release strategy. Our model provides a theoretical foundation for AI governance decisions around openness and enables evaluation and refinement of practical open-source policies. △ Less

Submitted 23 October, 2025; v1 submitted 14 July, 2025; originally announced July 2025.

CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching

Authors: Sidharth Kannan, Tian Qiu, Carolina Cuesta-Lazaro, Haewon Jeong

Abstract: Generative machine learning models have been demonstrated to be able to learn low dimensional representations of data that preserve information required for downstream tasks. In this work, we demonstrate that flow matching based generative models can learn compact, semantically rich latent representations of field level cold dark matter (CDM) simulation data without supervision. Our model, CosmoFl… ▽ More Generative machine learning models have been demonstrated to be able to learn low dimensional representations of data that preserve information required for downstream tasks. In this work, we demonstrate that flow matching based generative models can learn compact, semantically rich latent representations of field level cold dark matter (CDM) simulation data without supervision. Our model, CosmoFlow, learns representations 32x smaller than the raw field data, usable for field level reconstruction, synthetic data generation, and parameter inference. Our model also learns interpretable representations, in which different latent channels correspond to features at different cosmological scales. △ Less

Submitted 15 July, 2025; originally announced July 2025.

GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field

Authors: Zhizhuo Pang, Zhihui Ke, Xiaobo Zhou, Tie Qiu

Abstract: Implicit neural representations for video have been recognized as a novel and promising form of video representation. Existing works pay more attention to improving video reconstruction quality but little attention to the decoding speed. However, the high computation of convolutional network used in existing methods leads to low decoding speed. Moreover, these convolution-based video representatio… ▽ More Implicit neural representations for video have been recognized as a novel and promising form of video representation. Existing works pay more attention to improving video reconstruction quality but little attention to the decoding speed. However, the high computation of convolutional network used in existing methods leads to low decoding speed. Moreover, these convolution-based video representation methods also suffer from long training time, about 14 seconds per frame to achieve 35+ PSNR on Bunny. To solve the above problems, we propose GSVR, a novel 2D Gaussian-based video representation, which achieves 800+ FPS and 35+ PSNR on Bunny, only needing a training time of $2$ seconds per frame. Specifically, we propose a hybrid deformation field to model the dynamics of the video, which combines two motion patterns, namely the tri-plane motion and the polynomial motion, to deal with the coupling of camera motion and object motion in the video. Furthermore, we propose a Dynamic-aware Time Slicing strategy to adaptively divide the video into multiple groups of pictures(GOP) based on the dynamic level of the video in order to handle large camera motion and non-rigid movements. Finally, we propose quantization-aware fine-tuning to avoid performance reduction after quantization and utilize image codecs to compress Gaussians to achieve a compact representation. Experiments on the Bunny and UVG datasets confirm that our method converges much faster than existing methods and also has 10x faster decoding speed compared to other methods. Our method has comparable performance in the video interpolation task to SOTA and attains better video compression performance than NeRV. △ Less

Submitted 7 July, 2025; originally announced July 2025.

GamerAstra: Supporting 2D Non-Twitch Video Games for Blind and Low-Vision Players through a Multi-Agent Framework

Authors: Tianrun Qiu, Changxin Chen, Sizhe Cheng, Xuyang Liu, Xumeng Wang, Zhicong Lu, Yuxin Ma

Abstract: Blind and low-vision (BLV) players face critical challenges in engaging with video games due to the inaccessibility of visual elements, difficulties navigating interfaces, and limitations in performing interaction. Meanwhile, the development of specialized accessibility features typically requires substantial programming effort and is often implemented on a game-by-game basis. To address these cha… ▽ More Blind and low-vision (BLV) players face critical challenges in engaging with video games due to the inaccessibility of visual elements, difficulties navigating interfaces, and limitations in performing interaction. Meanwhile, the development of specialized accessibility features typically requires substantial programming effort and is often implemented on a game-by-game basis. To address these challenges, we introduce GamerAstra, a multi-agent human-AI collaboration framework that leverages a multi-agent design to facilitate access to 2D non-twitch video games for BLV players. It integrates vision-language models and computer vision techniques, enabling interaction with games lacking native accessibility support. The framework also incorporates custom assistance granularities to support varying degrees of visual impairment and enhances interface navigation through multiple input modalities. Technical evaluations and user studies indicate that GamerAstra effectively enhances playability and provides a more immersive gaming experience for BLV players. These findings also underscore potential avenues for advancing intelligent accessibility frameworks in the gaming domain. △ Less

Submitted 26 September, 2025; v1 submitted 28 June, 2025; originally announced June 2025.

Comments: 17 pages, 11 figures, 2 tables

ACM Class: H.5.2

AnyAni: An Interactive System with Generative AI for Animation Effect Creation and Code Understanding in Web Development

Authors: Tianrun Qiu, Yuxin Ma

Abstract: Generative AI assistants have been widely used in front-end programming. However, besides code writing, developers often encounter the need to generate animation effects. As novices in creative design without the assistance of professional designers, developers typically face difficulties in describing, designing, and implementing desired animations. To address this issue, we conducted a formative… ▽ More Generative AI assistants have been widely used in front-end programming. However, besides code writing, developers often encounter the need to generate animation effects. As novices in creative design without the assistance of professional designers, developers typically face difficulties in describing, designing, and implementing desired animations. To address this issue, we conducted a formative study (N=6) to identify the challenges that code developers face when dealing with animation design issues. Then, we introduce AnyAni, a human-AI collaborative system that supports front-end developers in the ideation, manipulation, and implementation of animation effects. The system combines the assistance of generative AI in creative design by adopting a nonlinear workflow for iterative animation development. In addition, developers can understand and learn the code generated for implementing animations through various interactive methods. A user study (N=9) demonstrated the usability of AnyAni in animation effect creation support for developers. △ Less

Submitted 27 June, 2025; originally announced June 2025.

ACM Class: J.6

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test

Authors: Xiaoyuan Zhu, Yaowen Ye, Tianyi Qiu, Hanlin Zhu, Sijun Tan, Ajraf Mannan, Jonathan Michala, Raluca Ada Popa, Willie Neiswanger

Abstract: As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants, which can degrade performance and compromise safety. Detecting such substitutions is difficult, as use… ▽ More As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants, which can degrade performance and compromise safety. Detecting such substitutions is difficult, as users lack access to model weights and, in most cases, even output logits. To tackle this problem, we propose a rank-based uniformity test that can verify the behavioral equality of a black-box LLM to a locally deployed authentic model. Our method is accurate, query-efficient, and avoids detectable query patterns, making it robust to adversarial providers that reroute or mix responses upon the detection of testing attempts. We evaluate the approach across diverse threat scenarios, including quantization, harmful fine-tuning, jailbreak prompts, and full model substitution, showing that it consistently achieves superior statistical power over prior methods under constrained query budgets. △ Less

Submitted 8 April, 2026; v1 submitted 7 June, 2025; originally announced June 2025.

The Lock-in Hypothesis: Stagnation by Algorithm

Authors: Tianyi Alex Qiu, Zhonghao He, Tejasveer Chugh, Max Kleiman-Weiner

Abstract: The training and deployment of large language models (LLMs) create a feedback loop with human users: models learn human beliefs from data, reinforce these beliefs with generated content, reabsorb the reinforced beliefs, and feed them back to users again and again. This dynamic resembles an echo chamber. We hypothesize that this feedback loop entrenches the existing values and beliefs of users, lea… ▽ More The training and deployment of large language models (LLMs) create a feedback loop with human users: models learn human beliefs from data, reinforce these beliefs with generated content, reabsorb the reinforced beliefs, and feed them back to users again and again. This dynamic resembles an echo chamber. We hypothesize that this feedback loop entrenches the existing values and beliefs of users, leading to a loss of diversity and potentially the lock-in of false beliefs. We formalize this hypothesis and test it empirically with agent-based LLM simulations and real-world GPT usage data. Analysis reveals sudden but sustained drops in diversity after the release of new GPT iterations, consistent with the hypothesized human-AI feedback loop. Code and data available at https://thelockinhypothesis.com △ Less

Submitted 6 June, 2025; originally announced June 2025.

Comments: ICML 2025, 46 pages

WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems

Authors: Hao Wu, Junzhou Chen, Ronghui Zhang, Nengchao Lyu, Hongyu Hu, Yanyong Guo, Tony Z. Qiu

Abstract: Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer from significant performance degradation under low-light conditions due to poor image quality. To address this challenge, we proposes WTEFNet, a real-time object detection framework specifically designed for low-light scenarios,… ▽ More Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer from significant performance degradation under low-light conditions due to poor image quality. To address this challenge, we proposes WTEFNet, a real-time object detection framework specifically designed for low-light scenarios, with strong adaptability to mainstream detectors. WTEFNet comprises three core modules: a Low-Light Enhancement (LLE) module, a Wavelet-based Feature Extraction (WFE) module, and an Adaptive Fusion Detection (AFFD) module. The LLE enhances dark regions while suppressing overexposed areas; the WFE applies multi-level discrete wavelet transforms to isolate high- and low-frequency components, enabling effective denoising and structural feature retention; the AFFD fuses semantic and illumination features for robust detection. To support training and evaluation, we introduce GSN, a manually annotated dataset covering both clear and rainy night-time scenes. Extensive experiments on BDD100K, SHIFT, nuScenes, and GSN demonstrate that WTEFNet achieves state-of-the-art accuracy under low-light conditions. Furthermore, deployment on a embedded platform (NVIDIA Jetson AGX Orin) confirms the framework's suitability for real-time ADAS applications. △ Less

Submitted 29 May, 2025; v1 submitted 29 May, 2025; originally announced May 2025.

Comments: This paper is expected to be submitted to IEEE Transactions on Instrumentation and Measurement

Efficient Long CoT Reasoning in Small Language Models

Authors: Zhaoyang Wang, Jinqi Jiang, Tian Qiu, Hui Liu, Xianfeng Tang, Huaxiu Yao

Abstract: Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long CoT. Thus, distillation becomes a practical method to enable SLMs for such reasoning ability. However, the long CoT often contains a lot of redundant contents (e… ▽ More Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long CoT. Thus, distillation becomes a practical method to enable SLMs for such reasoning ability. However, the long CoT often contains a lot of redundant contents (e.g., overthinking steps) which may make SLMs hard to learn considering their relatively poor capacity and generalization. To address this issue, we propose a simple-yet-effective method to prune unnecessary steps in long CoT, and then employ an on-policy method for the SLM itself to curate valid and useful long CoT training data. In this way, SLMs can effectively learn efficient long CoT reasoning and preserve competitive performance at the same time. Experimental results across a series of mathematical reasoning benchmarks demonstrate the effectiveness of the proposed method in distilling long CoT reasoning ability into SLMs which maintains the competitive performance but significantly reduces generating redundant reasoning steps. △ Less

Submitted 18 June, 2025; v1 submitted 23 May, 2025; originally announced May 2025.

CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning

Authors: Jinyuan Feng, Chaopeng Wei, Tenghai Qiu, Tianyi Hu, Zhiqiang Pu

Abstract: In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has been widely adopted as a promising approach to trade-off between model capacity and computation overhead. However, current MoE variants fall short on heterogeneous datasets, ignoring the fact that experts may learn similar… ▽ More In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has been widely adopted as a promising approach to trade-off between model capacity and computation overhead. However, current MoE variants fall short on heterogeneous datasets, ignoring the fact that experts may learn similar knowledge, resulting in the underutilization of MoE's capacity. In this paper, we propose Contrastive Representation for MoE (CoMoE), a novel method to promote modularization and specialization in MoE, where the experts are trained along with a contrastive objective by sampling from activated and inactivated experts in top-k routing. We demonstrate that such a contrastive objective recovers the mutual-information gap between inputs and the two types of experts. Experiments on several benchmarks and in multi-task settings demonstrate that CoMoE can consistently enhance MoE's capacity and promote modularization among the experts. △ Less

Submitted 28 August, 2025; v1 submitted 23 May, 2025; originally announced May 2025.

Comments: Accepted by EMNLP Findings 2025

Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning

Authors: Enyi Jiang, Changming Xu, Nischay Singh, Tian Qiu, Gagandeep Singh

Abstract: While Chain-of-Thought (CoT) prompting has become a cornerstone for complex reasoning in Large Language Models (LLMs), the faithfulness of the generated reasoning remains an open question. We investigate the Decoupling Hypothesis: that correct answers often mask fragile, post-hoc rationalizations that are not causally tied to the model's prediction. To systematically verify this, we introduce MATC… ▽ More While Chain-of-Thought (CoT) prompting has become a cornerstone for complex reasoning in Large Language Models (LLMs), the faithfulness of the generated reasoning remains an open question. We investigate the Decoupling Hypothesis: that correct answers often mask fragile, post-hoc rationalizations that are not causally tied to the model's prediction. To systematically verify this, we introduce MATCHA, a novel Answer-Conditioned Probing framework. Unlike standard evaluations that focus on final output accuracy, MATCHA isolates the reasoning phase by conditioning generation on the model's predicted answer, allowing us to stress-test the stability of the rationale itself. Our experiments reveal a critical vulnerability: under imperceptible input perturbations, LLMs frequently maintain the correct answer while generating inconsistent or nonsensical reasoning - effectively being ``Right for the Wrong Reasons''. Using LLM judges to quantify this robustness gap, we find that multi-step and commonsense tasks are significantly more susceptible to this decoupling than logical tasks. Furthermore, we demonstrate that adversarial examples generated by MATCHA transfer non-trivially to black-box models. Our findings expose the illusion of CoT robustness and underscore the need for future architectures that enforce genuine answer-reasoning consistency rather than mere surface-level accuracy. △ Less

Submitted 4 February, 2026; v1 submitted 22 May, 2025; originally announced May 2025.