Showing 1–50 of 195 results for author: Yao, B

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions

Authors: Xinzhe Huang, Biwu Yao, Kedong Xiu, Mengnan Zhao, Di Wang, Puning Zhao, Tianhang Zheng

Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a deterministic classification task, mapping a discrete token sequence to a discrete safety label. However, this paradigm has two limitations: First, safety assessment is inherently an uncertain problem, particularly during… ▽ More Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a deterministic classification task, mapping a discrete token sequence to a discrete safety label. However, this paradigm has two limitations: First, safety assessment is inherently an uncertain problem, particularly during the early generation state. Second, relying solely on discrete token sequences discards the rich probabilistic information embedded in the LLM output distribution. To address these limitations, we propose the first completely probabilistic architecture-agnostic guardrail \textsc{ProbGuard} to leverage the LLM early output distributional signals for estimating and calibrating the safety probability, thereby enabling early stopping of unsafe ongoing outputs. Specifically, given an LLM's generated prefix distribution, we formulate the safety risk as the unsafe probability of its continued generation dynamics and estimate this risk by Monte-Carlo sampling. Through post-training on the distributional signals and calibrated safety risk, \textsc{ProbGuard} achieves the best calibration performance across all nine model--dataset combination settings, reducing the average Brier score and ECE by 79.6\% and 71.9\%, respectively, over the best baseline. \textsc{ProbGuard} further limits the attack success rate to at most 1\% across six representative jailbreak attacks after observing the LLM early output distributions from only the first ten decoding steps. △ Less

Submitted 11 August, 2026; originally announced August 2026.

EchoChange: A Diffusion Language Model with Dual Pass Remasking for Factual Remote Sensing Disaster Change Captioning

Authors: Dongwei Sun, Bowen Yao, Yujie Zhang, Pei Liu, Jing Yao, Xiangyong Cao

Abstract: Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions. However, existing change captioning methods always follow an autoregressive decoding paradigm to generate the change description and thus an early misinterpretation of the changed ob… ▽ More Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions. However, existing change captioning methods always follow an autoregressive decoding paradigm to generate the change description and thus an early misinterpretation of the changed object, event, or spatial relation becomes an irreversible premise for subsequent text, amplifying visual ambiguity into cascading factual errors. To address this limitation, we propose EchoChange, a multimodal discrete diffusion language model that formulates change captioning as iterative masked-token denoising rather than left-to-right generation. By repeatedly revising the entire caption while conditioning on the image pair, EchoChange can reconsider uncertain content and correct imperfect intermediate predictions. We further introduce draft-aware dual-pass training, a progressive masking curriculum, and confidence-guided remasking to align training with iterative inference. Extensive experiments on the RSCC benchmark show that EchoChange substantially outperforms both general-purpose and remote-sensing-specific baselines across lexical and semantic metrics. The EchoChange Project is at https://sundongwei.github.io/EchoChange_Project/ △ Less

Submitted 14 August, 2026; v1 submitted 3 August, 2026; originally announced August 2026.

DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulation

Authors: Yunfan Lou, Hewen Gao, Xiyu Zhu, Zhuoran Qiao, Xuan Han, Yifan Yang, Yifan Ye, Boxian Yao, Zhibo Pang

Abstract: Dynamic manipulation requires robots to infer target motion and respond promptly, yet existing World-Action Models (WAMs) typically condition only on the current frame and execute large backbones synchronously, limiting motion awareness and responsive control in dynamic scenes. We propose DynamicWAM, a compact WAM for dynamic object manipulation with dual-path motion conditioning. DynamicWAM intro… ▽ More Dynamic manipulation requires robots to infer target motion and respond promptly, yet existing World-Action Models (WAMs) typically condition only on the current frame and execute large backbones synchronously, limiting motion awareness and responsive control in dynamic scenes. We propose DynamicWAM, a compact WAM for dynamic object manipulation with dual-path motion conditioning. DynamicWAM introduces history-flow conditioning, encoding temporally aligned optical-flow frames alongside the current observation through a frozen pretrained video VAE to preserve spatial motion structure, while injecting kinematic descriptors of displacement, duration, velocity, and acceleration into the action expert to provide motion magnitude and timing. The two complementary paths are fused through joint world-action attention. A distilled compact backbone and real-time chunking (RTC)-based asynchronous execution further enable responsive control. On DOMINO, DynamicWAM achieves a 38.2% success rate and a 53.2 manipulation score, outperforming all evaluated baselines. Across 12 real-world tasks spanning linear, circular, and compound target motion, it achieves a 46.7% average success rate, exceeding the strongest baseline by 22.9 percentage points. △ Less

Submitted 6 August, 2026; v1 submitted 1 August, 2026; originally announced August 2026.

Comments: 18 pages, 9 figures. Project page: https://dynamicwam.github.io/

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Authors: Kehan Li, Bohan Hou, Minghao Zhu, Tianyi Zhang, Zesen Cheng, Zhikai Wang, Sicong Leng, Xin Li, Xiao Lin, Biying Yao, Minghua Zeng, Jiangpin Liu, Ronghao Dang, Jiayan Guo, Siteng Huang, Haoyu Zhao, Heng Ping, Yaxi Zhao, Tong Zhao, Kexiang Wang, Tong Lu, Shengke Xue, Jiahao Tang, Yulei Wang, Zejing Wang , et al. (6 additional authors not shown)

Abstract: We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared with RynnBrain 1.0, it further introduces contact-point prediction across the model family and native 3D grounding for the… ▽ More We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared with RynnBrain 1.0, it further introduces contact-point prediction across the model family and native 3D grounding for the 2B and 9B models, yielding representations and outputs that are more directly aligned with robot manipulation. We also develop RynnBrain-VLA with a unified cross-embodiment action space and embodiment-specific masking, and deploy it on Unitree G1, Astribot-S1, and Tianji-Wuji. RynnBrain 1.1 achieves strong results on embodied cognition, localization, and 3D grounding, with the 122B-A10B model outperforming all evaluated proprietary and open-source models on VSI-Bench, MMSI, and RefSpatial-Bench. Real-robot experiments show that RynnBrain-initialized policies outperform Qwen-based and representative generalist VLAs, while joint multi-task and multi-embodiment training improves process scores and success rates over per-task training. △ Less

Submitted 31 July, 2026; v1 submitted 20 July, 2026; originally announced July 2026.

Comments: KL,BH,MZ,TZ,ZC,ZW,SL,XL,XL,BY,MZ,JL,RD contribute equally. Project Lead: Kehan Li and Xin Li project: https://alibaba-damo-academy.github.io/RynnBrain github: https://github.com/alibaba-damo-academy/RynnBrain huggingface: https://huggingface.co/collections/Alibaba-DAMO-Academy/rynnbrain-11 modelscope: https://modelscope.cn/collections/DAMO_Academy/RynnBrain-11

Hybrid Retriever Evolution for Multimodal Document Reasoning Agents

Authors: Bohan Yao, Shruthan Radhakrishna, Vikas Yadav

Abstract: Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that cannot adapt to the demands of individual reasoning steps. In this work, we ask whether retrieval orchestration itself can be learned as part of the reasoning process. We introduce a fa… ▽ More Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that cannot adapt to the demands of individual reasoning steps. In this work, we ask whether retrieval orchestration itself can be learned as part of the reasoning process. We introduce a failure-driven evolution framework in which a meta-agent autonomously discovers how a tool-using task agent should coordinate diverse retrievers during multi-step document question answering. The meta-agent analyzes incorrect reasoning trajectories, actively probes the same tool environment to diagnose root causes, and iteratively rewrites the task agent's instructions, turning retrieval from a fixed front-end stage into an adaptive, step-wise reasoning decision. The evolved agent learns when to invoke each retriever, how to combine them, and how to compose evidence across modalities and pages. On MMLongBench-Doc and DocBench, the evolved agent achieves gains of up to +19.6 points over the unevolved baseline and consistently outperforms recent systems including MACT, MDocAgent, and SimpleDoc. Detailed retrieval analyses confirm that these improvements arise from adaptive routing and evidence composition rather than reliance on any hard coded retrieval mode, and evolution dynamics reveal a progressive shift from narrow lexical behavior to rich multi-tool coordination. These findings establish autonomous multi-agent coordination as a promising paradigm for multimodal document reasoning. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Comments: 17 pages, 3 figures

P-K-GCN: Physics-augmented Koopman-enhanced Graph Convolutional Network for Deep Spatiotemporal Super-resolution

Authors: Xizhuo, Zhang, Zekai Wang, Fei Liu, Bing Yao

Abstract: High-fidelity simulation of spatiotemporal dynamics is computationally prohibitive, necessitating efficient super-resolution techniques to reconstruct high-resolution data from coarse-grained inputs. Traditional data-driven methods often lack physical constraints, and simple physics-informed learning struggles with irregular spatial geometries and intricately evolving temporal dynamics. To tackle… ▽ More High-fidelity simulation of spatiotemporal dynamics is computationally prohibitive, necessitating efficient super-resolution techniques to reconstruct high-resolution data from coarse-grained inputs. Traditional data-driven methods often lack physical constraints, and simple physics-informed learning struggles with irregular spatial geometries and intricately evolving temporal dynamics. To tackle these challenges, we propose a Physics-augmented Koopman-enhanced Graph Convolutional Network (P-K-GCN) for spatiotemporal super-resolution on irregular geometries. Specifically, a continuous spline-based GCN is first designed to extract spatial dependencies directly from coarse graph, and Koopman operator theory is incorporated to project the nonlinear dynamics into a compact latent space where temporal progression is linearized. Second, we augment the optimization objective with a physics-based loss to force the data-driven reconstructions to adhere to physical laws for improving predictive fidelity and robustness. Finally, we provide a rigorous theoretical analysis, establishing that the physics augmentation and Koopman regularization mathematically guarantees a reduction in super-resolution error by diminishing Rademacher complexity and tightening generalization bounds. We evaluate our framework on reconstructing spatially high-resolution cardiac electrodynamics across a 3D heart geometry from sparse low-resolution measurements. Numerical experiments demonstrate that our method achieves superior accuracy compared to baseline models. △ Less

Submitted 17 June, 2026; originally announced June 2026.

CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments

Authors: Jiaju Chen, Bo Sun, Yuxuan Lu, Yun Wang, Dakuo Wang, Bingsheng Yao

Abstract: Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels much as human teams do. Yet recent study suggests that MAS often falter not because agents lack individual task-solving ability, but because they lack collaborative competence: the capacity to establish common ground, mai… ▽ More Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels much as human teams do. Yet recent study suggests that MAS often falter not because agents lack individual task-solving ability, but because they lack collaborative competence: the capacity to establish common ground, maintain shared task understanding, balance individual and collective incentives, and repair misalignment as interaction unfolds. Decades of research in Computer-Supported Cooperative Work have characterized these requirements for human teams coordinating under constrained communication, yet existing MAS evaluations focus mainly on task outcomes or single-agent proficiency in reasoning, planning, and tool use. To enable a systematic analysis of agents' collaborative competence in MAS, we introduce CollabSim, a configurable simulation framework that combines a theory-grounded definition of collaborative capabilities, controlled manipulation of interaction conditions, and action-level probing of agents' internal states. Experiments across four LLMs show that CollabSim can capture condition effects, separate model performance patterns, and reveal task-dependent effects of agent design. △ Less

Submitted 5 June, 2026; v1 submitted 4 June, 2026; originally announced June 2026.

MSC Class: 68T50

Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration

Authors: Jiaju Chen, Yuxuan Lu, Jiayi Su, Chaoran Chen, Songlin Xiao, Zheng Zhang, Yun Wang, Yunyao Li, Jian Zhao, Tongshuang Wu, Toby Jia-Jun Li, Dakuo Wang, Bingsheng Yao

Abstract: Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human collaborators. Effective collaboration, however, requires collaborators to continuously maintain and align mental models of their own reasoning,partners' intentions, and shared goals during the collaborative process. Today… ▽ More Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human collaborators. Effective collaboration, however, requires collaborators to continuously maintain and align mental models of their own reasoning,partners' intentions, and shared goals during the collaborative process. Today's agents rarely develop such capabilities since they are primarily optimized for task completion, and the community lacks authentic human collaboration data with action-level mental model annotations that could guide agents toward process-level collaborative competence. To bridge this gap, we present ALMANAC, a dataset of Action-Level Mental model ANnotations for Agent Collaboration built from the Map Task, a classic dyadic routing task from social science. ALMANAC contains 2,987 collaboration actions, each paired with theory-informed mental model annotations that record the participants' self-reasoning, perceived partner intent, and perceived team goal. We benchmark six LLMs on predicting humans' next-turn behavior and mental models. Our results demonstrate ALMANAC's utility in evaluating models' ability to simulate human collaborative behaviors and infer their underlying mental models. △ Less

Submitted 5 June, 2026; v1 submitted 4 June, 2026; originally announced June 2026.

MSC Class: 68T50

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction

Authors: Jiahao Shao, Xudong Wang, Anam Nawaz Khan, Christopher Brett, Xueping Li, Bing Yao

Abstract: Breast cancer recurrence, a leading cause of long-term mortality among survivors, requires timely and accurate risk assessment to guide follow-up care and treatment planning. Traditional predictive models, often limited to either structured or unstructured data alone, struggle to capture the full clinical context. This study examines the impact of integrating multi-modal clinical data, including t… ▽ More Breast cancer recurrence, a leading cause of long-term mortality among survivors, requires timely and accurate risk assessment to guide follow-up care and treatment planning. Traditional predictive models, often limited to either structured or unstructured data alone, struggle to capture the full clinical context. This study examines the impact of integrating multi-modal clinical data, including treatment records, pathology reports, and clinician notes, on recurrence prediction. By integrating a rule-based regular expression extraction mechanism with a rigorous precedence-based conflict reconciliation strategy, our approach effectively recovers definitive tumor characteristics from free-text pathology narratives to augment structured records. We also benchmark performance against commonly used feature sets from prior breast cancer studies to assess the added value of multi-modal integration. Single-source and multi-modal inputs are evaluated across a range of machine learning models. Results show that multi-modal integration consistently improves predictive accuracy compared to single-modal methods. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: 33 pages, 10 figures

Deco: Extending Personal Physical Objects into Pervasive AI Companion through a Dual-Embodiment Framework

Authors: Zhihan Jiang, Mengyuan Millie Wu, Ruishi Zou, Shiyu Xu, Xun Qian, Emma Macmanus, Steven Liao, Ping Zhang, Bingsheng Yao, Tingyu Cheng, James L. David, Nabila El-Bassel, Lena Mamykina, Frances R. Levin, Ryan Sultan, Dakuo Wang, Xuhai Xu

Abstract: Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI companions offer responsiveness and personalization, they exist independently of these physical objects and lack an ongoing connection to them. To bridge this gap, we conducted a formative study (N=9) to explore how digital agents could inherit and ex… ▽ More Individuals frequently form deep attachments to physical objects (e.g., plush toys) that usually cannot sense or respond to their emotions. While AI companions offer responsiveness and personalization, they exist independently of these physical objects and lack an ongoing connection to them. To bridge this gap, we conducted a formative study (N=9) to explore how digital agents could inherit and extend the emotional bond, deriving four design principles (Faithful Identity, Calibrated Agency, Ambient Presence, and Reciprocal Memory). We then present the Dual-Embodiment Companion Framework, instantiated as Deco, a mobile system integrating multimodal Large Language Models (LLMs) and Augmented Reality to create synchronized digital embodiments of users' physical companions. A within-subjects study (N=25) showed Deco significantly outperformed a personalized LLM-empowered digital companion baseline on perceived companionship, emotional bond, and design-principle scales (all p<0.01). A seven-day field deployment (N=17) showed sustained engagement, subjective well-being improvement (p=.040), and three key relational patterns: digital activities retroactively vitalized physical objects, bond deepening was driven by emotional engagement depth rather than interaction frequency, and users sustained bonds while actively navigating digital companions' AI nature. This work highlights a promising alternative for designing digital companions: moving from creating new relationships to dual embodiment, where digital agents seamlessly extend the emotional history of physical objects. △ Less

Submitted 5 May, 2026; originally announced May 2026.

Comments: 27 pages, 7 figures

The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview

Authors: Kai Liu, Haoyang Yue, Zeli Lin, Zheng Chen, Jingkai Wang, Jue Gong, Jiatong Li, Xianglong Yan, Libo Zhu, Jianze Li, Ziqing Zhang, Zihan Zhou, Xiaoyang Liu, Radu Timofte, Yulun Zhang, Junye Chen, Zhenming Yan, Yucong Hong, Ruize Han, Song Wang, Li Pang, Heng Zhao, Xinqiao Wu, Deyu Meng, Xiangyong Cao , et al. (43 additional authors not shown)

Abstract: This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The challenge aims to recover high-resolution (HR) infrared images from low-resolution (LR) inputs generated through bicubic downsampling with a x4 scaling factor. The objective is to develop effective models or solutions that achieve state-of-the-art pe… ▽ More This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The challenge aims to recover high-resolution (HR) infrared images from low-resolution (LR) inputs generated through bicubic downsampling with a x4 scaling factor. The objective is to develop effective models or solutions that achieve state-of-the-art performance for infrared image SR in remote sensing scenarios. To reflect the characteristics of infrared data and practical application needs, the challenge adopts a single-track setting. A total of 115 participants registered for the competition, with 13 teams submitting valid entries. This report summarizes the challenge design, dataset, evaluation protocol, main results, and the representative methods of each team. The challenge serves as a benchmark to advance research in infrared image super-resolution and promote the development of effective solutions for real-world remote sensing applications. △ Less

Submitted 23 April, 2026; originally announced April 2026.

Comments: Github Repo: https://github.com/Kai-Liu001/NTIRE2026_infraredSR

DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization

Authors: Haokun Lin, Xinle Jia, Haobo Xu, Bingchen Yao, Xianglong Guo, Yichen Wu, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun

Abstract: The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference, backed by native hardware support on NVIDIA Blackwell Tensor Cores. However, activation outliers pose a unique challenge under this format: a single outlier inflates the shared block scale, compressing the effective dyn… ▽ More The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference, backed by native hardware support on NVIDIA Blackwell Tensor Cores. However, activation outliers pose a unique challenge under this format: a single outlier inflates the shared block scale, compressing the effective dynamic range of the remaining elements and causing significant quantization error. Existing rotation-based remedies, including randomized Hadamard and learnable rotations, are data-agnostic and therefore unable to specifically target the channels where outliers concentrate. We propose DuQuant++, which adapts the outlier-aware fine-grained rotation of DuQuant to the MXFP4 format by aligning the rotation block size with the microscaling group size (B{=}32). Because each MXFP4 group possesses an independent scaling factor, the cross-block variance issue that necessitates dual rotations and a zigzag permutation in the original DuQuant becomes irrelevant, enabling DuQuant++ to replace the entire pipeline with a single outlier-aware rotation, which halves the online rotation cost while simultaneously smoothing the weight distribution. Extensive experiments on the LLaMA-3 family under MXFP4 W4A4 quantization show that DuQuant++ consistently achieves state-of-the-art performance. Our code is available at https://github.com/Hsu1023/DuQuant-v2. △ Less

Submitted 21 April, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Comments: Technical Report

Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classification

Authors: Meijia Wang, Guochao Wang, Haozhen Chu, Bin Yao, Weichuan Zhang, Yuan Wang, Junpo Yang

Abstract: Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency backgr… ▽ More Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain features. Confined to this single perspective, models inevitably suffer from inherent texture biases, entangling essential structural details with high-frequency background noise. Furthermore, lacking cross-view geometric constraints, single-view metrics tend to overfit this noise, resulting in structural instability under few-shot conditions. To address these issues, this paper proposes the Frequency-Enhanced Dual-Subspace Network (FEDSNet). Specifically, FEDSNet utilizes the Discrete Cosine Transform (DCT) and a low-pass filtering mechanism to explicitly isolate low-frequency global structural components from spatial features, thereby suppressing background interference. Truncated Singular Value Decomposition (SVD) is employed to construct independent, low-rank linear subspaces for both spatial texture and frequency structural features. An adaptive gating mechanism is designed to dynamically fuse the projection distances from these dual views. This strategy leverages the structural stability of the frequency subspace to prevent the spatial subspace from overfitting to background features. Extensive experiments on four benchmark datasets - CUB-200-2011, Stanford Cars, Stanford Dogs, and FGVC-Aircraft - demonstrate that FEDSNet exhibits excellent classification performance and robustness, achieving highly competitive results compared to existing metric learning algorithms. Complexity analysis further confirms that the proposed network achieves a favorable balance between high accuracy and computational efficiency, providing an effective new paradigm for few-shot fine-grained visual recognition. △ Less

Submitted 16 April, 2026; originally announced April 2026.

The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview

Authors: Zheng Chen, Kai Liu, Jingkai Wang, Xianglong Yan, Jianze Li, Ziqing Zhang, Jue Gong, Jiatong Li, Lei Sun, Xiaoyang Liu, Radu Timofte, Yulun Zhang, Jihye Park, Yoonjin Im, Hyungju Chun, Hyunhee Park, MinKyu Park, Zheng Xie, Xiangyu Kong, Weijun Yuan, Zhan Li, Qiurong Song, Luen Zhu, Fengkai Zhang, Xinzhe Zhu , et al. (128 additional authors not shown)

Abstract: This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze… ▽ More This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution. △ Less

Submitted 15 April, 2026; originally announced April 2026.

Comments: NTIRE 2026 webpage: https://cvlai.net/ntire/2026. Code: https://github.com/zhengchen1999/NTIRE2026_ImageSR_x4

Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction

Authors: Jiahao Shao, Anam Nawaz Khan, Christopher Brett, Tom Berg, Xueping Li, Bing Yao

Abstract: Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large Language Models (LLMs) offer semantic reasoning, their deployment is often limited by high computational costs and hallucination risks. This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-M… ▽ More Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large Language Models (LLMs) offer semantic reasoning, their deployment is often limited by high computational costs and hallucination risks. This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-Metastasis (TNM) staging, histologic grade, and biomarkers. We fine-tune a Llama-3-8B-Instruct encoder using Low-Rank Adaptation (LoRA) on a curated, expert-verified dataset of 10,677 reports. Unlike generative approaches, our architecture utilizes parallel classification heads to enforce consistent schema adherence. Experimental results demonstrate that the model achieves a Macro F1 score of 0.976, successfully resolving complex contextual ambiguities and heterogeneous reporting formats that challenge traditional extraction methods including rule-based natural language processing (NLP) pipelines, zero-shot LLMs, and single-task LLM baselines. The proposed adapter-efficient, multi-task architecture enables reliable, scalable pathology-derived cancer staging and biomarker profiling, with the potential to enhance clinical decision support and accelerate data-driven oncology research. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Comments: 11 pages, 3 figures and 4 tables in the main manuscript. Additional content, figures and tables are in supplementary material section. 17 pages in total

Dual-Branch Remote Sensing Infrared Image Super-Resolution

Authors: Xining Ge, Gengjia Chang, Weijun Yuan, Zhan Li, Zhanglu Chen, Boyang Yao, Yihang Chen, Yifan Deng, Shuhong Liu

Abstract: Remote sensing infrared image super-resolution aims to recover sharper thermal observations from low-resolution inputs while preserving target contours, scene layout, and radiometric stability. Unlike visible-image super-resolution, thermal imagery is weakly textured and more sensitive to unstable local sharpening, which makes complementary local and global modeling especially important. This pape… ▽ More Remote sensing infrared image super-resolution aims to recover sharper thermal observations from low-resolution inputs while preserving target contours, scene layout, and radiometric stability. Unlike visible-image super-resolution, thermal imagery is weakly textured and more sensitive to unstable local sharpening, which makes complementary local and global modeling especially important. This paper presents our solution to the NTIRE 2026 Infrared Image Super-Resolution Challenge, a dual-branch system that combines a HAT-L branch and a MambaIRv2-L branch. The inference pipeline applies test-time local conversion on HAT, eight-way self-ensemble on MambaIRv2, and fixed equal-weight image-space fusion. We report both the official challenge score and a reproducible evaluation on 12 synthetic times-four thermal samples derived from Caltech Aerial RGB-Thermal, on which the fused output outperforms either single branch in PSNR, SSIM, and the overall Score. The results suggest that infrared super-resolution benefits from explicit complementarity between locally strong transformer restoration and globally stable state-space modeling. △ Less

Submitted 27 April, 2026; v1 submitted 11 April, 2026; originally announced April 2026.

PA-SFM: Tracker-free differentiable acoustic radiation for freehand 3D photoacoustic imaging

Authors: Shuang Li, Jian Gao, Chulhong Kim, Seongwook Choi, Qian Chen, Yibing Wang, Shuang Wu, Yu Zhang, Tingting Huang, Yucheng Zhou, Boxin Yao, Yao Yao, Changhui Li

Abstract: Three-dimensional (3D) handheld photoacoustic tomography typically relies on bulky and expensive external positioning sensors to correct motion artifacts, which severely limits its clinical flexibility and accessibility. To address this challenge, we present PA-SFM, a tracker-free framework that leverages exclusively single-modality photoacoustic data for both sensor pose recovery and high-fidelit… ▽ More Three-dimensional (3D) handheld photoacoustic tomography typically relies on bulky and expensive external positioning sensors to correct motion artifacts, which severely limits its clinical flexibility and accessibility. To address this challenge, we present PA-SFM, a tracker-free framework that leverages exclusively single-modality photoacoustic data for both sensor pose recovery and high-fidelity 3D reconstruction via differentiable acoustic radiation modeling. Unlike traditional structure-from-motion (SFM) methods based on visual features, PA-SFM integrates the acoustic wave equation into a differentiable programming pipeline. By leveraging a high-performance, GPU-accelerated acoustic radiation kernel, the framework simultaneously optimizes the 3D photoacoustic source distribution and the sensor array pose via gradient descent. To ensure robust convergence in freehand scenarios, we introduce a coarse-to-fine optimization strategy that incorporates geometric consistency checks and rigid-body constraints to eliminate motion outliers. We validated the proposed method through both numerical simulations and in-vivo rat experiments. The results demonstrate that PA-SFM achieves sub-millimeter positioning accuracy and restores high-resolution 3D vascular structures comparable to ground-truth benchmarks, offering a low-cost, software-defined solution for clinical freehand photoacoustic imaging. The source code is publicly available at \href{https://github.com/JaegerCQ/PA-SFM}{https://github.com/JaegerCQ/PA-SFM}. △ Less

Submitted 23 March, 2026; originally announced April 2026.

RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs

Authors: Liang Yao, Shengxiang Xu, Fan Liu, Chuanyi Zhang, Bishun Yao, Rui Min, Yongjun Li, Chaoqian Ouyang, Shimin Di, Min-Ling Zhang

Abstract: Earth Observation (EO) systems are essentially designed to support domain experts who often express their requirements through vague natural language rather than precise, machine-friendly instructions. Depending on the specific application scenario, these vague queries can demand vastly different levels of visual precision. Consequently, a practical EO AI system must bridge the gap between ambiguo… ▽ More Earth Observation (EO) systems are essentially designed to support domain experts who often express their requirements through vague natural language rather than precise, machine-friendly instructions. Depending on the specific application scenario, these vague queries can demand vastly different levels of visual precision. Consequently, a practical EO AI system must bridge the gap between ambiguous human queries and the appropriate multi-granularity visual analysis tasks, ranging from holistic image interpretation to fine-grained pixel-wise predictions. While Multi-modal Large Language Models (MLLMs) demonstrate strong semantic understanding, their text-based output format is inherently ill-suited for dense, precision-critical spatial predictions. Existing agentic frameworks address this limitation by delegating tasks to external tools, but indiscriminate tool invocation is computationally inefficient and underutilizes the MLLM's native capabilities. To this end, we propose RemoteAgent, an agentic framework that strategically respects the intrinsic capability boundaries of MLLMs. To empower this framework to understand real user intents, we construct VagueEO, a human-centric instruction dataset pairing EO tasks with simulated vague natural-language queries. By leveraging VagueEO for reinforcement fine-tuning, we align an MLLM into a robust cognitive core that directly resolves image- and sparse region-level tasks. Consequently, RemoteAgent processes suitable tasks internally while intelligently orchestrating specialized tools via the Model Context Protocol exclusively for dense predictions. Extensive experiments demonstrate that RemoteAgent achieves robust intent recognition capabilities while delivering highly competitive performance across diverse EO tasks. △ Less

Submitted 12 April, 2026; v1 submitted 8 April, 2026; originally announced April 2026.

PA3: Policy-Aware Agent Alignment through Chain-of-Thought

Authors: Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya

Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "… ▽ More Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "needle-in-the-haystack" problem. To address these challenges, we propose a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context. Furthermore, we introduce a novel PolicyRecall reward based on the Jaccard score and a Hallucination Penalty for GRPO training. Altogether, our best model outperforms the baseline by 16 points and surpasses comparable in-context baselines of similar model size by 3 points, while using 40% fewer words. △ Less

Submitted 21 March, 2026; v1 submitted 15 March, 2026; originally announced March 2026.

SettleFL: Trustless and Scalable Reward Settlement Protocol for Federated Learning on Permissionless Blockchains (Extended version)

Authors: Shuang Liang, Yang Hua, Linshan Jiang, Peishen Yan, Tao Song, Bin Yao, Haibing Guan

Abstract: In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-ch… ▽ More In open Federated Learning (FL) environments where no central authority exists, ensuring collaboration fairness relies on decentralized reward settlement, yet the prohibitive cost of permissionless blockchains directly clashes with the high-frequency, iterative nature of model training. Existing solutions either compromise decentralization or suffer from scalability bottlenecks due to linear on-chain costs. To address this, we present SettleFL, a trustless and scalable reward settlement protocol designed to minimize total economic friction by offering a family of two interoperable protocols. Leveraging a shared domain-specific circuit architecture, SettleFL offers two interoperable strategies: (1) a Commit-and-Challenge variant that minimizes on-chain costs via optimistic execution and dispute-driven arbitration, and (2) a Commit-with-Proof variant that guarantees instant finality through per-round validity proofs. This design allows the protocol to flexibly adapt to varying latency and cost constraints while enforcing rational robustness without trusted coordination. We conduct extensive experiments combining real FL workloads and controlled simulations. Results show that SettleFL remains practical when scaling to 800 participants, achieving substantially lower gas cost. △ Less

Submitted 26 February, 2026; originally announced February 2026.

Positive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation

Authors: Bret Nestor, Bohan Yao, Jasmine Moore, Jasper Kanes

Abstract: This work presents the largest curation of Southern Resident Killer Whale (SRKW) acoustic data to date, also containing other marine mammals in their environment. We systematically search all available public archival hydrophone data within the SRKW habitat (over 30 years of audio data). The search consists of a weakly-supervised, positive-unlabelled, active learning strategy to identify all insta… ▽ More This work presents the largest curation of Southern Resident Killer Whale (SRKW) acoustic data to date, also containing other marine mammals in their environment. We systematically search all available public archival hydrophone data within the SRKW habitat (over 30 years of audio data). The search consists of a weakly-supervised, positive-unlabelled, active learning strategy to identify all instances of marine mammals. The resulting transformer-based presence or absence classifiers outperform state-of-the-art classifiers on 3 of 4 expert-annotated datasets in terms of accuracy and energy efficiency. The fleet of WHISPER detection models range from 0.58 (0.48-0.67) AUROC with WHISPER-tiny to 0.77 (0.63-0.93) with WHISPER-large-v3. Our multiclass species classifier obtains a top-1 accuracy of 53.2\% (11 train classes, 4 test classes) and our ecotype classifier obtains a top-1 accuracy of 33.6\% (4 train classes, 5 test classes) on the DCLDE-2026 dataset. We yield 919 hours of SRKW data, 230 hours of Bigg's orca data, 1374 hours of orca data from unlabelled ecotypes, 1501 hours of humpback data, 88 hours of sea lion data, 246 hours of pacific white-sided dolphin data, and over 784 hours of unspecified marine mammal data. This SRKW dataset is larger than DCLDE-2026, Ocean Networks Canada, and OrcaSound combined. The curated species labels are available under CC-BY 4.0 license, and the corresponding audio data are available under the licenses of the original owners. The comprehensive nature of this dataset makes it suitable for unsupervised machine translation, habitat usage surveys, and conservation endeavours for this critically endangered ecotype. △ Less

Submitted 13 April, 2026; v1 submitted 9 February, 2026; originally announced February 2026.

From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents

Authors: Bingsheng Yao, Chaoran Chen, April Yi Wang, Sherry Tongshuang Wu, Toby Jia-jun Li, Dakuo Wang

Abstract: The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a "tool" to become genuine collaborators with humans, thereby realizing a novel human-agent collaboration paradigm. Our vision is that LLM agents should resemble remote human collaborators, which allows HCI researchers to ground the future exploration in decades of re… ▽ More The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a "tool" to become genuine collaborators with humans, thereby realizing a novel human-agent collaboration paradigm. Our vision is that LLM agents should resemble remote human collaborators, which allows HCI researchers to ground the future exploration in decades of research on trust, awareness, and common ground in remote human collaboration, while also revealing the unique opportunities and challenges that emerge when one or more partners are AI agents. This workshop establishes a foundational research agenda for the new era by posing the question: How can the rich understanding of remote human collaboration inspire and inform the design and study of human-agent collaboration? We will bring together an interdisciplinary group from HCI, CSCW, and AI to explore this critical transition. The 180-minute workshop will be highly interactive, featuring a keynote speaker, a series of invited lightning talks, and an exploratory group design session where participants will storyboard novel paradigms of human-agent partnership. Our goal is to enlighten the research community by cultivating a shared vocabulary and producing a research agenda that charts the future of collaborative agents. △ Less

Submitted 5 February, 2026; originally announced February 2026.

A Multi-View Consistency Framework with Semi-Supervised Domain Adaptation

Authors: Yuting Hong, Li Dong, Xiaojie Qiu, Hui Xiao, Baochen Yao, Siming Zheng, Chengbin Peng

Abstract: Semi-Supervised Domain Adaptation (SSDA) leverages knowledge from a fully labeled source domain to classify data in a partially labeled target domain. Due to the limited number of labeled samples in the target domain, there can be intrinsic similarity of classes in the feature space, which may result in biased predictions, even when the model is trained on a balanced dataset. To overcome this limi… ▽ More Semi-Supervised Domain Adaptation (SSDA) leverages knowledge from a fully labeled source domain to classify data in a partially labeled target domain. Due to the limited number of labeled samples in the target domain, there can be intrinsic similarity of classes in the feature space, which may result in biased predictions, even when the model is trained on a balanced dataset. To overcome this limitation, we introduce a multi-view consistency framework, which includes two views for training strongly augmented data. One is a debiasing strategy for correcting class-wise prediction probabilities according to the prediction performance of the model. The other involves leveraging pseudo-negative labels derived from the model predictions. Furthermore, we introduce a cross-domain affinity learning aimed at aligning features of the same class across different domains, thereby enhancing overall performance. Experimental results demonstrate that our method outperforms the competing methods on two standard domain adaptation datasets, DomainNet and Office-Home. Combining unsupervised domain adaptation and semi-supervised learning offers indispensable contributions to the industrial sector by enhancing model adaptability, reducing annotation costs, and improving performance. △ Less

Submitted 27 January, 2026; originally announced January 2026.

Comments: 11 pages, 7 figures

SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages

Authors: Tianyi Xu, Xuan Ouyang, Binwei Yao, Shoua Xiong, Sara Misurelli, Maichou Lor, Junjie Hu

Abstract: Tonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different lexical meanings. To address this, we propose SITA, a lightweight adaptation recipe that enforces Speaker-Invariance and Tone-Awareness for pretrained wav2vec-styl… ▽ More Tonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different lexical meanings. To address this, we propose SITA, a lightweight adaptation recipe that enforces Speaker-Invariance and Tone-Awareness for pretrained wav2vec-style encoders. SITA uses staged multi-objective training: (i) a cross-gender contrastive objective encourages lexical consistency across speakers, while a tone-repulsive loss prevents tone collapse by explicitly separating same-word different-tone realizations; and (ii) an auxiliary Connectionist Temporal Classification (CTC)-based ASR objective with distillation stabilizes recognition-relevant structure. We evaluate primarily on Hmong, a highly tonal and severely under-resourced language where off-the-shelf multilingual encoders fail to represent tone effectively. On a curated Hmong word corpus, SITA improves cross-gender lexical retrieval accuracy, while maintaining usable ASR accuracy relative to an ASR-adapted XLS-R teacher. We further observe similar gains when transferring the same recipe to Mandarin, suggesting SITA is a general, plug-in approach for adapting multilingual speech encoders to tonal languages. △ Less

Submitted 13 January, 2026; originally announced January 2026.

Comments: 8 pages (excluding references, limitations, ethics, acknowledgement, and appendix); 4 figures in the main paper; appendix included

ACM Class: I.2.7

How Do Large Language Models Learn Concepts During Continual Pre-Training?

Authors: Barry Menglong Yao, Sha Li, Yunzhi Yao, Minqian Liu, Zaishuo Xia, Qifan Wang, Lifu Huang

Abstract: Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large language models (LLMs) acquire, retain, and forget such concepts during continual pretraining remains poorly understood. In this work, we study how individual concepts are acquired and forgotten, as well as how multiple con… ▽ More Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large language models (LLMs) acquire, retain, and forget such concepts during continual pretraining remains poorly understood. In this work, we study how individual concepts are acquired and forgotten, as well as how multiple concepts interact through interference and synergy. We link these behavioral dynamics to LLMs' internal concept circuits, computational subgraphs associated with specific concepts, and incorporate graph metrics to characterize circuit topology. Our analysis reveals: (1) LLMs concept circuits provide a non-trivial, consistent signal of concept learning and forgetting; (2) concept circuits exhibit a stage-wise temporal pattern during continual pretraining, with an early increase followed by gradual decrease and stabilization; (3) concepts with larger learning gains tend to exhibit greater forgetting under subsequent training; (4) semantically similar concepts induce stronger interference than weakly related ones; (5) conceptual knowledge differs in their transferability, with some significantly facilitating the learning of others. Together, our findings provide a circuit-level view of concept learning dynamics and motivate concept-aware training strategies, such as Circuit-aware Experience Replay, which uses circuit topology to prioritize concepts vulnerable to forgetting. △ Less

Submitted 17 August, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

Comments: 19 pages, 27 figures

Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity

Authors: Doyoung Kim, Zhiwei Ren, Jie Hao, Zhongkai Sun, Lichao Wang, Xiyao Ma, Zack Ye, Xu Han, Jun Yin, Heng Ji, Wei Shen, Xing Fan, Benjamin Yao, Chenlei Guo

Abstract: We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that assumes an idealized API system and disregards real-world factors such as noisy API outputs, WildAGTEval accounts for two dimensions of real-world complexity: 1. API specification, which includes detailed documentation an… ▽ More We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that assumes an idealized API system and disregards real-world factors such as noisy API outputs, WildAGTEval accounts for two dimensions of real-world complexity: 1. API specification, which includes detailed documentation and usage constraints, and 2. API execution, which captures runtime challenges. Consequently, WildAGTEval offers (i) an API system encompassing 60 distinct complexity scenarios that can be composed into approximately 32K test configurations, and (ii) user-agent interactions for evaluating LLM agents on these scenarios. Using WildAGTEval, we systematically assess several advanced LLMs and observe that most scenarios are challenging, with irrelevant information complexity posing the greatest difficulty and reducing the performance of strong LLMs by 27.3%. Furthermore, our qualitative analysis reveals that LLMs occasionally distort user intent merely to claim task completion, critically affecting user satisfaction. △ Less

Submitted 1 January, 2026; originally announced January 2026.

Comments: 26 pages

LMG Index: A Robust and Efficient Learned Index Framework for Multi-Dimensional Performance Balance

Authors: Yuzhen Chen, Bin Yao

Abstract: Index structures are fundamental for efficient query processing on large-scale datasets. Learned indexes model the indexing process as a prediction problem to overcome the inherent trade-offs of traditional indexes. However, most existing learned indexes optimize only for limited objectives like query latency or space usage, neglecting other practical evaluation dimensions such as update efficienc… ▽ More Index structures are fundamental for efficient query processing on large-scale datasets. Learned indexes model the indexing process as a prediction problem to overcome the inherent trade-offs of traditional indexes. However, most existing learned indexes optimize only for limited objectives like query latency or space usage, neglecting other practical evaluation dimensions such as update efficiency and stability. Moreover, many learned indexes rely on assumptions about data distributions or workloads, lacking theoretical guarantees when facing unknown or evolving scenarios, which limits their generality in real-world systems. In this paper, we propose LMG, a robust and efficient learned index framework designed for multi-dimensional performance balance. LMG integrates a decoupled routing structure with theoretical $O(1)$ complexity for fixed key types and an optimal error threshold training algorithm that approaches $O(1)$ overhead in practice. Furthermore, the framework enhances query performance by optimizing gap allocation. Extensive evaluations show that our framework achieves competitive or leading performance across all key evaluation dimensions, including bulk loading (up to 7.55$\times$ faster), point queries (up to 1.68$\times$ faster), range queries (up to 11.41$\times$ faster), and mixed read-write throughput (up to 3.50$\times$ faster). Furthermore, LMG ensures robust long-term stability and high space efficiency (up to 6.26$\times$ smaller footprint). These results demonstrate that LMG significantly mitigates the multi-dimensional performance trade-offs often observed in state-of-the-art approaches, offering a balanced and efficient framework. △ Less

Submitted 29 March, 2026; v1 submitted 31 December, 2025; originally announced December 2025.

Derivative-Informed Fourier Neural Operator: Universal Approximation and Applications to PDE-Constrained Optimization

Authors: Boyuan Yao, Dingcheng Luo, Lianghao Cao, Nikola Kovachki, Thomas O'Leary-Roseberry, Omar Ghattas

Abstract: We present approximation theories and efficient training methods for derivative-informed Fourier neural operators (DIFNOs) with applications to PDE-constrained optimization. A DIFNO is an FNO trained by minimizing its prediction error jointly on output and Fréchet derivative samples of a high-fidelity operator (e.g., a parametric PDE solution operator). As a result, a DIFNO can closely emulate not… ▽ More We present approximation theories and efficient training methods for derivative-informed Fourier neural operators (DIFNOs) with applications to PDE-constrained optimization. A DIFNO is an FNO trained by minimizing its prediction error jointly on output and Fréchet derivative samples of a high-fidelity operator (e.g., a parametric PDE solution operator). As a result, a DIFNO can closely emulate not only the high-fidelity operator's response but also its sensitivities. To motivate the use of DIFNOs instead of conventional FNOs as surrogate models, we show that accurate surrogate-driven PDE-constrained optimization requires accurate surrogate Fréchet derivatives. Then, we establish (i) simultaneous universal approximation of continuously differentiable operators and their Fréchet derivatives by FNOs on compact sets, and (ii) universal approximation of continuously differentiable operators by FNOs in weighted Sobolev spaces with input measures that have unbounded supports. Our theoretical results certify the capability of FNOs for accurate derivative-informed operator learning and for the solution of PDE-constrained optimization problems. Furthermore, we develop efficient training schemes that leverage dimensionality reduction and multi-resolution techniques to significantly reduce memory and computational costs in Fréchet derivative learning. Numerical examples on nonlinear diffusion--reaction, Helmholtz, and Navier--Stokes equations demonstrate that DIFNOs are superior in sample complexity for operator learning and solving infinite-dimensional PDE-constrained inverse problems, achieving high accuracy at low training sample sizes. △ Less

Submitted 15 March, 2026; v1 submitted 15 December, 2025; originally announced December 2025.

MSC Class: 41A65; 68T07 (Primary) 65K10; 65J22 (Secondary)

Has ACL Lost Its Crown? A Decade-Long Quantitative Analysis of Scale and Impact Across Leading AI Conferences

Authors: Jianglin Ma, Ben Yao, Xiang Li, Yazhou Zhang

Abstract: The recent surge of language models (LMs) has rapidly expanded NLP/AI research, driving an exponential rise in submissions and acceptances at major conferences. Yet this growth has been shadowed by escalating concerns over conference quality, such as plagiarism, reviewer inexperience, and collusive bidding. However, existing studies rely largely on qualitative accounts, for example expert intervie… ▽ More The recent surge of language models (LMs) has rapidly expanded NLP/AI research, driving an exponential rise in submissions and acceptances at major conferences. Yet this growth has been shadowed by escalating concerns over conference quality, such as plagiarism, reviewer inexperience, and collusive bidding. However, existing studies rely largely on qualitative accounts, for example expert interviews and social media discussions, lacking longitudinal empirical evidence. To fill this gap, we conduct a ten-year empirical study (2014-2024) spanning seven leading conferences. We build a four-dimensional bibliometric framework covering conference scale, core citation statistics, impact dispersion, and cross-venue and journal influence. Notably, we further propose a metric called Quality-Quantity Elasticity (QQE), which measures the elasticity of citation growth relative to acceptance growth. We highlight two key findings. First, conference expansion does not lead to proportional growth in scholarly impact, as QQE consistently declines over time across all venues. Second, ACL has not lost its crown, continuing to outperform other NLP conferences in median citations, milestone contributions, and citation coverage. This study provides the first decade-long, cross-venue empirical evidence on the evolution of major NLP/AI conferences. Our code is available at https://anonymous.4open.science/r/acl-crown-analysis-38D5. △ Less

Submitted 10 August, 2026; v1 submitted 3 December, 2025; originally announced December 2025.

Comments: The authors have identified substantive issues in the current version that require substantial revisions to the analysis and interpretation. We are therefore withdrawing this version to avoid potential misunderstanding or inappropriate citation of its current findings

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Authors: Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai, You Li, Smit Vasani, Binwei Yao, Michael Henry Tessler, Sijia Yang, Dhavan Shah, Robert Hawkins, Junjie Hu, Timothy T. Rogers

Abstract: Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real… ▽ More Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a large-scale benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels and supporting future individual-level analyses. We instantiate "digital twin" RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. On the held-out group split, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves auxiliary stance alignment and reduces group-level convergence error, though discrepancies in opinion change and belief updating remain. DEBATE enables rigorous benchmarking of simulated opinion dynamics and supports future research on aligning multi-agent RPLAs with realistic human interactions. △ Less

Submitted 28 May, 2026; v1 submitted 28 October, 2025; originally announced October 2025.

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans

Authors: Bingsheng Yao, Bo Sun, Yuanzhe Dong, Yuxuan Lu, Dakuo Wang

Abstract: The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework… ▽ More The emerging large language model role-playing agents (LLM RPAs) aim to simulate individual human behaviors, but the persona fidelity is often undermined by manually-created profiles (e.g., cherry-picked information and personality characteristics) without validating the alignment with the target individuals. To address this limitation, our work introduces the Dynamic Persona Refinement Framework (DPRF). DPRF aims to optimize the alignment of LLM RPAs' behaviors with those of target individuals by iteratively identifying the cognitive divergence, either through free-form or theory-grounded, structured analysis, between generated behaviors and human ground truth, and refining the persona profile to mitigate these divergences. We evaluate DPRF with five LLMs on four diverse behavior-prediction scenarios: formal debates, social media posts with mental health issues, public interviews, and movie reviews. DPRF can consistently improve behavioral alignment considerably over baseline personas and generalizes across models and scenarios. Our work provides a robust methodology for creating high-fidelity persona profiles and enhancing the validity of downstream applications, such as user simulation, social studies, and personalized AI. △ Less

Submitted 28 October, 2025; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: In Submission

Physics-augmented Multi-task Gaussian Process for Modeling Spatiotemporal Dynamics

Authors: Xizhuo Zhang, Bing Yao

Abstract: Recent advances in sensing and imaging technologies have enabled the collection of high-dimensional spatiotemporal data across complex geometric domains. However, effective modeling of such data remains challenging due to irregular spatial structures, rapid temporal dynamics, and the need to jointly predict multiple interrelated physical variables. This paper presents a physics-augmented multi-tas… ▽ More Recent advances in sensing and imaging technologies have enabled the collection of high-dimensional spatiotemporal data across complex geometric domains. However, effective modeling of such data remains challenging due to irregular spatial structures, rapid temporal dynamics, and the need to jointly predict multiple interrelated physical variables. This paper presents a physics-augmented multi-task Gaussian Process (P-M-GP) framework tailored for spatiotemporal dynamic systems. Specifically, we develop a geometry-aware, multi-task Gaussian Process (M-GP) model to effectively capture intrinsic spatiotemporal structure and inter-task dependencies. To further enhance the model fidelity and robustness, we incorporate governing physical laws through a physics-based regularization scheme, thereby constraining predictions to be consistent with governing dynamical principles. We validate the proposed P-M-GP framework on a 3D cardiac electrodynamics modeling task. Numerical experiments demonstrate that our method significantly improves prediction accuracy over existing methods by effectively incorporating domain-specific physical constraints and geometric prior. △ Less

Submitted 15 October, 2025; originally announced October 2025.

Comments: 13 pages, 5 figures

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems

Authors: Bohan Yao, Shiva Krishna Reddy Malay, Vikas Yadav

Abstract: Large Language Model (LLM)-powered Multi-agent systems (MAS) have achieved state-of-the-art results on various complex reasoning tasks. Recent works have proposed techniques to automate the design of MASes, eliminating the need for manual engineering. However, these techniques perform poorly, often achieving similar or inferior performance to simple baselines. Furthermore, they require computation… ▽ More Large Language Model (LLM)-powered Multi-agent systems (MAS) have achieved state-of-the-art results on various complex reasoning tasks. Recent works have proposed techniques to automate the design of MASes, eliminating the need for manual engineering. However, these techniques perform poorly, often achieving similar or inferior performance to simple baselines. Furthermore, they require computationally expensive re-discovery of architectures for each new task domain and expensive data annotation on domains without existing labeled validation sets. A critical insight is that simple Chain of Thought (CoT) reasoning often performs competitively with these complex systems, suggesting that the fundamental reasoning unit of MASes, CoT, warrants further investigation. To this end, we present a new paradigm for automatic MAS design that pivots the focus to optimizing CoT reasoning. We introduce the Agentic Reasoning Module (ARM), an agentic generalization of CoT where each granular reasoning step is executed by a specialized reasoning module. This module is discovered through a tree search over the code space, starting from a simple CoT module and evolved using mutations informed by reflection on execution traces. The resulting ARM acts as a versatile reasoning building block which can be utilized as a direct recursive loop or as a subroutine in a learned meta-orchestrator. Our approach significantly outperforms both manually designed MASes and state-of-the-art automatic MAS design methods. Crucially, MASes built with ARM exhibit superb generalization, maintaining high performance across different foundation models and task domains without further optimization. △ Less

Submitted 19 May, 2026; v1 submitted 7 October, 2025; originally announced October 2025.

Comments: 29 pages, 2 figures

Exploring Collaboration Breakdowns Between Provider Teams and Patients in Post-Surgery Care

Authors: Bingsheng Yao, Menglin Zhao, Zhan Zhang, Pengqi Wang, Emma G Chester, Changchang Yin, Tianshi Li, Varun Mishra, Lace Padilla, Odysseas Chatzipanagiotou, Timothy Pawlik, Ping Zhang, Weidan Cao, Dakuo Wang

Abstract: Post-surgery care involves ongoing collaboration between provider teams and patients, which starts from post-surgery hospitalization through home recovery after discharge. While prior HCI research has primarily examined patients' challenges at home, less is known about how provider teams coordinate discharge preparation and care handoffs, and how breakdowns in communication and care pathways may a… ▽ More Post-surgery care involves ongoing collaboration between provider teams and patients, which starts from post-surgery hospitalization through home recovery after discharge. While prior HCI research has primarily examined patients' challenges at home, less is known about how provider teams coordinate discharge preparation and care handoffs, and how breakdowns in communication and care pathways may affect patient recovery. To investigate this gap, we conducted semi-structured interviews with 13 healthcare providers and 4 patients in the context of gastrointestinal (GI) surgery. We found coordination boundaries between in- and out-patient teams, coupled with complex organizational structures within teams, impeded the "invisible work" of preparing patients' home care plans and triaging patient information. For patients, these breakdowns resulted in inadequate preparation for home transition and fragmented self-collected data, both of which undermine timely clinical decision-making. Based on these findings, we outline design opportunities to formalize task ownership and handoffs, contextualize co-temporal signals, and align care plans with home resources. △ Less

Submitted 16 February, 2026; v1 submitted 27 September, 2025; originally announced September 2025.

Comments: Accepted at CHI 2026

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate

Authors: Binwei Yao, Chao Shang, Wanyu Du, Jianfeng He, Ruixue Lian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi

Abstract: Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to refine arguments and foster innovative thinking. LLMs' inherent sycophancy can collapse debates into premature consensus, potentially undermining the benefits of multi-agent debate… ▽ More Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS) that rely on productive disagreement to refine arguments and foster innovative thinking. LLMs' inherent sycophancy can collapse debates into premature consensus, potentially undermining the benefits of multi-agent debate. While prior studies focus on user--LLM sycophancy, the impact of inter-agent sycophancy in debate remains poorly understood. To address this gap, we introduce the first operational framework that (1) proposes a formal definition of sycophancy specific to MADS settings, (2) develops new metrics to evaluate the agent sycophancy level and its impact on information exchange in MADS, and (3) systematically investigates how varying levels of sycophancy across agent roles (debaters and judges) affects outcomes in both decentralized and centralized debate frameworks. Our findings reveal that sycophancy is a core failure mode that amplifies disagreement collapse before reaching a correct conclusion in multi-agent debates, yields lower accuracy than single-agent baselines, and arises from distinct debater-driven and judge-driven failure modes. Building on these findings, we propose actionable design principles for MADS, effectively balancing productive disagreement with cooperation in agent interactions. △ Less

Submitted 26 September, 2025; originally announced September 2025.

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?

Authors: Lu Sun, Shihan Fu, Bingsheng Yao, Yuxuan Lu, Wenbo Li, Hansu Gu, Jiri Gesi, Jing Huang, Chen Luo, Dakuo Wang

Abstract: Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific cus… ▽ More Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human participants to shop with Amazon Rufus, collected their personas, interaction traces, and UX feedback, and then created digital twins to repeat the task. Pairwise comparison of human and digital-twin traces shows that while agents often explored more diverse choices, their action patterns aligned with humans and yielded similar design feedback. This study is the first to quantify how closely LLM agents can mirror human multi-turn interaction with an agentic AI system, highlighting their potential for scalable evaluation. △ Less

Submitted 25 September, 2025; originally announced September 2025.

Through the Lens of Human-Human Collaboration: A Configurable Research Platform for Exploring Human-Agent Collaboration

Authors: Bingsheng Yao, Jiaju Chen, Chaoran Chen, April Wang, Toby Jia-jun Li, Dakuo Wang

Abstract: Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles o… ▽ More Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles of computer-mediated collaboration established in HCI and CSCW persist, change, or fail when humans collaborate with LLM agents. To support systematic investigations of these questions, we introduce an open and configurable research platform for HCI researchers. The platform's modular design allows seamless adaptation of classic CSCW experiments and manipulation of theory-grounded interaction controls. We demonstrate the platform's research efficacy and usability through three case studies: (1) two Shape Factory experiments for resource negotiation with 16 participants, (2) one Hidden Profile experiment for information pooling with 16 participants, and (3) a participatory cognitive walkthrough with five HCI researchers to refine workflows of researcher interface for experiment setup and analysis. △ Less

Submitted 15 February, 2026; v1 submitted 22 September, 2025; originally announced September 2025.

Comments: Accepted at CHI 2026

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight

Authors: Jingyu Tang, Chaoran Chen, Jiawen Li, Zhiping Zhang, Bingcan Guo, Ibrahim Khalilov, Simret Araya Gebreegziabher, Bingsheng Yao, Dakuo Wang, Yanfang Ye, Tianshi Li, Ziang Xiao, Yaxing Yao, Toby Jia-Jun Li

Abstract: The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents,… ▽ More The dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight. △ Less

Submitted 12 September, 2025; originally announced September 2025.

VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results

Authors: Sizhuo Ma, Wei-Ting Chen, Qiang Gao, Jian Wang, Chris Wei Zhou, Wei Sun, Weixia Zhang, Linhan Cao, Jun Jia, Xiangyang Zhu, Dandan Zhu, Xiongkuo Min, Guangtao Zhai, Baoying Chen, Xiongwei Xiao, Jishen Zeng, Wei Wu, Tiexuan Lou, Yuchen Tan, Chunyi Song, Zhiwei Xu, MohammadAli Hamidi, Hadi Amirpour, Mingyin Bai, Jiawang Du , et al. (34 additional authors not shown)

Abstract: Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created li… ▽ More Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches. △ Less

Submitted 25 August, 2025; originally announced August 2025.

Comments: ICCV 2025 VQualA workshop FIQA track

PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs

Authors: Hao Duan, Yitong Song, Bin Yao, Anqi Liang

Abstract: Approximate Nearest Neighbor Search (ANNS) plays a crucial role in many key areas. Proximity graphs (PGs) are the leading method for ANNS, offering the best balance between query efficiency and accuracy. However, their performance heavily depends on various construction and query parameters, which are difficult to optimize due to their complex inter-dependencies. Given that users often prioritize… ▽ More Approximate Nearest Neighbor Search (ANNS) plays a crucial role in many key areas. Proximity graphs (PGs) are the leading method for ANNS, offering the best balance between query efficiency and accuracy. However, their performance heavily depends on various construction and query parameters, which are difficult to optimize due to their complex inter-dependencies. Given that users often prioritize specific accuracy levels, efficiently identifying the optimal PG configurations to meet these targets is essential. Although some studies have explored automatic configuration tuning for PGs, they are limited by inefficiencies and suboptimal results. These issues stem from the need to construct numerous PGs for searching and re-tuning from scratch whenever the dataset changes, as well as the failure to capture the complex dependencies between configurations, query performance, and tuning objectives. To address these challenges, we propose PGTuner, an efficient framework for automatic PG configuration tuning leveraging pre-training knowledge and model transfer techniques. PGTuner improves efficiency through a pre-trained query performance prediction (QPP) model, eliminating the need to build multiple PGs. It also features a deep reinforcement learning-based parameter configuration recommendation (PCR) model to recommend optimal configurations for specific datasets and accuracy targets. Additionally, PGTuner incorporates out-of-distribution detection and deep active learning for efficient tuning in dynamic scenarios and transferring to new datasets. Extensive experiments demonstrate that PGTuner can stably achieve the top-level tuning effect across different datasets while significantly improving tuning efficiency by up to 14.69X, with a 14.64X boost in dynamic scenarios. The code and data for PGTuner are available online at https://github.com/hao-duan/PGTuner. △ Less

Submitted 25 August, 2025; originally announced August 2025.

TRIM: Accelerating High-Dimensional Vector Similarity Search with Enhanced Triangle-Inequality-Based Pruning

Authors: Yitong Song, Pengcheng Zhang, Chao Gao, Bin Yao, Kai Wang, Zongyuan Wu, Lin Qu

Abstract: High-dimensional vector similarity search (HVSS) is critical for many data processing and AI applications. However, traditional HVSS methods often require extensive data access for distance calculations, leading to inefficiencies. Triangle-inequality-based lower bound pruning is a widely used technique to reduce the number of data access in low-dimensional spaces but becomes less effective in high… ▽ More High-dimensional vector similarity search (HVSS) is critical for many data processing and AI applications. However, traditional HVSS methods often require extensive data access for distance calculations, leading to inefficiencies. Triangle-inequality-based lower bound pruning is a widely used technique to reduce the number of data access in low-dimensional spaces but becomes less effective in high-dimensional settings. This is attributed to the "distance concentration" phenomenon, where the lower bounds derived from the triangle inequality become too small to be useful. To address this, we propose TRIM, which enhances the effectiveness of traditional triangle-inequality-based pruning in high-dimensional vector similarity search using two key ways: (1) optimizing landmark vectors used to form the triangles, and (2) relaxing the lower bounds derived from the triangle inequality, with the relaxation degree adjustable according to user's needs. TRIM is a versatile operation that can be seamlessly integrated into both memory-based (e.g., HNSW, IVFPQ) and disk-based (e.g., DiskANN) HVSS methods, reducing distance calculations and disk access. Extensive experiments show that TRIM enhances memory-based methods, improving graph-based search by up to 90% and quantization-based search by up to 200%, while achieving a pruning ratio of up to 99%. It also reduces I/O costs by up to 58% and improves efficiency by 102% for disk-based methods, while preserving high query accuracy. △ Less

Submitted 25 August, 2025; originally announced August 2025.

ARSP: Automated Repair of Verilog Designs via Semantic Partitioning

Authors: Bingkun Yao, Ning Wang, Xiangfeng Liu, Yuxin Du, Yuchen Hu, Hong Gao, Zhe Jiang, Nan Guan

Abstract: Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds… ▽ More Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds of unrelated lines, diffusing the model's attention. To address this issue, we introduce ARSP, a two-stage system that mitigates dilution via semantics-guided fragmentation. A Partition LLM splits a module into semantically tight fragments; a Repair LLM patches each fragment; edits are merged without altering unrelated logic. A synthetic data framework generates fragment-level training pairs spanning bug types, design styles, and scales to supervise both models. Experiments show that ARSP achieves 77.92% pass@1 and 83.88% pass@5, outperforming mainstream commercial LLMs including Claude-3.7 and SOTA automated Verilog debugging tools Strider and MEIC. Also, semantic partitioning improves pass@1 by 11.6% and pass@5 by 10.2% over whole-module debugging, validating the effectiveness of fragment-level scope reduction in LLM-based Verilog debugging. △ Less

Submitted 22 August, 2025; originally announced August 2025.

SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis

Authors: Jiahao Xu, Changchang Yin, Odysseas Chatzipanagiotou, Diamantis Tsilimigras, Kevin Clear, Bingsheng Yao, Dakuo Wang, Timothy Pawlik, Ping Zhang

Abstract: Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs as… ▽ More Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Large Language Models for Subjective Language Understanding: A Survey

Authors: Changhao Song, Yazhou Zhang, Hui Gao, Ben Yao, Peng Zhang

Abstract: Subjective language understanding refers to a broad set of natural language processing tasks where the goal is to interpret or generate content that conveys personal feelings, opinions, or figurative meanings rather than objective facts. With the advent of large language models (LLMs) such as ChatGPT, LLaMA, and others, there has been a paradigm shift in how we approach these inherently nuanced ta… ▽ More Subjective language understanding refers to a broad set of natural language processing tasks where the goal is to interpret or generate content that conveys personal feelings, opinions, or figurative meanings rather than objective facts. With the advent of large language models (LLMs) such as ChatGPT, LLaMA, and others, there has been a paradigm shift in how we approach these inherently nuanced tasks. In this survey, we provide a comprehensive review of recent advances in applying LLMs to subjective language tasks, including sentiment analysis, emotion recognition, sarcasm detection, humor understanding, stance detection, metaphor interpretation, intent detection, and aesthetics assessment. We begin by clarifying the definition of subjective language from linguistic and cognitive perspectives, and we outline the unique challenges posed by subjective language (e.g. ambiguity, figurativeness, context dependence). We then survey the evolution of LLM architectures and techniques that particularly benefit subjectivity tasks, highlighting why LLMs are well-suited to model subtle human-like judgments. For each of the eight tasks, we summarize task definitions, key datasets, state-of-the-art LLM-based methods, and remaining challenges. We provide comparative insights, discussing commonalities and differences among tasks and how multi-task LLM approaches might yield unified models of subjectivity. Finally, we identify open issues such as data limitations, model bias, and ethical considerations, and suggest future research directions. We hope this survey will serve as a valuable resource for researchers and practitioners interested in the intersection of affective computing, figurative language processing, and large-scale language models. △ Less

Submitted 11 August, 2025; originally announced August 2025.

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation

Authors: Jiaju Chen, Yuxuan Lu, Xiaojie Wang, Huimin Zeng, Jing Huang, Jiri Gesi, Ying Xu, Bingsheng Yao, Dakuo Wang

Abstract: Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-… ▽ More Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods. △ Less

Submitted 28 July, 2025; originally announced July 2025.

MSC Class: 68T50

A Toolbox, Not a Hammer -- Multi-TAG: Scaling Math Reasoning with Multi-Tool Aggregation

Authors: Bohan Yao, Vikas Yadav

Abstract: Augmenting large language models (LLMs) with external tools is a promising avenue for developing high-performance mathematical reasoning systems. Prior tool-augmented approaches typically finetune an LLM to select and invoke a single tool at each reasoning step and show promising results on simpler math reasoning benchmarks such as GSM8K. However, these approaches struggle with more complex math p… ▽ More Augmenting large language models (LLMs) with external tools is a promising avenue for developing high-performance mathematical reasoning systems. Prior tool-augmented approaches typically finetune an LLM to select and invoke a single tool at each reasoning step and show promising results on simpler math reasoning benchmarks such as GSM8K. However, these approaches struggle with more complex math problems that require precise reasoning over multiple steps. To address this limitation, in this work, we propose Multi-TAG, a Multi-Tool AGgregation-based framework. Instead of relying on a single tool, Multi-TAG guides an LLM to concurrently invoke multiple tools at each reasoning step. It then aggregates their diverse outputs to verify and refine the reasoning process, enhancing solution robustness and accuracy. Notably, Multi-TAG is a finetuning-free, inference-only framework, making it readily applicable to any LLM backbone, including large open-weight models which are computationally expensive to finetune and proprietary frontier models which cannot be finetuned with custom recipes. We evaluate Multi-TAG on four challenging benchmarks: MATH500, AIME, AMC, and OlympiadBench. Across both open-weight and closed-source LLM backbones, Multi-TAG consistently and substantially outperforms state-of-the-art baselines, achieving average improvements of 6.0% to 7.5% over state-of-the-art baselines. △ Less

Submitted 21 August, 2025; v1 submitted 25 July, 2025; originally announced July 2025.

Comments: Published at EMNLP Findings 2025; 21 pages, 3 figures

Self-Wearing Adaptive Garments via Soft Robotic Unfurling

Authors: Nam Gyun Kim, William E. Heap, Yimeng Qin, Elvy B. Yao, Jee-Hwan Ryu, Allison M. Okamura

Abstract: Robotic dressing assistance has the potential to improve the quality of life for individuals with limited mobility. Existing solutions predominantly rely on rigid robotic manipulators, which have challenges in handling deformable garments and ensuring safe physical interaction with the human body. Prior robotic dressing methods require excessive operation times, complex control strategies, and con… ▽ More Robotic dressing assistance has the potential to improve the quality of life for individuals with limited mobility. Existing solutions predominantly rely on rigid robotic manipulators, which have challenges in handling deformable garments and ensuring safe physical interaction with the human body. Prior robotic dressing methods require excessive operation times, complex control strategies, and constrained user postures, limiting their practicality and adaptability. This paper proposes a novel soft robotic dressing system, the Self-Wearing Adaptive Garment (SWAG), which uses an unfurling and growth mechanism to facilitate autonomous dressing. Unlike traditional approaches,the SWAG conforms to the human body through an unfurling based deployment method, eliminating skin-garment friction and enabling a safer and more efficient dressing process. We present the working principles of the SWAG, introduce its design and fabrication, and demonstrate its performance in dressing assistance. The proposed system demonstrates effective garment application across various garment configurations, presenting a promising alternative to conventional robotic dressing assistance. △ Less

Submitted 9 July, 2025; originally announced July 2025.

Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting

Authors: Zekai Wang, Bing Yao

Abstract: Spatiotemporal dynamics forecasting is inherently challenging, particularly in systems defined over irregular geometric domains, due to the need to jointly capture complex spatial correlations and nonlinear temporal dynamics. To tackle these challenges, we propose TK-GCN, a two-stage framework that integrates geometry-aware spatial encoding with long-range temporal modeling. In the first stage, a… ▽ More Spatiotemporal dynamics forecasting is inherently challenging, particularly in systems defined over irregular geometric domains, due to the need to jointly capture complex spatial correlations and nonlinear temporal dynamics. To tackle these challenges, we propose TK-GCN, a two-stage framework that integrates geometry-aware spatial encoding with long-range temporal modeling. In the first stage, a Koopman-enhanced Graph Convolutional Network (K-GCN) is developed to embed the high-dimensional dynamics distributed on spatially irregular domains into a latent space where the evolution of system states is approximately linear. By leveraging Koopman operator theory, this stage enhances the temporal consistency during the latent learning. In the second stage, a Transformer module is employed to model the temporal progression within the Koopman-encoded latent space. Through the self-attention mechanism, the Transformer captures long-range temporal dependencies, enabling accurate forecasting over extended horizons. We evaluate TK-GCN in spatiotemporal cardiac dynamics forecasting and benchmark its performance against several state-of-the-art baselines. Experimental results and ablation studies show that TK-GCN consistently delivers superior predictive accuracy across a range of forecast horizons, demonstrating its capability to effectively model complex spatial structures and nonlinear temporal dynamics. △ Less

Submitted 4 July, 2025; originally announced July 2025.

$σ$-Maximal Ancestral Graphs

Authors: Binghua Yao, Joris M. Mooij

Abstract: Maximal Ancestral Graphs (MAGs) provide an abstract representation of Directed Acyclic Graphs (DAGs) with latent (selection) variables. These graphical objects encode information about ancestral relations and d-separations of the DAGs they represent. This abstract representation has been used amongst others to prove the soundness and completeness of the FCI algorithm for causal discovery, and to d… ▽ More Maximal Ancestral Graphs (MAGs) provide an abstract representation of Directed Acyclic Graphs (DAGs) with latent (selection) variables. These graphical objects encode information about ancestral relations and d-separations of the DAGs they represent. This abstract representation has been used amongst others to prove the soundness and completeness of the FCI algorithm for causal discovery, and to derive a do-calculus for its output. One significant inherent limitation of MAGs is that they rule out the possibility of cyclic causal relationships. In this work, we address that limitation. We introduce and study a class of graphical objects that we coin ''$σ$-Maximal Ancestral Graphs'' (''$σ$-MAGs''). We show how these graphs provide an abstract representation of (possibly cyclic) Directed Graphs (DGs) with latent (selection) variables, analogously to how MAGs represent DAGs. We study the properties of these objects and provide a characterization of their Markov equivalence classes. △ Less

Submitted 30 June, 2025; originally announced July 2025.

Comments: It has beee accepted by the 41st Conference on Uncertainty in Artificial Intelligence (UAI)

Journal ref: Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:4775-4805, 2025

A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving

Authors: Yupeng Zhou, Can Cui, Juntong Peng, Zichong Yang, Juanwu Lu, Jitesh H Panchal, Bin Yao, Ziran Wang

Abstract: Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-dri… ▽ More Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-driven evaluation methods, although valuable, often fail to capture the full complexity of real-world scenarios and cannot easily accommodate repeatable closed-loop testing with flexible scenario manipulation. In this paper, we introduce a hierarchical real-world test platform specifically designed to evaluate VLM-integrated autonomous driving systems. Our approach includes a modular, low-latency on-vehicle middleware that allows seamless incorporation of various VLMs, a clearly separated perception-planning-control architecture that can accommodate both VLM-based and conventional modules, and a configurable suite of real-world testing scenarios on a closed track that facilitates controlled yet authentic evaluations. We demonstrate the effectiveness of the proposed platform`s testing and evaluation ability with a case study involving a VLM-enabled autonomous vehicle, highlighting how our test framework supports robust experimentation under diverse conditions. △ Less

Submitted 16 June, 2025; originally announced June 2025.