Showing 1–50 of 319 results for author: Cheng, R

Automated ACL Footprint Identification Using 3D Deep Learning

Authors: Ruida Cheng, Ali Uneri, Gabriel Gibson, Frances T. Sheehan, Barry Boden

Abstract: One of the most common reasons for anterior cruciate ligament (ACL) reconstruction failure is femoral tunnel malpositioning (ACL footprint center and tunnel orientation). Such failures may lead to the development of meniscal pathology and osteoarthritis. Accurate ACL femoral footprint identification is therefore essential for precise tunnel placement, restoration of the native knee joint mechanics… ▽ More One of the most common reasons for anterior cruciate ligament (ACL) reconstruction failure is femoral tunnel malpositioning (ACL footprint center and tunnel orientation). Such failures may lead to the development of meniscal pathology and osteoarthritis. Accurate ACL femoral footprint identification is therefore essential for precise tunnel placement, restoration of the native knee joint mechanics, post-surgical knee joint health and prevention of graft failure. Recent advances in artificial intelligence (AI) bring new opportunities to improve image-guided orthopedic surgery. However, at present, existing AI research focuses primarily on ACL segmentation and rupture classification based on pre- and post-operative magnetic resonance (MR) images. Identification of the ACL footprint center using deep learning methods has not been thoroughly researched. Thus, the purpose of this study is to explore 3D deep learning models for ACL femoral footprint identification directly from 3D MR images. Two comprehensive 3D deep learning architectures were developed: a 3D graph convolutional neural network-based geometric model applied to 3D femoral meshes; and a 3D landmark-enhanced identification model based on 3D MR images. A total of 4883 right and 3087 left knee image sets were used from a publicly available database. Eighty percent (80%) were applied to model generation, and twenty percent (20%) were preserved for model testing. Both models achieved excellent performance; however, the image-based method outperformed the model-based method (average error of 2.1mm vs 2.8 mm). Thus, 3D deep learning provides a feasible clinical approach for ACL footprint localization and has the potential to improve ACL reconstruction footprint accuracy. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: 10 pages, 5 figures

Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test Generation

Authors: Michele Tufano, James McClure, José Cambronero, Runxiang Cheng, Sherry Y. Shi, Renyao Wei, Dorothy Chen, Franjo Ivančić, Livio Dalloro, Pat Rondon

Abstract: LLM-based agents are increasingly used for coding tasks, where they have outperformed many classical approaches and scaled to repository-level tasks, such as test generation. However, when directly prompted to generate tests, these agents can fail to reason about the code and its underlying contracts, thereby missing edge cases and behavioral boundaries that affect test quality. To address this li… ▽ More LLM-based agents are increasingly used for coding tasks, where they have outperformed many classical approaches and scaled to repository-level tasks, such as test generation. However, when directly prompted to generate tests, these agents can fail to reason about the code and its underlying contracts, thereby missing edge cases and behavioral boundaries that affect test quality. To address this limitation, we propose Spec-Driven Test Generation, where we instruct an agent to first reason about -- and explicitly document -- code pre-conditions, post-conditions, and undefined behaviors. This intermediate semi-formal specification acts as a cognitive scaffold to guide subsequent test generation. Our evaluation on production bugs from Google shows that the spec-driven agent can deliver a 9.8 percentage points ($p = 0.0352$) improvement in bug detection rate and a 2.5 percentage point ($p = 0.0034$) improvement in branch coverage, compared to a traditional test generation agent baseline. Using LLM-as-a-Judge, we further show that test suites generated by the spec-driven agent are superior to the baseline and human-authored tests in 77.8% and 56.7% of the cases, respectively, and demonstrated improvements on following best practices, readability, and edge-case coverage. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Validation of Smartphone-Based Photogrammetric 3D Body Scanning for Automated Anthropometric Measurements Compared with a Commercial Depth-Sensor-Based Body Scanner

Authors: Ruting Cheng, Boyuan Feng, Chuhui Qiu, Joaquin A. Calderon, Qing Pan, Yufan Liu, James K. Hahn

Abstract: 3D body scanning has become an important tool in healthcare applications because of its rapid and non-invasive nature. While smartphone-based photogrammetric reconstruction provide a low-cost and accessible alternative to commercial 3D body scanners, their performance for whole-body scanning remains insufficiently validated. Thus, we designed this study to comprehensively validate the photogrammet… ▽ More 3D body scanning has become an important tool in healthcare applications because of its rapid and non-invasive nature. While smartphone-based photogrammetric reconstruction provide a low-cost and accessible alternative to commercial 3D body scanners, their performance for whole-body scanning remains insufficiently validated. Thus, we designed this study to comprehensively validate the photogrammetric 3D scanning application by evaluating automatically extracted whole-body measurements and longitudinal body-shape monitoring. We evaluated a representative application, PolyCam, against the commercial depth-sensor-based Fit3D ProScanner using 144 pregnant participants scanned longitudinally throughout pregnancy. We designed an automatic circumference extraction pipeline to get measurements at four anatomical landmarks from paired 3D scans. A linear mixed-effects model was used to evaluate scanner effects and longitudinal body-shape changes. Measurement consistency was assessed using repeated PolyCam scans and tape measurements on a rigid mannequin. PolyCam demonstrated strong agreement with Fit3D, with average biases below 16 mm, intraclass correlation coefficients above 0.8, and Pearson correlation coefficients above 0.9 across all landmarks. Both systems captured comparable longitudinal body-shape changes. Mannequin experiments showed mean biases below 3.5 mm and no significant differences from tape measurements. These findings support smartphone photogrammetry as a potential accessible alternative to commercial body scanners and applicable for longitudinal 3D body-shape assessment. △ Less

Submitted 13 August, 2026; originally announced August 2026.

Comments: 16 pages, 5 figures, 4 tables

MSC Class: 68U05 (Primary) 68U10; 65D18 (Secondary) ACM Class: I.4.7

Towards Color-Faithful Low-Light Image Enhancement via Adaptive Color Debiasing and Saturation Rectification

Authors: Zhichen Yang, Rui Xu, Yuzhen Niu, Fusheng Li, Hui Da, Ri Cheng

Abstract: Low-light imaging often introduces color bias caused by the low signal-to-noise ratio and the image formation process. Although recent low-light image enhancement methods have achieved strong brightness recovery, faithful color restoration remains challenging, manifesting as overall color bias together with local under- and over-saturation. To address this issue, we propose CAGE, a cylindrical col… ▽ More Low-light imaging often introduces color bias caused by the low signal-to-noise ratio and the image formation process. Although recent low-light image enhancement methods have achieved strong brightness recovery, faithful color restoration remains challenging, manifesting as overall color bias together with local under- and over-saturation. To address this issue, we propose CAGE, a cylindrical color correction framework with adaptive color debiasing and gamut-harmonized saturation rectification for color-faithful low-light image enhancement. We first introduce AdaLAB, a cylindrical adaptive LAB color space that provides a decoupled and image-specific basis for uniform color correction. Building on this color space, we further develop AdaCCT, an adaptive cylindrical color transform with forward and inverse transforms for the conversion between RGB and AdaLAB color space, as well as necessary color debiasing and saturation rectification. The forward transform suppresses embedded color bias before backbone enhancement by reorganizing the chromatic distribution through chromatic-plane shifting and scaling, while the inverse transform achieves faithful saturation rectification through out-of-gamut lightness compensation. Extensive experiments on multiple benchmarks show that CAGE achieves more faithful color restoration, specifically reduces color bias and saturation abnormality, and delivers better overall visual quality across different low-light enhancement backbones. The code is available at https://yangzhichen763.github.io/CAGE/. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Comments: Accepted by ACMMMM 2026

Persistent Recursive Worlds Enable Autonomous Software Evolution

Authors: Beichen Huang, Zhenyu Liang, Bowen Zheng, Ran Cheng

Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents softwa… ▽ More Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US\$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent. Project Website: https://genesis.evox.group/ △ Less

Submitted 16 August, 2026; v1 submitted 11 August, 2026; originally announced August 2026.

Learning human joint torques from pixels

Authors: Chen Chen, Rui Cheng

Abstract: Estimating human joint torques from visual observations is a key step toward bringing biomechanical analysis from controlled laboratories to real-world movement scenarios. Existing torque estimation methods typically depend on surface electromyography, motion-capture markers, force plates, or simulated imitation data, which limits their applicability to ordinary RGB images. In this work, we introd… ▽ More Estimating human joint torques from visual observations is a key step toward bringing biomechanical analysis from controlled laboratories to real-world movement scenarios. Existing torque estimation methods typically depend on surface electromyography, motion-capture markers, force plates, or simulated imitation data, which limits their applicability to ordinary RGB images. In this work, we introduce VID, a vision-based inverse dynamics dataset and benchmark for predicting human joint torques directly from real monocular images. VID contains 63,369 synchronized frames with real human images, kinematic annotations, anthropometric attributes, and OpenSim-derived dynamic labels, providing paired visual and biomechanical supervision for real-image inverse dynamics. We further define a standardized evaluation protocol covering overall torque estimation, joint-specific analysis, and action-specific prediction. To establish a strong reference model, we propose VID-Network, which combines pose-pretrained spatial probabilistic features, marker regression, and temporal torque inference to recover joint torques from image sequences. Experiments on VID show that VID-Network achieves an overall mPJE of 1.7612 N$\cdot$m/kg, improving over the best compared baseline by 39.81\%, and obtains the lowest error across all evaluated joint types and most action categories. VID establishes a first practical benchmark for vision-driven human inverse dynamics and provides a foundation for studying biomechanical inference in less constrained environments. △ Less

Submitted 9 August, 2026; originally announced August 2026.

AutoPSO: A Metaframework for Automated Particle Swarm Optimization

Authors: Xinmeng Yu, Jiaxin Gao, Jianguo Zhang, Dongmei Jiang, Ran Cheng

Abstract: Particle swarm optimization (PSO) is a widely used metaheuristic, prized for its simplicity and small parameter set. Although decades of research have produced numerous PSO variants that improve performance by modifying key components (e.g., parameter schedules, swarm topologies, or updating rules), two fundamental challenges persist. First, most existing approaches are problem-specific and hand-c… ▽ More Particle swarm optimization (PSO) is a widely used metaheuristic, prized for its simplicity and small parameter set. Although decades of research have produced numerous PSO variants that improve performance by modifying key components (e.g., parameter schedules, swarm topologies, or updating rules), two fundamental challenges persist. First, most existing approaches are problem-specific and hand-crafted, leading to poor cross-task generalization and forcing practitioners to navigate an impractically large design space, which also hinders systematic reuse of prior effective mechanisms. Second, mainstream implementations remain CPU-bound, constraining scalability and substantially increasing computational cost in real-world applications. To address these challenges, we propose {AutoPSO}, a highly automated metaframework for constructing customized PSO algorithms. AutoPSO formulates PSO-based optimization as a bi-level process: an outer search explores the joint space of effective PSO components, while an inner loop instantiates candidate variants to solve the target task and provide feedback. The outer search operates over a curated, open-design component pool, supporting flexible replacement of the component set and the outer optimizer. Crucially, by leveraging EvoX for population tensorization and batched evaluations, AutoPSO can efficiently assess thousands of particles within practical time budgets. Comprehensive experiments on numerical benchmarks and neuroevolution robotic control tasks demonstrate that AutoPSO consistently discovers novel PSO variants that significantly outperform strong baselines. Ablation and scalability studies further highlight the contribution of individual algorithmic components and confirm that AutoPSO achieves increasing performance gains with larger swarm sizes. Code is available at {https://github.com/EMI-Group/autopso}. △ Less

Submitted 10 August, 2026; v1 submitted 28 July, 2026; originally announced August 2026.

Comments: Accepted by IEEE TEVC

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

Authors: Ruoxi Cheng, Haoxuan Ma, Hongyi Zhang, Junming Zhang, Ranjie Duan, Qiaolin Xia, Hao Wang, Yu Lu, Haibo Shi, Xingjun Ma

Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards provide either sparse outcome supervision or richer feedback from process annotations and LLM judges. Outcome rewards scale readily but cannot distinguish grounded retrieval from redundant search, whereas richer signals require costly a… ▽ More Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards provide either sparse outcome supervision or richer feedback from process annotations and LLM judges. Outcome rewards scale readily but cannot distinguish grounded retrieval from redundant search, whereas richer signals require costly annotation or inference during training. Internal rewards based on policy-side signals such as entropy, likelihood, or information gain are graded and inexpensive to evaluate, yet mainly reflect model confidence rather than evidence grounding. We propose Search-G1, a representation-based intrinsic reward framework that measures the operational grounding of an agent's answers through two intervention-calibrated readouts. A prompt-state readout predicts closed-book sufficiency, whose complement defines policy-relative retrieval necessity; an answer-commit readout estimates evidence reliance from answer-stage sensitivity to evidence deletion. Together, they provide additional credit to correct searched trajectories when retrieval is estimated necessary and the answer is evidence-sensitive, favor correct direct answers when closed-book knowledge suffices, and penalize repeated search. After calibration, reward scoring requires neither process annotations nor LLM-as-judge inference during policy optimization. Because reinforcement learning changes policy representations, Search-G1 periodically refits both readouts on trajectories from the latest checkpoint, allowing the reward to co-evolve with the policy. Experiments across multiple search-based question-answering benchmarks and two model scales show that Search-G1 improves the grounding--search-cost trade-off, producing shorter response-side trajectories at competitive task accuracy. Code is available at https://github.com/Rosy0912/Search-G1. △ Less

Submitted 18 August, 2026; v1 submitted 24 July, 2026; originally announced August 2026.

A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation

Authors: Ruida Cheng, Tejas S. Mathai, Benjamin Hou, Qingqing Zhu, Zhiyong Lu, Matthew McAuliffe, Ronald M. Summers

Abstract: In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports. In this study, we developed a unified 2D lesion analysis framework that integrates LLM-based reasoning, lesion bounding box detection, segmentation, and radiology report generation from the original DeepLesion dataset. In… ▽ More In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports. In this study, we developed a unified 2D lesion analysis framework that integrates LLM-based reasoning, lesion bounding box detection, segmentation, and radiology report generation from the original DeepLesion dataset. In the testing phase, we achieved relatively high lesion bounding box detection accuracy with mAP50 of 70.1%, mAP50-95 of 46.4%; Lesion segmentation performance with a Dice score of 62.6%; short report generation accuracy with BLEU_1 score of 64.3%, BLEU_4 score of 49.6%, METEOR of 34.7%, and ROUGE_L of 60.1%. In this work, we address the challenging issue of segmentation in the original DeepLesion dataset and achieve a 28.5% Dice score improvement over the nnUNet lesion segmentation model. We also integrated spatial and anatomical context into the DeepLesion short report generation. We released the implementation, dataset, and models on Github. https://github.com/ruida/2D_DeepLesion_Foundation △ Less

Submitted 3 August, 2026; originally announced August 2026.

Comments: 18 pages, 8 figures

Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms

Authors: Zongyuan Shen, Shalabh Gupta, Shancheng Zhao, Dehua Zhou, Gao Wang, Rui Cheng, Yaming Ou, Zhongqiang Ren, Yikui Zhai, C. L. Philip Chen

Abstract: Motion planning in dynamic environments is a fundamental problem in robotics, aiming to generate safe and efficient paths, trajectories, or control actions in the presence of moving obstacles, uncertain predictions, and multi-agent interactions. It has broad applications in autonomous driving, service robotics, warehouse logistics, human-robot collaboration, crowd navigation, and multi-robot syste… ▽ More Motion planning in dynamic environments is a fundamental problem in robotics, aiming to generate safe and efficient paths, trajectories, or control actions in the presence of moving obstacles, uncertain predictions, and multi-agent interactions. It has broad applications in autonomous driving, service robotics, warehouse logistics, human-robot collaboration, crowd navigation, and multi-robot systems. This survey reviews representative works published primarily between 2015 and 2025, with a particular focus on how recent learning-based advances extend, complement, or interact with classical planning foundations. We first revisit classical planning methods as algorithmic foundations and reference frameworks for learning-based extensions. We then propose a role-of-learning taxonomy that categorizes existing methods according to how learning participates in the planning pipeline, including direct policy learning, learning-augmented classical planning, hybrid planning, and training enhancement methods. For each category, we summarize the main problem settings, representative algorithms, key ideas, integration mechanisms, strengths, and limitations. We further analyze how observation representations, prediction uncertainty, interaction modeling, planner integration, safety constraints, and training strategies shape learning-based motion planning in dynamic environments. Finally, we discuss open challenges and future directions, including sim-to-real gap, safe and certifiable planning, dense crowd navigation, perception-planning coupling, and embodied AI. △ Less

Submitted 1 August, 2026; originally announced August 2026.

RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images

Authors: Renxi Cheng, Jie Gui, Hongsong Wang

Abstract: The rapid advancement of image generation models has made it increasingly difficult for people to distinguish AI-generated images from real ones. To prevent the potential risks associated with the misuse of fake images, AI-generated image detection has gained significant attention. Existing methods neglect the inherent differences between real and fake images, thus lacking robustness and generaliz… ▽ More The rapid advancement of image generation models has made it increasingly difficult for people to distinguish AI-generated images from real ones. To prevent the potential risks associated with the misuse of fake images, AI-generated image detection has gained significant attention. Existing methods neglect the inherent differences between real and fake images, thus lacking robustness and generalization ability. In this work, we innovatively investigate AI-generated image detection using bit-planes, and introduce the bit-reversed image. We propose a simple yet effective pipeline consisting of construction of bit-reversed images, gradient-based patch selection and a convolutional classifier. Besides, we provide a theoretical analysis from the mathematical perspective to demonstrate the validity of our approach. We also introduce two challenging datasets for AI-generated image detection. Extensive experiments verify the effectiveness of our approach across different settings, including cross-generator generalization, cross-dataset generalization and zero-shot performance. Without bells and whistles, our approach outperforms existing methods on over 40 benchmarks, and is nearly 100 times faster than counterparts. The code is at https://github.com/renxi-seu/RAID. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 14 pages, 6 figures

Retrieval-Driven Training-Free AI-Generated Video Attribution

Authors: Renxi Cheng, Chaolei Han, Jie Gui, Hongsong Wang

Abstract: AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses growing threats to cybersecurity and social governance. Attributing AI-generated videos to their specific generative sources is therefore of critical importance for forensic investigation and legal regulation. However, most existing visual attributi… ▽ More AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses growing threats to cybersecurity and social governance. Attributing AI-generated videos to their specific generative sources is therefore of critical importance for forensic investigation and legal regulation. However, most existing visual attribution methods focus on images and particularly rely on the image generation model, thereby lacking the ability to generalize to large-scale AI-generated video data. To address these limitations, we introduce an training-free AI-generated video attribution paradigm. Specifically, we formulates AI-generated video attribution as an instance retrieval task, and design a generative fingerprint-based pipeline. This pipeline consists of an adapted orthogonal color transformation, multi-scale quantized residual generation, and temporal-semantic aggregation, progressively capturing and integrating artifacts introduced by generative models across video frames. Extensive experiments on the GenVidBench benchmark demonstrate that our method achieves strong performance in both AI-generated video detection and attribution, outperforming existing state-of-the-art methods with a Rank-1 accuracy of 20.5% and a mean Average Precision of 16.6%. The code is at https://github.com/renxi-seu/Video_Attribution. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

Authors: Haorui He, Xinwen Chen, Dacheng Wen, Reynold Cheng, Francis C. M. Lau, Yupeng Li

Abstract: Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence. However, most existing static benchmarks risk contamination: they primarily consist of outdated claims verifiable using an LLM's internal knowledge without external evidence. This can inflate performance estimates and fail to reflect true capability on novel claims that require up-to-date… ▽ More Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence. However, most existing static benchmarks risk contamination: they primarily consist of outdated claims verifiable using an LLM's internal knowledge without external evidence. This can inflate performance estimates and fail to reflect true capability on novel claims that require up-to-date information. To address this, emerging dynamic benchmarks collect claims published after LLMs' knowledge cut-off dates, assuming they are uncontaminated. This work revisits this assumption by empirically studying contamination risks in both the state-of-the-art (SOTA) static AVeriTeC benchmark and our newly constructed dynamic ClaimReview2025Q4 benchmark, as well as their impact on MAFC evaluation. Our experiments yield 16 findings, highlighting three key results: (1) Dynamic evaluation reduces but does not eliminate contamination risks, as 17.09\%--29.30\% of post-cut-off claims remain potentially contaminated; (2) Many newly published claims can be verified either directly or by synthesizing multiple pieces of public knowledge available before the cut-off; and (3) Contamination can induce statistically significant inflation in MAFC performance, increasing Macro-F1 by up to 11.34 points and distorting system rankings. In light of these findings, we re-evaluate SOTA LLMs under a strictly contamination-controlled setting. Our study provides practical guidelines for trustworthy MAFC evaluation. △ Less

Submitted 26 July, 2026; originally announced July 2026.

Comments: Accepted at ACM Multimedia (ACM MM), 2026

Continual Video-MLLM Adaptation over Evolving Domains

Authors: Rui Cheng, Meixing Shi, Yuxiang Cai, Jingcai Guo, Jianwei Yin, Zhi Chen

Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learn… ▽ More Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains. DAER maintains domain-isolated lightweight experts while keeping the pretrained Video-MLLM backbone frozen, thereby decoupling domain-specific adaptation from the general multimodal knowledge of the pretrained model. To enable fine-grained specialization, we introduce an intra-domain distribution-aware routing mechanism that matches each input to expert-level prototype reservoirs using MMD. To address the absence of task identities at inference time, we further propose an inter-domain routing mechanism that performs prototype matching in a discriminative subspace for robust domain identification. In addition, we introduce adaptive domain merging to improve parameter scalability and adopt a two-stage optimization strategy to stabilize expert specialization during continual learning. We evaluate DAER by curating a domain-incremental benchmark built from ten VidQA datasets covering diverse visual environments and reasoning demands. Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: Accepted to ACM MM 2026

Uplink SRS-Based Real-Time Indoor Localization System over OpenAirInterface

Authors: Ping-Yu Hsieh, Chieh-Chun Chen, Navid Nikaein, Ray-Guang Cheng

Abstract: Indoor localization is one of the important services for future 5G-Advanced and 6G systems. This paper presents an uplink Sounding Reference Signal (SRS)-based real-time indoor localization system implemented over an OpenAirInterface (OAI) 5G Radio Access Network (RAN). The proposed system uses a Positioning xApp to derive Channel Frequency Response (CFR) measurements from uplink SRS measurements.… ▽ More Indoor localization is one of the important services for future 5G-Advanced and 6G systems. This paper presents an uplink Sounding Reference Signal (SRS)-based real-time indoor localization system implemented over an OpenAirInterface (OAI) 5G Radio Access Network (RAN). The proposed system uses a Positioning xApp to derive Channel Frequency Response (CFR) measurements from uplink SRS measurements. The SRS measurements are obtained from the gNB through the E2 Service Model for Lower Layer Control (E2SM-LLC) over the standardized E2 interface. The xApp transforms the CFR into a 32-dimensional physics-aware feature vector and uses a Random Forest (RF) regressor to estimate the two-dimensional position of the user equipment. We implemented the Positioning xApp on an OAI-based 5G testbed in a multipath-rich indoor laboratory at EURECOM to validate the proposed system. Experimental results show that the proposed system achieves a mean absolute error (MAE) of 0.12 m under random train-test evaluation. These results demonstrate the feasibility and limitations of uplink SRS-based real-time indoor localization over OAI. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: This paper is accepted by ICMIC 2026

Evaluating Power Control Strategies for UORA in IEEE 802.11be Systems with Capture Effect

Authors: Kuan-Chin Li, Ting-Wei Hung, Lain-Chyr Hwang, Pengwenlong Gu, Ray-Guang Cheng

Abstract: Uplink OFDMA-based random access (UORA) is a new channel access mechanism that supports uplink multiuser access in the new generation WiFi systems. Any associated stations (STAs) can use UORA to send their requests or data to the access point (AP) in a contention manner. In this paper, we provide a comprehensive evaluation for simulation study that investigates two power control strategies combine… ▽ More Uplink OFDMA-based random access (UORA) is a new channel access mechanism that supports uplink multiuser access in the new generation WiFi systems. Any associated stations (STAs) can use UORA to send their requests or data to the access point (AP) in a contention manner. In this paper, we provide a comprehensive evaluation for simulation study that investigates two power control strategies combined with capture effect in UORA and observes the fairness issue for spatial distribution of STAs. The results demonstrate that power control strategies can improve the performance of access success probability, delay, resource utilization, and power efficiency of UORA. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: Accepted by ICMIC 2026

Technical Design Review of Duke Robotics Club's Oogway & Crush: AUVs for RoboSub 2026

Authors: Patrick Zheng, Saagar Arya, Hung Le, Mathew Chu, Nathanael Ren, Niko Weaver, Isabella Chen, Jill Wang, Raine Cheng, Siddharth Kini, Avrick Altmann, Srinath Iyer, Ivan Chen, Ian Suh, Parker Jones, Pierson Jones, Sebastian deSouza, Suhaani Sriram, Suvas Aggarwal

Abstract: The Duke Robotics Club presents Oogway and Crush, our AUVs for RoboSub 2026. This year's strategy expands on our previously narrowed scope, targeting all four of RoboSub's design goals for the first time: movement, vision, manipulation, and acoustic tracking. This expansion is based on sustained reliability investment across all three subsystems. Mechanically, Crush gained two additional thrusters… ▽ More The Duke Robotics Club presents Oogway and Crush, our AUVs for RoboSub 2026. This year's strategy expands on our previously narrowed scope, targeting all four of RoboSub's design goals for the first time: movement, vision, manipulation, and acoustic tracking. This expansion is based on sustained reliability investment across all three subsystems. Mechanically, Crush gained two additional thrusters and a CFD-optimized case, providing pitch stability. Electrically, we addressed accumulated failure points by repairing unreliable connections and upgraded thruster control hardware. We also redesigned our acoustics system, adding a new custom PCB with higher-order filters, significantly improving pinger detection reliability. On the software side, improvements to state estimation, sonar-based object detection, vision-driven task planning, and IVC enable more capable and coordinated autonomous runs. Paired with investments in our testing infrastructure to maximize our limited pool time, we can now attempt a broader set of tasks while maintaining the reliability our competition strategy demands. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Toward Semantic Communication for Real-time Mobile 3D Reconstruction

Authors: Fangzhou Zhao, Yao Sun, Xuesong Liu, Runze Cheng, Shang Kai, Yi Sun

Abstract: Real-time mobile 3D reconstruction is fundamental to many emerging applications such as autonomous navigation and digital twin construction, where a moving platform continuously captures an image stream and transmit to a computing server for scene understanding. Unlike offline reconstruction, camera poses and scene geometry are estimated on-the-fly during acquisition, making multi-view consistency… ▽ More Real-time mobile 3D reconstruction is fundamental to many emerging applications such as autonomous navigation and digital twin construction, where a moving platform continuously captures an image stream and transmit to a computing server for scene understanding. Unlike offline reconstruction, camera poses and scene geometry are estimated on-the-fly during acquisition, making multi-view consistency a real-time requirement and rendering geometric estimation highly sensitive to communication-induced distortions. Semantic communication (SemCom) transmits compact semantic information, offering a promising way to preserve task-critical data over unreliable links. However, existing designs are optimized at the image or single-view level and without providing explicit reliability information for geometric estimation, limiting their applicability to real-time mobile 3D reconstruction. In this context, we propose a SemCom framework for real-time mobile 3D reconstruction. The framework includes a semantic transceiver that outputs a reconstructed image alongside a pixel-wise confidence map, quantifying the reliability of each region. We further introduce a confidence-guided geometric estimation method, incorporating confidence into RANSAC-based pose initialization and bundle adjustment to reduce the influence of unreliable regions and enhance robustness under noisy channels. Simulations show that, compared to existing SemCom and traditional seperate source and channel coding, our framework maintains high image quality while significantly improving pose estimation accuracy and 3D structural consistency. △ Less

Submitted 17 July, 2026; originally announced July 2026.

Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

Authors: Jihao Liu, Guoxiong Gao, Zeming Sun, Bin Wu, Shurui Liu, Jiedong Jiang, Haocheng Ju, Leheng Chen, Ronnie Cheng, Xiping Zhang, Bin Dong

Abstract: Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effectively remains challenging, due to the difficulty of coordinating parallel proof search while keeping intermediate claims organized and reliable. In this paper, we propose Danus, a… ▽ More Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effectively remains challenging, due to the difficulty of coordinating parallel proof search while keeping intermediate claims organized and reliable. In this paper, we propose Danus, an orchestration system for research-level mathematical reasoning centered on a shared fact graph as a global memory-management mechanism. Danus consists of a main agent that performs planning and coordination, multiple worker agents that carry out proof search in parallel, and a stateless verifier that checks proposed mathematical claims before they are admitted into the fact graph. Each verified fact is stored together with its proof and logical dependencies, allowing the system to build long arguments incrementally while keeping the shared proof state organized. The main agent periodically summarizes the evolving proof state, redirects workers across promising directions, and supports interaction with human mathematicians through progress reports. We evaluate Danus through six research-level case studies in algebraic geometry, singularity theory, and combinatorics, illustrating how the fact-graph memory mechanism enables Danus to construct long, detailed mathematical proofs. Our results suggest that fact-graph-based orchestration provides an effective route toward scaling mathematical reasoning agents for long-horizon research problems. Danus is open source at https://github.com/frenzymath/Danus. △ Less

Submitted 8 July, 2026; v1 submitted 7 July, 2026; originally announced July 2026.

Tangent classes of matroids and wonderful compactifications

Authors: Ronnie Cheng, Shurui Liu, Guoxiong Gao

Abstract: For every loopless matroid $M$ and every Feichtner--Yuzvinsky building set $\mathcal{G}$ containing the top flat, we construct an integral tangent class $T_{M,\mathcal{G}}^{\mathbb{Z}}\in K_{\mathbb{Z}}(M,\mathcal{G})$; in the realizable case it specializes to the class of the tangent bundle of the corresponding wonderful compactification, it recovers the Hilbert series of the Chow ring through Hi… ▽ More For every loopless matroid $M$ and every Feichtner--Yuzvinsky building set $\mathcal{G}$ containing the top flat, we construct an integral tangent class $T_{M,\mathcal{G}}^{\mathbb{Z}}\in K_{\mathbb{Z}}(M,\mathcal{G})$; in the realizable case it specializes to the class of the tangent bundle of the corresponding wonderful compactification, it recovers the Hilbert series of the Chow ring through Hirzebruch--Riemann--Roch, and it satisfies the expected Chern-alpha lower bounds. This reproduces the tangent class and its key properties studied by the first author in arXiv:2606.22650. The main body of this paper was produced autonomously, without human mathematical guidance, by Danus, an AI mathematical reasoning agent. Danus solved the problem before arXiv:2606.22650 was publicly available, demonstrating the potential of AI agents in mathematical research. We reproduce its output faithfully, adding only editorial comments; the experiment is documented in Appendix B. △ Less

Submitted 8 July, 2026; v1 submitted 7 July, 2026; originally announced July 2026.

Comments: v2: added reference to Danus report [Liu et al., arXiv:2607.06447] and minor edits

MSC Class: 05E14; 68T07; 68V15 ACM Class: I.2.3; I.2.6; G.2.1

Clustered Codebook Quantization for 2D Gaussian-based Image Compression

Authors: Runze Cheng, Yicheng Zhan, Josef Spjut, Kaan Akşit

Abstract: Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (… ▽ More Gaussian-based image representations effectively model image content using compact parametric primitives while preserving high visual fidelity, yet storing a large number of floating-point parameters per primitive degrades rate-distortion efficiency at higher fidelity targets. To improve the rate-distortion performance in Gaussian representation, we present our Cluster-Guided Vector Quantization (CGVQ), a Gaussian primitive based image compression method. Our key idea is to partition Gaussian parameters further into homogeneous groups prior to quantization, enabling higher compression efficiency and accurate parameter reconstruction. In practice, our extensive experiments show that CGVQ decreases the bpp by 20% with respect to our baseline, while maintaining on-par visual quality △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: 3 pages. Accepted to ACM SIGGRAPH 2026 Poster Track. Code available at https://github.com/complight/Cluster_Guided_Vector_Quantization

MSC Class: 94A08 (Primary); 68T07 (Secondary)

Learning Transferable Dynamics Priors from Action to World Modeling

Authors: Ze Huang, Jiahui Zhang, Hairuo Liu, Chenxi Zhang, Ran Cheng, Li Zhang

Abstract: We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual scene evolution, the resulting world model captures reusable interaction dynamics beyond appearance-level video generation. Concretely, we pretrain a multi-view interactive base diffusion world model, A2World, on large-sca… ▽ More We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict how actions drive visual scene evolution, the resulting world model captures reusable interaction dynamics beyond appearance-level video generation. Concretely, we pretrain a multi-view interactive base diffusion world model, A2World, on large-scale robot manipulation data with real action annotations. We validate the learned dynamics priors from two complementary perspectives. First, we adapt A2World into a task- or scene-specialized real-world simulator, A2World-sim, whose long-horizon rollouts support simulator-based policy evaluation and scalable what-if analysis by replacing real-robot rollouts with world model rollouts. Second, starting from the same pretrained weights, we adapt A2World into a video-action joint prediction model, A2World-policy, that predicts actions under visual and instruction conditioning. Experiments across simulation benchmarks and real-robot settings demonstrate that action-conditioned world model pretraining yields transferable dynamics priors that benefit both simulator-centric and policy-centric robot learning. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Comments: ECCV 2026 Accepted

DMuon: Efficient Distributed Muon Training with Near-Adam Overhead

Authors: Vincent Chen, Starrick Liu, Regis Cheng, Dance Yang, Shalfun Li, Ryan Yu, Lucy Liang, Hang Su, Roy Gan, Hao Wang, Qian Wang

Abstract: Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learning workloads. The matrix-aware updates offer a compelling alternative to conventional element-wise optimization, particularly as model architectures continue to grow in scale and heterogeneity. Yet contemporary distributed training infrastructure bu… ▽ More Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learning workloads. The matrix-aware updates offer a compelling alternative to conventional element-wise optimization, particularly as model architectures continue to grow in scale and heterogeneity. Yet contemporary distributed training infrastructure built around the assumption of element-wise optimizers is poorly matched to matrix-level optimizers such as Muon, whose updates couple entire weight matrices and require costly Newton-Schulz iterations. Vanilla Muon implementations incur more than 2x the cost of forward and backward passes. To close this gap, we present DMuon, an open-source distributed Muon implementation that integrates into existing training pipelines as a drop-in module, with no framework-level modifications. Across both embodied foundation model and large language model (LLM) training workloads, DMuon achieves a 1.48x-3.01x speedup in end-to-end step time and a 6.85x-163.00x speedup in optimizer-step time, bringing per-step latency to near-AdamW levels and enabling efficient scaling in our model training. △ Less

Submitted 25 June, 2026; originally announced June 2026.

LLM-assisted gNB Parameter Configuration for Radio Access Network

Authors: Yao-Cong Dong, Maria Amparo Canaveras Galdon, Ari Uskudar, Kuntal Chowdhury, Edwin K. P. Chong, Ray-Guang Cheng

Abstract: gNB parameter misconfigurations are a common cause of system failures in radio access networks (RANs), and their diagnosis and correction rely on manual analysis of complex network logs that does not scale well. This paper proposes a large language model (LLM)-assisted framework for automatic gNB parameter configuration. The framework adopts a synthetic data generation pipeline following a configu… ▽ More gNB parameter misconfigurations are a common cause of system failures in radio access networks (RANs), and their diagnosis and correction rely on manual analysis of complex network logs that does not scale well. This paper proposes a large language model (LLM)-assisted framework for automatic gNB parameter configuration. The framework adopts a synthetic data generation pipeline following a configuration, log, correction workflow. Starting from a workable configuration and the gNB technical references, the pipeline uses a commercial LLM to generate modified configurations and derive structured reasoning traces from gNB error logs. The synthetic training data maps network states to corrective actions and is used to fine-tune an LLM for configuration correction. During inference, the fine-tuned LLM generates valid and deployable gNB parameter configurations from gNB error logs. The framework is validated on an OpenAirInterface (OAI) gNB testbed with 480 unseen misconfiguration scenarios, where fine-tuning improves correction accuracy from 13.8% (zero-shot baseline) to 85.4%, and retrieval-augmented generation (RAG) further improves accuracy to 92.7%. The results demonstrate that the framework may enable automated recovery from misconfigurations without manual intervention and supports scalable and autonomous RAN operation. △ Less

Submitted 1 May, 2026; originally announced June 2026.

Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection

Authors: Renxi Cheng, Jie Gui, Hongsong Wang

Abstract: With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor. The majority of existing research endeavors concentrate on the development of detectors for identifying samples generated by generative adversarial networks. Nevertheless, the detection of AI-generated videos, particularly those produced by text-to-… ▽ More With the rapid advancement of video generation models, distinguishing between AI-generated and authentic videos has emerged as a challenging endeavor. The majority of existing research endeavors concentrate on the development of detectors for identifying samples generated by generative adversarial networks. Nevertheless, the detection of AI-generated videos, particularly those produced by text-to-video models, still remains an uncharted territory. Although state-of-the-art text-to-video models can generate realistic visual content similar to real videos, they fall short of generating the details of the images and the changes in details within the videos. Inspired by this, we address AI-generated video detection from a novel perspective of bit-planes, which can effectively describe the details or noises in images or videos. To this end, we propose a simple yet effective approach called Noise Amplification. This approach first extracts noise signals based on bit-planes, then amplifies these noise signals, and finally feeds them into the discriminator networks for video fake classification. Noise amplification is comprehensively constructed by incorporating three aspects: pixel-level intensity enhancement, region-level spatial amplification, and frame-level temporal aggregation. To evaluate methods of AI-generated video detection in challenging scenarios, we also introduce a benchmark named HardGVD. Extensive experiments on both the large-scale dataset GenVidBench and HardGVD show that our simple approach significantly outperforms state-of-the-art methods. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: 13 pages, 5 figures

WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning

Authors: Renmin Cheng, Changhao Chen

Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of \textit{what-w… ▽ More Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hierarchical approaches. Despite their promise, low-level controllers often become performance bottlenecks due to repeated execution failures. We argue that a key limitation is not only the lack of episodic memory, but also the decoupling of \textit{what-where-when} memory from \textit{which-why} reasoning. To address this, we propose \textbf{WISE} (Which-Why Informed Semantic Explorer), a long-horizon agent framework with an enhanced low-level controller equipped with a Causal Event Graph that augments episodic memory with explicit causal structure linking observations to task relevance. Unlike prior work such as MrSteve, which relies on feature similarity for retrieval, WISE enables robust recall under viewpoint changes and supports opportunistic task reordering through causal reasoning. Building on this memory, we propose an Opportunistic Task Scheduler that dynamically re-prioritizes subtasks when causally relevant opportunities are detected. We further equip WISE with a multi-scale progressive exploration strategy to provide spatially comprehensive observations for downstream reasoning. Experiments show that WISE largely improves task success and efficiency on long-horizon sparse tasks, particularly in settings requiring adaptive decision-making. △ Less

Submitted 10 June, 2026; originally announced June 2026.

TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders

Authors: Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer Özsu, Tianshu Yu

Abstract: Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-… ▽ More Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code and data: https://github.com/LOGO-CUHKSZ/TRL-Bench △ Less

Submitted 8 June, 2026; originally announced June 2026.

Closed-Form Spectral Regularization for Multi-Task Model Merging

Authors: Yongxian Wei, Runxi Cheng, Xingxuan Zhang, Li Shen, Chun Yuan, Peng Cui, Dacheng Tao

Abstract: Model merging combines several independently fine-tuned experts into a single multi-task model without any training data, reducing the storage, serving, and decentralized-development costs of large foundation models. State-of-the-art merging methods formulate merging as a layer-wise quadratic interference minimization problem. Although this problem admits an exact closed-form pseudoinverse solutio… ▽ More Model merging combines several independently fine-tuned experts into a single multi-task model without any training data, reducing the storage, serving, and decentralized-development costs of large foundation models. State-of-the-art merging methods formulate merging as a layer-wise quadratic interference minimization problem. Although this problem admits an exact closed-form pseudoinverse solution, that solution underperforms hundreds of iterations of gradient descent in practice. The iterative loop dominates the cost of the pipeline, yet its effectiveness has remained unexplained. We revisit this regime and show that the iterative solver does not primarily act as an optimizer; rather, it serves as an implicit spectral regularizer for an ill-posed normal equation, where small-eigenvalue directions of the per-layer interference operator amplify proxy noise. Building on this finding, we formalize multi-task model merging as a noisy linear inverse problem and propose a spectral filtering estimator parameterized by a per-direction filter. We instantiate this estimator with SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent, with a hard top-K truncation that suppresses noise-amplifying small-eigenvalue directions. Furthermore, we propose SWUDI-A, an adaptive variant that replaces the global rank hyperparameter with per-layer rank rules, further improving robustness across architectures. Both variants share a single symmetric eigendecomposition per linear layer and require no training data or optimizer state. Across four general benchmarks and a multimodal merging benchmark spanning VQA, Geometry, Chart, OCR, Grounding, and modality merging, our proposed spectral solvers match or outperform state-of-the-art merging methods. Crucially, they reduce wall-clock time by 28-72x and peak GPU memory by up to 50%. △ Less

Submitted 5 June, 2026; originally announced June 2026.

WALL-WM: Carving World Action Modeling at the Event Joints

Authors: Shalfun Li, Victor Yao, Charles Yang, Truth Qu, Regis Cheng, Ryan Yu, Howard Lu, Newton Von, Vincent Chen, Yohann Tang, Maeve Zhang, Ellie Ma, Gody Li, Sage Yang, Lorien Shu, J. W. Gao, Ethan Chen, Colin Ye, Yu Sun, Elise Mon, PS Zhang, Neo Li, Lily Li, James Wang, Ping Yang , et al. (6 additional authors not shown)

Abstract: WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and… ▽ More WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction. Although convenient, this chunk-centric formulation creates a fundamental granularity mismatch. Language describes semantic goals and events, vision evolves through continuous scene dynamics, and actions operate at control-level timescales; forcing all three into the same fixed-length prediction window turns VLA training into short-horizon correlation fitting. WALL-WM addresses this mismatch by organizing both supervision and data around semantic events. Specifically, it pairs event-grounded VLA pretraining with a data ecosystem built from event-level captions and cluster-balanced sampling, enabling scalable learning over diverse behaviors, scenes, and task structures. From the same event-pretrained backbone, WALL-WM supports two complementary inference modes. The event mode consumes next-event descriptions and enables variable-length execution chunks, while the unified mode uses a VLM with Staircase Decoding to condition conventional fixed-length chunk inference while preserving a gradient-continuous VLA path. Together with Muon-optimizer-based large-scale pretraining infrastructure, WALL-WM provides a practical scale-up recipe for general-purpose WAMs. Experiments show that WALL-WM generalizes broadly across language, scenes, and tasks, achieving state-of-the-art performance in large-scale real-world generalization evaluation. △ Less

Submitted 1 June, 2026; originally announced June 2026.

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning

Authors: Jian Yao, Xiongcai Luo, Ran Cheng, Kay Chen Tan

Abstract: Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL). However, generated reasoning chains frequently suffer from structural redundancy (i.e., \emph{overthinking}), incurring high computational overhead without improving answer correctness. Existing mitigation strategies typically rely on token-uniform length penal… ▽ More Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL). However, generated reasoning chains frequently suffer from structural redundancy (i.e., \emph{overthinking}), incurring high computational overhead without improving answer correctness. Existing mitigation strategies typically rely on token-uniform length penalties, which provide coarse, segment-agnostic pressure toward shorter outputs and can inadvertently suppress useful reasoning alongside redundancy. To address this, we demonstrate that inefficiency concentrates in high-probability segments with low marginal utility. We derive a theoretical characterization of segment suboptimality under the correctness-length trade-off objective and propose \textsc{SLAT} (Segment-Level Adaptive Trimming), an RL framework that selectively suppresses redundant segments based on this criterion. Empirical results on standard benchmarks indicate that \textsc{SLAT} establishes a superior accuracy-efficiency Pareto frontier, reducing reasoning length by $50\%$ relative to uncompressed baselines while maintaining competitive accuracy. Overall, our results suggest that theoretically grounded, segment-aware trimming is a promising direction for efficient CoT reasoning in large language models. △ Less

Submitted 29 May, 2026; originally announced May 2026.

EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization

Authors: Tao Jiang, Xinmeng Yu, Chenhao Yi, Yiling Wu, Yan Li, Ran Cheng, Dongmei Jiang, Jianguo Zhang

Abstract: Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space. We propose Evolutionary Generative Merging (EvoGM), a framework that transcends manual heuristics… ▽ More Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space. We propose Evolutionary Generative Merging (EvoGM), a framework that transcends manual heuristics by employing learnable generative modeling to optimize merging coefficients. Specifically, EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates. By constructing winner-loser pairs from historical search trajectories, our framework effectively captures high-performance parameter distributions and maximizes data efficiency. This generative process is seamlessly integrated into a multi-round evolutionary pipeline, where elite merged models iteratively serve as new expert foundations. Extensive experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines, exhibiting robust performance on both seen and unseen tasks. Code and data are available at https://github.com/JiangTao97/evogm. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Comments: Accepted by ICML 2026

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation

Authors: Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai, Yiyan Huang, Ranjie Duan, Tianle Zhang, Xu Yang, Ziyi Ye, Xingjun Ma

Abstract: Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external interventions, such as instruction tuning and retrieval, or use internal mechanisms that remain limited by flawed attention weights and entangled hidden represe… ▽ More Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external interventions, such as instruction tuning and retrieval, or use internal mechanisms that remain limited by flawed attention weights and entangled hidden representations. We propose Adversarial Orthogonal Disentanglement (AOD), a latent geometric framework for mitigating LVLM hallucinations. AOD learns a hallucination-related direction through a minimax objective: a classifier concentrates hallucination signals into the projected component, while an adversary removes them from the orthogonal residual space via a Gradient Reversal Layer. The learned direction enables a training-free dual-forward-pass contrastive decoding strategy that suppresses hallucinations while preserving general capabilities. Experiments on three LVLMs across four hallucination and four utility benchmarks show that AOD consistently outperforms strong baselines. It improves POPE accuracy by over 6\% on average, boosts AMBER by 6\%, and maintains strong performance on utility tasks such as MMMU. Further analysis shows robust transfer across datasets, suggesting that AOD captures general hallucination-related biases rather than dataset-specific artifacts. Our source code and datasets are available at https://github.com/Hunter-Wrynn/AOD. △ Less

Submitted 24 May, 2026; originally announced May 2026.

Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory

Authors: Runxi Cheng, Yuchen Guan, Yongxian Wei, Qianpu Sun, Qixiu Li, Sinan Du, Feng Xiong, Chun Yuan, Yan Lu, Yeyun Gong

Abstract: Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-training, making memory scaling expensive and sometimes ineffective. We propose Memory Grafting, a conditional memory scaling method that utilizes frozen hidden states from a grafting model as conditional n-gram memory. Given f… ▽ More Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-training, making memory scaling expensive and sometimes ineffective. We propose Memory Grafting, a conditional memory scaling method that utilizes frozen hidden states from a grafting model as conditional n-gram memory. Given frequent local n-grams, we run the grafting model offline, store final-token hidden representations as memory values, and let the recipient model retrieve them through exact longest-match suffix lookup. Retrieved memories are adapted by lightweight projections and gates, while a hash-based Engram fallback preserves coverage for unmatched contexts. Since the grafting model is only run offline and exact lookup has expected O(1) complexity with respect to memory-bank size, Memory Grafting expands external latent capacity with limited training and inference overhead. Experiments under matched recipient architectures and pre-training budgets show that Memory Grafting improves over both MoE and vanilla Engram baselines. In the 2.8B-scale setting, it improves the average benchmark score from 51.95 for MoE and 52.43 for vanilla Engram to 53.86. In the 0.92B-scale setting, all grafting-model variants improve over the baselines, with Qwen3.5-35B-A3B giving the strongest gains. These results suggest that pretrained models can serve as reusable constructors of external latent memory, providing a practical step toward scaling future language models beyond trainable parameters alone. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Comments: 25 pages, 12 figures, 5 tables

Complete Local Reasoning About Parameterized Programs Over Topologies (Extended Version)

Authors: Ruotong Cheng, Azadeh Farzan

Abstract: This paper investigates the algorithmic safety verification problem of infinite-state parameterized concurrent programs over a rich set of communication topologies. The goal is to automatically produce a proof of correctness in the form of a universally quantified inductive invariant, where the quantification is over the nodes in the topology. We illustrate that under reasonable assumptions on the… ▽ More This paper investigates the algorithmic safety verification problem of infinite-state parameterized concurrent programs over a rich set of communication topologies. The goal is to automatically produce a proof of correctness in the form of a universally quantified inductive invariant, where the quantification is over the nodes in the topology. We illustrate that under reasonable assumptions on the underlying topology, the problem can be reduced to and solved as a compositional scheme, that is, the verification of the parameterized family is reduced to a set of local proofs, in a complete manner. We propose a verification algorithm, which is implemented as a tool, and demonstrate through a set of benchmarks over several different topologies that our approach is effective in proving parameterized programs safe. △ Less

Submitted 21 July, 2026; v1 submitted 14 May, 2026; originally announced May 2026.

Comments: Extended version of the paper "Complete Local Reasoning About Parameterized Programs Over Topologies" accepted to CAV 2026

Efficient Prompt Learning for Traffic Forecasting

Authors: Qianru Zhang, Xinyi Gao, Alexander Zhou, Reynold Cheng, Siu-Ming Yiu, Hongzhi Yin

Abstract: Accurate traffic prediction is essential for optimizing transportation systems, enhancing resource allocation, and improving overall urban administration. Spatio-temporal graph neural networks (GNNs) have achieved state-of-the-art performance and have been widely used in various spatio-temporal prediction scenarios. However, these prediction methods often exhibit low generalization ability, strugg… ▽ More Accurate traffic prediction is essential for optimizing transportation systems, enhancing resource allocation, and improving overall urban administration. Spatio-temporal graph neural networks (GNNs) have achieved state-of-the-art performance and have been widely used in various spatio-temporal prediction scenarios. However, these prediction methods often exhibit low generalization ability, struggling with distribution shifts caused by spatio-temporal dynamics. To address this challenge, we propose an approach to enhance the generalization and adaptation of spatio-temporal GNNs through efficient prompting. Specifically, we introduce a lightweight and model-agnostic prompt tuning framework for spatio-temporal GNNs, named SimpleST. It facilitates adapting pre-trained spatio-temporal GNNs to novel distributions while keeping the model parameters fixed. This prompt mechanism reduces the overhead and complexity of adaptation, enabling efficient utilization of pre-trained models for out-of-distribution generalization. Extensive experiments conducted on five real-world urban spatio-temporal datasets demonstrate the superiority of our approach in terms of prediction accuracy and computational efficiency. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Comments: 24 pages. This paper is accepted by VLDBJ

Journal ref: The VLDB Journal of 2026

Steering the Verifiability of Multimodal AI Hallucinations

Authors: Jianhong Pang, Ruoxi Cheng, Ziyi Ye, Xingjun Ma, Zuxuan Wu, Xuanjing Huang, Yu-Gang Jiang

Abstract: AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, such hallucinations are not equally problematic: some hallucination contents could be detected by human users(i.e., obvious hallucinations), while others are often missed or require more verification effort(i.e., elusive hallucinations). This indicat… ▽ More AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, such hallucinations are not equally problematic: some hallucination contents could be detected by human users(i.e., obvious hallucinations), while others are often missed or require more verification effort(i.e., elusive hallucinations). This indicates that multimodal AI hallucinations vary significantly in their verifiability. Yet, little research has explored how to control this property for AI applications with diverse security and usability demands. To address this gap, we construct a dataset from 4,470 human responses to AI-generated hallucinations and categorize these hallucinations into obvious and elusive types based on their verifiability by human users. Further, we propose an activation-space intervention method that learns separate probes for obvious and elusive hallucinations. We reveal that obvious and elusive hallucinations elicit different intervention probes, allowing for fine-grained control over the model's verifiability. Empirical results demonstrate the efficacy of this approach and show that targeted interventions yield superior performance in regulating corresponding verifiability. Moreover, simply mixing these interventions enables flexible control over the verifiability required for different scenarios. △ Less

Submitted 8 April, 2026; originally announced April 2026.

Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection

Authors: Yuzhen Niu, Yangqing Wang, Ri Cheng, Fusheng Li, Rongshen Wang, Zhichen Yang

Abstract: Camouflaged object detection (COD) is challenging due to high target-background similarity, and recent methods address this by complementarily using RGB-D texture and geometry cues. However, RGB-D COD methods still underutilize modality-specific cues, which limits fusion quality. We believe this is because RGB and depth features are fused directly after backbone extraction without modality-specifi… ▽ More Camouflaged object detection (COD) is challenging due to high target-background similarity, and recent methods address this by complementarily using RGB-D texture and geometry cues. However, RGB-D COD methods still underutilize modality-specific cues, which limits fusion quality. We believe this is because RGB and depth features are fused directly after backbone extraction without modality-specific enhancement. To address this limitation, we propose MHENet, an RGB-D COD framework that performs modality-specific hierarchical enhancement and adaptive fusion of RGB and depth features. Specifically, we introduce a Texture Hierarchical Enhancement Module (THEM) to amplify subtle texture variations by extracting high-frequency information and a Geometry Hierarchical Enhancement Module (GHEM) to enhance geometric structures via learnable gradient extraction, while preserving cross-scale semantic consistency. Finally, an Adaptive Dynamic Fusion Module (ADFM) adaptively fuses the enhanced texture and geometry features with spatially varying weights. Experiments on four benchmarks demonstrate that MHENet surpasses 16 state-of-the-art methods qualitatively and quantitatively. Code is available at https://github.com/afdsgh/MHENet. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Comments: 11 pages, 7 figures, including supplementary material. Accepted by IEEE ICME 2026

Dual-Domain Representation Alignment: Bridging 2D and 3D Vision via Geometry-Aware Architecture Search

Authors: Haoyu Zhang, Zhihao Yu, Rui Wang, Yaochu Jin, Qiqi Liu, Ran Cheng

Abstract: Modern computer vision requires balancing predictive accuracy with real-time efficiency, yet the high inference cost of large vision models (LVMs) limits deployment on resource-constrained edge devices. Although Evolutionary Neural Architecture Search (ENAS) is well suited for multi-objective optimization, its practical use is hindered by two issues: expensive candidate evaluation and ranking inco… ▽ More Modern computer vision requires balancing predictive accuracy with real-time efficiency, yet the high inference cost of large vision models (LVMs) limits deployment on resource-constrained edge devices. Although Evolutionary Neural Architecture Search (ENAS) is well suited for multi-objective optimization, its practical use is hindered by two issues: expensive candidate evaluation and ranking inconsistency among subnetworks. To address them, we propose EvoNAS, an efficient distributed framework for multi-objective evolutionary architecture search. We build a hybrid supernet that integrates Vision State Space and Vision Transformer (VSS-ViT) modules, and optimize it with a Cross-Architecture Dual-Domain Knowledge Distillation (CA-DDKD) strategy. By coupling the computational efficiency of VSS blocks with the semantic expressiveness of ViT modules, CA-DDKD improves the representational capacity of the shared supernet and enhances ranking consistency, enabling reliable fitness estimation during evolution without extra fine-tuning. To reduce the cost of large-scale validation, we further introduce a Distributed Multi-Model Parallel Evaluation (DMMPE) framework based on GPU resource pooling and asynchronous scheduling. Compared with conventional data-parallel evaluation, DMMPE improves efficiency by over 70% through concurrent multi-GPU, multi-model execution. Experiments on COCO, ADE20K, KITTI, and NYU-Depth v2 show that the searched architectures, termed EvoNets, consistently achieve Pareto-optimal trade-offs between accuracy and efficiency. Compared with representative CNN-, ViT-, and Mamba-based models, EvoNets deliver lower inference latency and higher throughput under strict computational budgets while maintaining strong generalization on downstream tasks such as novel view synthesis. Code is available at https://github.com/EMI-Group/evonas △ Less

Submitted 19 March, 2026; originally announced March 2026.

VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models

Authors: Zirui Ge, Pengxiang Ding, Baohua Yin, Qishen Wang, Zhiyong Xie, Yemin Wang, Jinbo Wang, Hengtao Li, Runze Suo, Wenxuan Song, Han Zhao, Shangke Lyu, Zhaoxin Fan, Haoang Li, Ran Cheng, Cheng Chi, Huibin Ge, Yaozhi Luo, Donglin Wang

Abstract: Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based video predictors are trained with likelihood-surrogate objectives, which encourage globally plausible predictions without explicitly optimizing the precision-criti… ▽ More Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based video predictors are trained with likelihood-surrogate objectives, which encourage globally plausible predictions without explicitly optimizing the precision-critical visual dynamics needed for manipulation. This objective mismatch often leads to subtle errors in object pose, spatial relations, and contact timing that can be amplified by downstream policies. We propose VAMPO, a post-training framework that directly improves visual dynamics in video action models through policy optimization. Our key idea is to formulate multi-step denoising as a sequential decision process and optimize the denoising policy with rewards defined over expert visual dynamics in latent space. To make this optimization practical, we introduce an Euler Hybrid sampler that injects stochasticity only at the first denoising step, enabling tractable low-variance policy-gradient estimation while preserving the coherence of the remaining denoising trajectory. We further combine this design with GRPO and a verifiable non-adversarial reward. Across diverse simulated and real-world manipulation tasks, VAMPO improves task-relevant visual dynamics, leading to better downstream action generation and stronger generalization. The homepage is https://vampo-robot.github.io/VAMPO/. △ Less

Submitted 19 March, 2026; originally announced March 2026.

Efficient and Effective Table-Centric Table Union Search in Data Lakes

Authors: Yongkang Sun, Zhihao Ding, Huiqiang Wang, Reynold Cheng, Jieming Shi

Abstract: In data lakes, information on the same subject is often fragmented across multiple tables. Table union search aims to find the top-k tables that can be unioned with a query table to extend it with more rows, without relying on metadata or ground-truth labels. Existing methods are mainly column-centric: they focus on modeling column unionability scores using column embeddings, which are then used t… ▽ More In data lakes, information on the same subject is often fragmented across multiple tables. Table union search aims to find the top-k tables that can be unioned with a query table to extend it with more rows, without relying on metadata or ground-truth labels. Existing methods are mainly column-centric: they focus on modeling column unionability scores using column embeddings, which are then used throughout the search process for column matching, filtering, and aggregation. However, this overlooks holistic table-level semantics, which may result in suboptimal rankings and inefficiencies. We introduce TACTUS, a novel table-centric method for table union search. Unlike prior work that searches from columns to tables, we search in a table-first way and examine columns only in the final step. During offline processing, we directly generate table embeddings for holistic, table-level unionability scoring by designing table-level representation techniques, including positive table pair construction to simulate unionable tables, two-pronged negative table sampling to avoid latent positives and mine hard negatives to enhance representation quality, and attentive table encoding for effective embeddings. During online search, we first develop a table-centric adaptive candidate retrieval method that efficiently selects a compact, high-quality candidate pool by leveraging the distribution of table-level unionability scores induced by table embeddings. We then inspect columns only within this compact candidate set and design a dual-evidence reranking technique that integrates table-level and column-level scores to refine the final top-k results. Extensive experiments on real-world datasets show that TACTUS significantly improves result quality while being much faster than existing methods in both offline and online processing, often by an order of magnitude. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: 14 pages

Membership Inference for Contrastive Pre-training Models with Text-only PII Queries

Authors: Ruoxi Cheng, Yizhong Ding, Jian Zhao, Hongyi Zhang, Haoxuan Ma, Tianle Zhang, Yiyan Huang, Xuelong Li

Abstract: Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises growing concerns about memorizing Personally Identifiable Information (PII). Auditing such models via membership inference is challenging in practice: shadow-model MIAs are computationally prohibitive for large multimodal… ▽ More Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises growing concerns about memorizing Personally Identifiable Information (PII). Auditing such models via membership inference is challenging in practice: shadow-model MIAs are computationally prohibitive for large multimodal backbones, and existing multimodal auditing methods typically require querying the target with paired biometric inputs, thereby directly exposing sensitive biometric information to the target model. To bypass this critical limitation, we demonstrate a highly desirable capability for privacy auditing: multimodal memorization within these foundational encoders can be accurately inferred using exclusively the text modality. We propose Unimodal Membership Inference Detector (UMID), a text-only auditing framework that performs text-guided cross-modal latent inversion and extracts two complementary signals, similarity (alignment to the queried text) and variability (consistency across randomized inversions). UMID compares these statistics to a lightweight non-member reference constructed from synthetic gibberish and makes decisions via an ensemble of unsupervised anomaly detectors. Comprehensive experiments across diverse CLIP and CLAP architectures demonstrate that UMID significantly improves the effectiveness and efficiency over prior MIAs, delivering strong detection performance with sub-second auditing cost using solely text queries, completely circumventing the need for biometric inputs and complying with strict privacy constraints. △ Less

Submitted 22 April, 2026; v1 submitted 15 March, 2026; originally announced March 2026.

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution

Authors: Hongsong Wang, Renxi Cheng, Chaolei Han, Jie Gui

Abstract: With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation techniques. To facilitate the identification of AI-generated images and the attribution of their source models, generative image watermarking and AI-generated image at… ▽ More With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation techniques. To facilitate the identification of AI-generated images and the attribution of their source models, generative image watermarking and AI-generated image attribution have emerged as key research focuses in recent years. However, existing methods are model-dependent, requiring access to the generative models and lacking generality and scalability to new and unseen generators. To address these limitations, this work presents a new paradigm for AI-generated image attribution by formulating it as an instance retrieval problem instead of a conventional image classification problem. We propose an efficient model-agnostic framework, called Low-bIt-plane-based Deepfake Attribution (LIDA). The input to LIDA is produced by Low-Bit Fingerprint Generation module, while the training involves Unsupervised Pre-Training followed by subsequent Few-Shot Attribution Adaptation. Comprehensive experiments demonstrate that LIDA achieves state-of-the-art performance for both Deepfake detection and image attribution under zero- and few-shot settings. The code is at https://github.com/hongsong-wang/LIDA △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: To appear in CVPR 2026, Code is at https://github.com/hongsong-wang/LIDA

Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting

Authors: Ran Cheng

Abstract: Catastrophic forgetting remains a central challenge in continual learning (CL), yet lacks a unified information-theoretic explanation for why some architectures forget catastrophically while others do not. We introduce \emph{Context Channel Capacity} ($C_\mathrm{ctx}$), the mutual information between a CL architecture's context signal and its generated parameters, and prove that zero forgetting re… ▽ More Catastrophic forgetting remains a central challenge in continual learning (CL), yet lacks a unified information-theoretic explanation for why some architectures forget catastrophically while others do not. We introduce \emph{Context Channel Capacity} ($C_\mathrm{ctx}$), the mutual information between a CL architecture's context signal and its generated parameters, and prove that zero forgetting requires $C_\mathrm{ctx} \geq H(T)$, where $H(T)$ is the task identity entropy. We establish an \emph{Impossibility Triangle} -- zero forgetting, online learning, and finite parameters cannot be simultaneously satisfied by sequential state-based learners -- and show that conditional regeneration architectures (HyperNetworks) bypass this triangle by redefining parameters as function values rather than states. We validate this framework across 8 CL methods on Split-MNIST (1,130+ experiments over 86 days, 4 seeds each), showing that $C_\mathrm{ctx}$ perfectly predicts forgetting behavior: methods with $C_\mathrm{ctx} = 0$ (NaiveSGD, EWC, SI, LwF, CFlow) exhibit catastrophic forgetting (6--97\%), while methods with $C_\mathrm{ctx} \approx 1$ (HyperNetwork) achieve zero forgetting (98.8\% ACC). We further propose \emph{Wrong-Context Probing} (P5), a practical diagnostic protocol for measuring $C_\mathrm{ctx}$, and extend the framework to CIFAR-10 via a novel \emph{Gradient Context Encoder} that closes the oracle gap from 23.3pp to 0.7pp. A systematic taxonomy of 15+ closed research directions -- including the Hebbian null result (frozen random features outperform learned features), CFlow's $θ_0$-memorizer phenomenon, and the $S_N$ symmetry barrier to column specialization -- provides the community with precisely diagnosed negative results. Our central design principle: \emph{architecture over algorithm} -- the context pathway must be structurally unbypassable. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Comments: 39 pages

Contract-based Agentic Intent Framework for Network Slicing in O-RAN

Authors: Fransiscus Asisi Bimo, Chun-Kai Lai, Zhi-Yuan Yang, Ray-Guang Cheng

Abstract: Intent-based networking aims to simplify network operation by translating operator intents into a collection of policies, configurations, and control actions. However, this translation process relies on heuristics and loose coupling. It often results in unpredictable behavior and ambiguous safety standards. This paper presents a Contract-based Agentic Intent Framework (CAIF) for the radio access n… ▽ More Intent-based networking aims to simplify network operation by translating operator intents into a collection of policies, configurations, and control actions. However, this translation process relies on heuristics and loose coupling. It often results in unpredictable behavior and ambiguous safety standards. This paper presents a Contract-based Agentic Intent Framework (CAIF) for the radio access network (RAN). The proposed framework employs a closed-loop agentic pipeline that systematically audits user objectives against formal RAN constraints prior to actuation. The proposed CAIF decouples probabilistic intent extraction from strictly governed policy execution to enable the enforcement of deterministic safety guarantees. We use network slicing as a representative use case to demonstrate the design flow and validate the effectiveness of the proposed approach on an O-RAN testbed. Experimental results show that the closed-loop agentic pipeline of the proposed CAIF can effectively eliminate harmful intent executions observed in direct-actuation baseline approaches. △ Less

Submitted 2 March, 2026; originally announced March 2026.

Comments: 6 pages, Accepted at IEEE INFOCOM 2026

NFT Games: an Empirical Look into the Play-to-Earn Model

Authors: Yixiao Gao, Fei Li, Ruizhe Shi, Ruizhi Cheng, Jean Zhang, Bo Han, Songqing Chen

Abstract: The past decade has witnessed the burgeoning and continuous development of blockchain and its applications. Besides various cryptocurrencies, an industry that has quickly embraced this trend is gaming. Thanks to the support of blockchain, games have started to incorporate non-fungible tokens (NFTs) that can enable a new gaming model, play-to-earn (P2E), which incentivizes users to participate and… ▽ More The past decade has witnessed the burgeoning and continuous development of blockchain and its applications. Besides various cryptocurrencies, an industry that has quickly embraced this trend is gaming. Thanks to the support of blockchain, games have started to incorporate non-fungible tokens (NFTs) that can enable a new gaming model, play-to-earn (P2E), which incentivizes users to participate and play. While recent studies looked at several NFT games qualitatively and individually, an in-depth understanding is still missing, particularly on how the P2E model has transformed traditional games. In this work, we set to conduct a measurement study of NFT games, aiming to gain a comprehensive understanding of the effectiveness of P2E in practice. For this purpose, we collect and analyze relevant NFT transaction data from the underlying blockchain (e.g., Ethereum) of 12 games, supplemented with various data scraped from their websites. Our study shows that (1) a few top wallets control unproportionally high percentage of NFTs, and the majority of wallets own only one or two NFTs and do not actively trade; (2) promotion events do boost the trade amount and the NFT price for some games, but their effect does not sustain; and (3) few players actually earned a profit, and players in 9 out of 12 games who traded NFTs have a negative profit on average. Motivated by these findings, we further investigate effective incentive mechanisms based on game theory to improve the trading profits that players can earn from these NFT games. Both modeling and simulation results confirm the effectiveness of the proposed incentive mechanism. △ Less

Submitted 14 February, 2026; originally announced February 2026.

Comments: 17 pages, 12 figures

A Multi-objective Evolutionary Algorithm Based on Bi-population with Uniform Sampling for Neural Architecture Search

Authors: Yu Xue, Pengcheng Jiang, Chenchen Zhu, Yong Zhang, Ran Cheng, Kaizhou Gao, Dunwei Gong

Abstract: Neural architecture search (NAS) automates neural network design, improving efficiency over manual approaches. However, efficiently discovering high-performance neural network architectures that simultaneously optimize multiple objectives remains a significant challenge in NAS. Existing methods often suffer from limited population diversity and inadequate exploration of the search space, particula… ▽ More Neural architecture search (NAS) automates neural network design, improving efficiency over manual approaches. However, efficiently discovering high-performance neural network architectures that simultaneously optimize multiple objectives remains a significant challenge in NAS. Existing methods often suffer from limited population diversity and inadequate exploration of the search space, particularly in regions with extreme complexity values. To address these challenges, we propose MOEA-BUS, an innovative multi-objective evolutionary algorithm based on bi-population with uniform sampling for neural architecture search, aimed at simultaneously optimizing both accuracy and network complexity. In MOEA-BUS, a novel uniform sampling method is proposed to initialize the population, ensuring that architectures are distributed uniformly across the objective space. Furthermore, to enhance exploration, we deploy a bi-population framework where two populations evolve synergistically, facilitating comprehensive search space coverage. Experiments on CIFAR-10 and ImageNet demonstrate MOEA-BUS's superiority, achieving top-1 accuracies of 98.39% on CIFAR-10, and 80.03% on ImageNet. Notably, it achieves 78.28% accuracy on ImageNet with only 446M MAdds. Ablation studies confirm that both uniform sampling and bi-population mechanisms enhance population diversity and performance. Additionally, in terms of the Kendall's tau coefficient, the SVM achieves an improvement of at least 0.035 compared to the other three commonly used machine learning models, and uniform sampling provided an enhancement of approximately 0.07. △ Less

Submitted 9 February, 2026; originally announced February 2026.

Comments: Accepted by IEEE Transactions on Neural Networks and Learning Systems. Published on this https URL: https://doi.org/10.1109/TNNLS.2026.3659508

Mapping the Design Space of User Experience for Computer Use Agents

Authors: Ruijia Cheng, Jenny T. Liang, Eldon Schoop, Jeffrey Nichols

Abstract: Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user experience (UX). We conducted a two-phase study to map the UX design space for computer use agents. In Phase 1, we reviewed existing systems to develop a taxonomy of… ▽ More Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user experience (UX). We conducted a two-phase study to map the UX design space for computer use agents. In Phase 1, we reviewed existing systems to develop a taxonomy of UX considerations, then refined it through interviews with eight UX and AI practitioners. The resulting taxonomy included categories such as user prompts, explainability, user control, and users' mental models, with corresponding subcategories and example design features. In Phase 2, we ran a Wizard-of-Oz study with 20 participants, where a researcher acted as a web-based computer use agent and probed user reactions during normal, error-prone and risky execution. We used the findings to validate the taxonomy from Phase 1 and deepen our understand of the design space by identifying the connections between design areas and divergence in user needs and scenarios. Our taxonomy and empirical insights provide a map for developers to consider different aspects of user experience in computer use agent design and to situate their designs within users' diverse needs and scenarios. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Journal ref: n 31st International Conference on Intelligent User Interfaces (IUI'26), March 23-26, 2026, Paphos, Cyprus. ACM, New York, NY, USA, 17 pages

FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matching

Authors: Ran Cheng, Lailai Zhu

Abstract: Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine learning (ML)-based forecasting pipelines due to reliance on traditional variational methods. Recent generative ML-based DA methods offer a promising alternative but typically require many sampling steps and suffer from error accumulation under long-horizon aut… ▽ More Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine learning (ML)-based forecasting pipelines due to reliance on traditional variational methods. Recent generative ML-based DA methods offer a promising alternative but typically require many sampling steps and suffer from error accumulation under long-horizon auto-regressive rollouts with cycling assimilation. We propose FlowDA, a low-latency weather-scale generative DA framework based on flow matching. FlowDA conditions on observations through a SetConv-based embedding and fine-tunes the Aurora foundation model to deliver accurate, efficient, and robust analyses. Experiments across observation rates decreasing from $3.9\%$ to $0.1\%$ demonstrate superior performance of FlowDA over strong baselines with similar tunable-parameter size. FlowDA further shows robustness to observational noise and stable performance in long-horizon auto-regressive cycling DA. Overall, FlowDA points to an efficient and scalable direction for data-driven DA. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Jamming Attacks on the Random Access Channel in 5G and B5G Networks

Authors: Wilfrid Azariah, Yi-Quan Chen, Zhong-Xin You, Ray-Guang Cheng, Shiann-Tsong Sheu, Binbin Chen

Abstract: Random Access Channel (RACH) jamming poses a critical security threat to 5G and beyond (B5G) networks. This paper presents an analytical model for predicting the impact of Msg1 jamming attacks on RACH performance. We use the OpenAirInterface (OAI) open-source user equipment (UE) to implement a Msg1 jamming attacker. Over-the-air experiments validate the accuracy of the proposed analytical model. T… ▽ More Random Access Channel (RACH) jamming poses a critical security threat to 5G and beyond (B5G) networks. This paper presents an analytical model for predicting the impact of Msg1 jamming attacks on RACH performance. We use the OpenAirInterface (OAI) open-source user equipment (UE) to implement a Msg1 jamming attacker. Over-the-air experiments validate the accuracy of the proposed analytical model. The results show that low-power and stealthy Msg1 jamming can effectively block legitimate UE access in 5G/B5G systems. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Comments: To be published on IEEE WCNC 2026

GRAB: An LLM-Inspired Sequence-First Click-Through Rate Prediction Modeling Paradigm

Authors: Shaopeng Chen, Chuyue Xie, Huimin Ren, Shaozong Zhang, Han Zhang, Ruobing Cheng, Zhiqiang Cao, Zehao Ju, Yu Gao, Jie Ding, Xiaodong Chen, Xuewu Jiao, Shuanglong Li, Liu Lin

Abstract: Traditional Deep Learning Recommendation Models (DLRMs) face increasing bottlenecks in performance and efficiency, often struggling with generalization and long-sequence modeling. Inspired by the scaling success of Large Language Models (LLMs), we propose Generative Ranking for Ads at Baidu (GRAB), an end-to-end generative framework for Click-Through Rate (CTR) prediction. GRAB integrates a novel… ▽ More Traditional Deep Learning Recommendation Models (DLRMs) face increasing bottlenecks in performance and efficiency, often struggling with generalization and long-sequence modeling. Inspired by the scaling success of Large Language Models (LLMs), we propose Generative Ranking for Ads at Baidu (GRAB), an end-to-end generative framework for Click-Through Rate (CTR) prediction. GRAB integrates a novel Causal Action-aware Multi-channel Attention (CamA) mechanism to effectively capture temporal dynamics and specific action signals within user behavior sequences. Full-scale online deployment demonstrates that GRAB significantly outperforms established DLRMs, delivering a 3.05% increase in revenue and a 3.49% rise in CTR. Furthermore, the model demonstrates desirable scaling behavior: its expressive power shows a monotonic and approximately linear improvement as longer interaction sequences are utilized. △ Less

Submitted 3 February, 2026; v1 submitted 2 February, 2026; originally announced February 2026.