Showing 1–50 of 55 results for author: Qu, T

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Authors: Zihan Ding, Longxu Dou, Qi Gao, Xiangwu Guo, Shengchao Hu, Zilong Huang, Zihang Jiang, Lei Ke, Mengcheng Lan, Weixian Lei, Hanxuan Li, Honglin Li, Xiyun Li, Zaitang Li, Leowei Liang, Xin Luo, Haozhe Ma, Jiayi Mao, Zhoujie Pan, Can Qin, Tianyuan Qu, Weiqi Wang, Wenkai Wang, Yonglin Wang, Yuxin Wang , et al. (4 additional authors not shown)

Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce arbitrary variations across runs. We present UI-Mate, a foundation GUI agent that integrates an environment-grounded training st… ▽ More Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce arbitrary variations across runs. We present UI-Mate, a foundation GUI agent that integrates an environment-grounded training stack with in-context demonstration learning. UI-Mate makes three contributions: A Scalable Environment-Grounded Training Stack: A closed-loop data engine automates task generation, environment construction, rollout, filtering, capability balancing, SFT, and online RL across massively parallel environments via unified task-verifier bundles. In-Context Demonstration Learning: A mechanism that transforms multimodal demonstrations into flexible subtask-level workflows, follows relevant demonstrated steps, and re-plans from the live interface. OSWorkerBench Benchmark and Insights: A benchmark of 100 long-horizon office tasks across 41 applications that supports instruction-only and demonstration-guided evaluation. Its demonstration resources separate a 33-task self-demo setting, built from successful strong-agent rollouts of the same targets, from a 45-task variant-demo setting, built from human recordings of related but non-identical tasks. Experiments show that UI-Mate-27B sets a new open-weight state of the art on general computer-use benchmarks, scoring 77.0% on OSWorld-Verified and 66.2% on WindowsAgentArena. On OSWorkerBench, it reaches 41.0% strict success and 76.9% progress, outperforming its Qwen3.6-27B base by 17.7 and 24.5 points. On the 33-task self-demo subset, one demonstration raises strict success from 17.2% to 35.4% and progress from 67.9% to 81.1%, substantially improving long-horizon reliability. Project page: https://ui-mate.github.io. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Comments: UI-Mate Technical Report. Project page: https://ui-mate.github.io

MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation

Authors: Yuqi Liu, Shengju Qian, Tianyuan Qu, Mingxian Lin, Zixuan Wang, Xin Wang, Bei Yu, Jiaya Jia

Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency while executing actions with low latency. Existing video-based VLN approaches typically struggle to satisfy both demands simultaneously. To address these challenges, we propose MemVLN, a novel VLN framework that achieves state-of-the-art performance… ▽ More Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency while executing actions with low latency. Existing video-based VLN approaches typically struggle to satisfy both demands simultaneously. To address these challenges, we propose MemVLN, a novel VLN framework that achieves state-of-the-art performance with real-time inference efficiency (14 FPS). MemVLN utilizes a visual encoder to process continuous observations and a Large Language Model (LLM) to interpret instructions and generate actions. Central to our approach is an Episodic Memory management that applies pyramidal resolutions. This mechanism concentrates computation on immediate percepts while retaining compressed long-term history. Complementing to this design, we introduce Procedural Memory for fast action with a compact vocabulary of atomic mid-level actions to bypass auto-regressive decoding latency. Experiments on VLN-CE show that MemVLN-4B surpasses the baseline Qwen3-VL-4B architecture by 5.8\% SR in R2R and 9.7\% SR in RxR, while achieving a 7$\times$ speedup in inference latency. △ Less

Submitted 26 July, 2026; originally announced July 2026.

HMAF: A Hierarchical Multi-Slot GD-RTB Allocation Framework

Authors: Tianxing Bu, Zhaoqi Zhang, Linyou Cai, Miao Xie, Shengri Xue, Tan Qu, Qianlong Xie, Xingxing Wang, Siqiang Luo, Gao Cong

Abstract: In modern online advertising platforms, Guaranteed Delivery (GD) contracts coexist and bid with Real-Time Bidding (RTB) auctions. Recent approaches either decouple GD and RTB optimization or rely on heuristic priority rules, and thus fail to effectively balance short-term revenue maximization with long-term contract delivery under complex multi-slot delivery and impression constraints. To address… ▽ More In modern online advertising platforms, Guaranteed Delivery (GD) contracts coexist and bid with Real-Time Bidding (RTB) auctions. Recent approaches either decouple GD and RTB optimization or rely on heuristic priority rules, and thus fail to effectively balance short-term revenue maximization with long-term contract delivery under complex multi-slot delivery and impression constraints. To address these challenges, we propose HMAF (Hierarchical Multi-Slot Allocation Framework), a unified framework designed to optimize impression allocation in GD--RTB advertising platforms. HMAF employs the Plan--Calibrate--Execute paradigm as its core structure, and integrates offline constraint optimization with online decision-making, balancing offline GD resource planning, dynamically calibrating GD--RTB competitiveness, and making real-time listwise rank decisions across multi-slot environments. HMAF has been implemented in multiple marketing scenarios at Meituan, one of the world's largest online food delivery platforms, leading to a 3.72% increase in GD delivery rate and a 1.59% increase in total advertisement revenue. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: Accepted by KDD 2026 Applied Data Science Track

SHB-AE: Spherical harmonic beamforming based Ambisonics encoding and upscaling method for smartphone microphone array

Authors: Yuhuan You, Yufan Qian, Tianshu Qu, Bin Wang, Xueyang Lv

Abstract: With the rapid development of virtual reality (VR) and augmented reality (AR), spatial audio recording and reproduction have gained increasing research interest. Higher Order Ambisonics (HOA) stands out for its adaptability to various playback devices and its ability to integrate head orientation. However, current HOA recordings often rely on bulky spherical microphone arrays (SMA), and portable d… ▽ More With the rapid development of virtual reality (VR) and augmented reality (AR), spatial audio recording and reproduction have gained increasing research interest. Higher Order Ambisonics (HOA) stands out for its adaptability to various playback devices and its ability to integrate head orientation. However, current HOA recordings often rely on bulky spherical microphone arrays (SMA), and portable devices like smartphones are limited by array configuration and number of microphones. We propose SHB-AE, a spherical harmonic beamforming based method for Ambisonics encoding using a smartphone microphone array (SPMA). By designing beamformers for each order of spherical harmonic functions based on the array manifold, the method enables Ambisonics encoding and up-scaling. Validation on a real SPMA and its simulated free-field counterpart in noisy and reverberant conditions showed that the method successfully encodes and up-scales Ambisonics up to the fourth order with just four irregularly arranged microphones. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Comments: Accepted for presentation at AES Europe 2025 Convention (AES 158th Convention), Warsaw, Poland, May 22-24, 2025

Flow-HOA: Generative Joint Optimization for Ambisonics Encoding via Flow Matching

Authors: Yuhuan You, Yufan Qian, Tianshu Qu, Bin Wang, Xueyang Lv

Abstract: Higher-Order Ambisonics (HOA) encoding from sparse, irregular microphone arrays remains a critical challenge for consumer spatial audio capture in immersive communication and XR. We propose Flow-HOA, a generative framework that jointly optimizes a multi-dimensional objective encompassing time-domain, spectral, and spatial fidelity while producing a deployable, time-invariant bank of Finite Impulse… ▽ More Higher-Order Ambisonics (HOA) encoding from sparse, irregular microphone arrays remains a critical challenge for consumer spatial audio capture in immersive communication and XR. We propose Flow-HOA, a generative framework that jointly optimizes a multi-dimensional objective encompassing time-domain, spectral, and spatial fidelity while producing a deployable, time-invariant bank of Finite Impulse Response (FIR) encoding filters. Using conditional flow matching, the model learns to map a simple prior distribution to the target distribution of FIR filter coefficients. Training is guided by a composite loss that balances time-domain waveform fidelity, multi-resolution spectral consistency, sub-band energy preservation, and spatial directivity constraints. Objective evaluations on synthetically simulated data demonstrate improved performance over strong model-based baselines in both signal fidelity and spatial accuracy metrics. Subjective listening tests on real microphone array recordings further confirm that Flow-HOA yields higher overall sound quality with reduced artifacts, demonstrating generalization from synthetic training data to real-world capture conditions. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Comments: Accepted for presentation at AES Europe 2026 Convention (AES 160th Convention), Copenhagen, Denmark, May 28-30, 2026

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

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

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

Submitted 1 June, 2026; originally announced June 2026.

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

Authors: Zixian Su, Hongkai Zhang, Fan Gao, Encheng Su, Taiping Qu, Jingwei Guo, Nan Zhang, Hui Wang, Zhen Zhou, Kairui Bo, Yan Chen, Yue Ren, Shuai Li, Lei Xu, Henggui Zhang

Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks. We introduce CardioLens, a leakage-resistant evaluation testbed for multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archi… ▽ More Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxies for clinical use, relying on isolated inputs and simplified recognition-style tasks. We introduce CardioLens, a leakage-resistant evaluation testbed for multi-sequence Cardiovascular Magnetic Resonance (CMR), constructed from private hospital archives through a rigorous report-to-QA construction and verification pipeline. CardioLens contains 473,896 slices and 13,494 verified QA pairs across 4D Cine, LGE, perfusion, and T2-weighted imaging, and evaluates three stages of CMR interpretation: image understanding, report generation, and disease diagnosis. Across 24 state-of-the-art MLLMs, CardioLens reveals a substantial clinical reality gap: models perform poorly overall, with performance degrading along the real CMR workflow. Confusion analysis further shows a category-collapse failure mode, where models default to frequent abnormal categories rather than distinguishing clinically distinct findings. To rule out MLLM-compatible input construction as the primary cause, we compare random, clinically motivated, and data-driven slice selection protocols under different slice budgets; performance changes only marginally, typically by about 1%. Explicit reasoning prompts also fail to rescue performance, often making models more conservative rather than improving visual evidence use. These results show that current MLLMs remain far from reliable CMR interpretation, where clinical decisions require integrating distributed evidence across sequences, views, and temporal phases. CardioLens provides a clinically grounded testbed for developing next-generation MLLMs toward real-world clinical deployment. △ Less

Submitted 28 May, 2026; originally announced June 2026.

BAAI Cardiac Agent: An intelligent multimodal agent for automated reasoning and diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging

Authors: Taiping Qu, Hongkai Zhang, Lantian Zhang, Can Zhao, Nan Zhang, Hui Wang, Zhen Zhou, Mingye Zou, Kairui Bo, Pengfei Zhao, Xingxing Jin, Zixian Su, Kun Jiang, Huan Liu, Yu Du, Maozhou Wang, Ruifang Yan, Zhongyuan Wang, Tiejun Huang, Lei Xu, Henggui Zhang

Abstract: Cardiac magnetic resonance (CMR) is a cornerstone for diagnosing cardiovascular disease. However, it remains underutilized due to complex, time-consuming interpretation across multi-sequences, phases, quantitative measures that heavily reliant on specialized expertise. Here, we present BAAI Cardiac Agent, a multimodal intelligent system designed for end-to-end CMR interpretation. The agent integra… ▽ More Cardiac magnetic resonance (CMR) is a cornerstone for diagnosing cardiovascular disease. However, it remains underutilized due to complex, time-consuming interpretation across multi-sequences, phases, quantitative measures that heavily reliant on specialized expertise. Here, we present BAAI Cardiac Agent, a multimodal intelligent system designed for end-to-end CMR interpretation. The agent integrates specialized cardiac expert models to perform automated segmentation of cardiac structures, functional quantification, tissue characterization and disease diagnosis, and generates structured clinical reports within a unified workflow. Evaluated on CMR datasets from two hospitals (2413 patients) spanning 7-types of major cardiovascular diseases, the agent achieved an area under the receiver-operating-characteristic curve exceeding 0.93 internally and 0.81 externally. In the task of estimating left ventricular function indices, the results generated by this system for core parameters such as ejection fraction, stroke volume, and left ventricular mass are highly consistent with clinical reports, with Pearson correlation coefficients all exceeding 0.90. The agent outperformed state-of-the-art models in segmentation and diagnostic tasks, and generated clinical reports showing high concordance with expert radiologists (six readers across three experience levels). By dynamically orchestrating expert models for coordinated multimodal analysis, this agent framework enables accurate, efficient CMR interpretation and highlights its potentials for complex clinical imaging workflows. Code is available at https://github.com/plantain-herb/Cardiac-Agent. △ Less

Submitted 5 April, 2026; originally announced April 2026.

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Authors: Boqiang Zhang, Lei Ke, Ruihan Yang, Qi Gao, Tianyuan Qu, Rossell Chen, Dong Yu, Leoweiliang

Abstract: Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pr… ▽ More Vision Language Model (VLM) development has largely relied on scaling model size, which hinders deployment on compute-constrained mobile and edge devices such as smartphones and robots. In this work, we explore the performance limits of compact (e.g., 2B and 8B) VLMs. We challenge the prevailing practice that state-of-the-art VLMs must rely on vision encoders initialized via massive contrastive pretraining (e.g., CLIP/SigLIP). We identify an objective mismatch: contrastive learning, optimized for discrimination, enforces coarse and category-level invariances that suppress fine-grained visual cues needed for dense captioning and complex VLM reasoning. To address this issue, we present Penguin-VL, whose vision encoder is initialized from a text-only LLM. Our experiments reveal that Penguin-Encoder serves as a superior alternative to traditional contrastive pretraining, unlocking a higher degree of visual fidelity and data efficiency for multimodal understanding. Across various image and video benchmarks, Penguin-VL achieves performance comparable to leading VLMs (e.g., Qwen3-VL) in mathematical reasoning and surpasses them in tasks such as document understanding, visual knowledge, and multi-perspective video understanding. Notably, these gains are achieved with a lightweight architecture, demonstrating that improved visual representation rather than model scaling is the primary driver of performance. Our ablations show that Penguin-Encoder consistently outperforms contrastive-pretrained encoders, preserving fine-grained spatial and temporal cues that are critical for dense perception and complex reasoning. This makes it a strong drop-in alternative for compute-efficient VLMs and enables high performance in resource-constrained settings. Code: https://github.com/tencent-ailab/Penguin-VL △ Less

Submitted 14 March, 2026; v1 submitted 6 March, 2026; originally announced March 2026.

Comments: Penguin-VL demonstrates that text-only initialized vision encoders can achieve superior performance in multimodal understanding tasks; Code: https://github.com/tencent-ailab/Penguin-VL

PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging

Authors: Tianyi Qu, Songxiao Yang, Haolin Wang, Huadong Song, Xiaoting Guo, Wenguang Hu, Guanlin Liu, Honghe Chen, Yafei Ou

Abstract: Pipeline integrity is critical to industrial safety and environmental protection, with Magnetic Flux Leakage (MFL) detection being a primary non-destructive testing technology. Despite the promise of deep learning for automating MFL interpretation, progress toward reliable models has been constrained by the absence of a large-scale public dataset and benchmark, making fair comparison and reproduci… ▽ More Pipeline integrity is critical to industrial safety and environmental protection, with Magnetic Flux Leakage (MFL) detection being a primary non-destructive testing technology. Despite the promise of deep learning for automating MFL interpretation, progress toward reliable models has been constrained by the absence of a large-scale public dataset and benchmark, making fair comparison and reproducible evaluation difficult. We introduce \textbf{PipeMFL-240K}, a large-scale, meticulously annotated dataset and benchmark for complex object detection in pipeline MFL pseudo-color images. PipeMFL-240K reflects real-world inspection complexity and poses several unique challenges: (i) an extremely long-tailed distribution over \textbf{12} categories, (ii) a high prevalence of tiny objects that often comprise only a handful of pixels and (iii) substantial intra-class variability. The dataset contains \textbf{249,320} images and \textbf{200,020} high-quality bounding-box annotations, collected from 12 pipelines spanning approximately \textbf{1,530} km. Extensive experiments are conducted with state-of-the-art object detectors to establish baselines. Results show that modern detectors still struggle with the intrinsic properties of MFL data, highlighting considerable headroom for improvement, while PipeMFL-240K provides a reliable and challenging testbed to drive future research. As the first public dataset and the first benchmark of this scale and scope for pipeline MFL inspection, it provides a critical foundation for efficient pipeline diagnostics as well as maintenance planning and is expected to accelerate algorithmic innovation and reproducible research in MFL-based pipeline integrity assessment. △ Less

Submitted 28 May, 2026; v1 submitted 3 February, 2026; originally announced February 2026.

Comments: Accepted by ACM KDD 2026 Datasets and Benchmarks Track

ACM Class: J.2; I.4.8; I.5.4

Geometry-Preserving Neural Architectures on Manifolds with Boundary

Authors: Karthik Elamvazhuthi, Shiba Biswal, Kian Rosenblum, Arushi Katyal, Tianli Qu, Grady Ma, Rishi Sonthalia

Abstract: A growing number of neural architectures have been proposed to enforce geometric constraints, including projection-based networks, exponential-map updates, constrained output layers, and manifold neural ODEs. We provide a unified framework for these geometry-preserving architectures by organizing them according to where and how constraints are enforced, either throughout the intermediate layers or… ▽ More A growing number of neural architectures have been proposed to enforce geometric constraints, including projection-based networks, exponential-map updates, constrained output layers, and manifold neural ODEs. We provide a unified framework for these geometry-preserving architectures by organizing them according to where and how constraints are enforced, either throughout the intermediate layers or only at the final output. This perspective reveals several gaps in the existing theory. To address these gaps, we prove high-level approximation theorems for projected neural ODEs, intermediate augmented architectures, and final augmented architectures on prox-regular constraint sets, including smooth manifolds with boundary. Numerical experiments on synthetic dynamics over S^2, the disk, SO(3), together with real-world protein backbone data on SE(3), demonstrate exact feasibility for analytic updates and show that the final augmentation have simpler architecture and outperform in most tasks considered. When the constraint set is unknown, we learn projections via small-time heat-kernel limits, showing diffusion/flow-matching can be used as data-based projections. Moreover, we also the demonstrate the usefulness of the architectures that enforce non-convex constraints for path planning on manifolds with boundary. △ Less

Submitted 1 July, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Does Motion Intensity Impair Cognition in HCI? The Critical Role of Physical Motion-Visual Target Directional Congruency

Authors: Jianshu Wang, Siyu Liu, Chao Zhou, Yawen Zheng, Yuan Yue, Tangjun Qu, Yang Li, Yutao Xie, Jin Huang, Yulong Bian, Feng Tian

Abstract: Human-computer interaction (HCI) increasingly occurs in motion-rich environments. The ability to accurately and rapidly respond to directional visual cues is critical in these contexts. How whole-body motion and individual differences affect human perception and reaction to these directional cues is therefore a key, yet an underexplored question for HCI. This study used a 6-DOF motion platform to… ▽ More Human-computer interaction (HCI) increasingly occurs in motion-rich environments. The ability to accurately and rapidly respond to directional visual cues is critical in these contexts. How whole-body motion and individual differences affect human perception and reaction to these directional cues is therefore a key, yet an underexplored question for HCI. This study used a 6-DOF motion platform to measure task performance on a visual direction judgment task. We analyzed performance by decomposing the complex motion into two distinct components: a task-irrelevant lateral interference component and a task-aligned directional congruency component. Results indicate that increased motion intensity lengthened reaction times. This effect was primarily driven by the lateral interference component, and this detrimental impact was disproportionately amplified for individuals with high motion sickness susceptibility. Conversely, directional congruency, where motion direction matched the visual cue, improved performance for all participants. These findings suggest that motion's impact on cognition is not monolithic, and that system design for mobile HCI can be informed by strategies that actively shape motion, such as minimizing lateral interference while maximizing directional congruency. △ Less

Submitted 19 January, 2026; originally announced January 2026.

The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models

Authors: Yuhuan You, Lai Wei, Xihong Wu, Tianshu Qu

Abstract: Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding still lacks a clear task interface. A model must also decide where sound events occur, which semantic and spatial attributes belong to the same auditory object, how multiple objects are arranged, and whether a scene-level answer is physically plausible. We… ▽ More Large audio-language models have made rapid progress in recognizing what is present in an audio clip, but spatial audio-language understanding still lacks a clear task interface. A model must also decide where sound events occur, which semantic and spatial attributes belong to the same auditory object, how multiple objects are arranged, and whether a scene-level answer is physically plausible. We formalize this capability as audio scene analysis (ASA), a three-level problem spanning atomic perception, relational integration, and cognitive reasoning. We propose The World is Not Mono (TWNM), a framework that equips audio-language models with explicit spatial evidence. TWNM uses physically grounded First-Order Ambisonics (FOA) simulation for controllable supervision, learns slot-regularized spatial representations from multichannel audio, fuses them with semantic audio features, and trains with a progressive curriculum ending in preference optimization over metadata-derived answers and auxiliary format/evidence rewards. To operationalize ASA, we build a controlled benchmark from scene metadata, covering localization, attribute binding, spatial comparison, scene abduction, and counterfactual reasoning. On this benchmark, TWNM achieves 70.8% overall accuracy, 66.4% on spatial-family tasks, and 79.76% on mixed L3 scene-level multiple-choice QA. We also audit monaural and binaural reference systems as diagnostic references with explicit audit labels, since they differ in spatial input, training interface, and output format. The supported claim is that a clearly defined ASA hierarchy, FOA-conditioned spatial representations, and metadata-grounded training enable controlled, auditable spatial audio-language reasoning, with STARSS23 providing a limited real-recording diagnostic. △ Less

Submitted 10 May, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

Comments: 25 pages, 4 figures

RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing

Authors: Tianyuan Qu, Lei Ke, Xiaohang Zhan, Longxiang Tang, Yuqi Liu, Bohao Peng, Bei Yu, Dong Yu, Jiaya Jia

Abstract: Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes… ▽ More Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall consistency. Our project page: https://replan-iv-edit.github.io △ Less

Submitted 16 July, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: [ECCV2026] Precise multi-region control and planning for instruction-based image editing. Our project page: https://replan-iv-edit.github.io

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Authors: Yuxin Wang, Lei Ke, Boqiang Zhang, Tianyuan Qu, Hanxun Yu, Zhenpeng Huang, Meng Yu, Dan Xu, Dong Yu

Abstract: While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretab… ▽ More While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretable spatial understanding. Unlike conventional end-to-end models that directly predict answers from RGB/RGB-D inputs, our approach equips the model with native 3D object perception capabilities, enabling it to directly localize objects in 3D space based on textual descriptions. Building upon accurate 3D object localization, the model further performs explicit reasoning in 3D, achieving more interpretable and structured spatial understanding. To support robust training for these capabilities, we develop a scalable data construction pipeline that leverages depth estimation to lift large-scale 2D annotations into 3D space, significantly increasing the diversity and coverage for 3D object grounding data, yielding over six times larger than the largest existing single-image 3D detection dataset. Moreover, the pipeline generates spatial question-answering datasets that target chain-of-thought (CoT) reasoning in 3D, facilitating joint training for both 3D object localization and 3D spatial reasoning. Experimental results demonstrate that our unified framework not only achieves state-of-the-art performance on 3D grounding tasks, but also consistently surpasses existing methods in 3D spatial reasoning in vision-language model. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Project Page: https://n3d-vlm.github.io

Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference

Authors: Chenxiang Zhang, Tongxi Qu, Zhong Li, Tian Zhang, Jun Pang, Sjouke Mauw

Abstract: Deep neural networks are widely deployed with quantization techniques to reduce memory and computational costs by lowering the numerical precision of their parameters. While quantization alters model parameters and their outputs, existing privacy analyses primarily focus on full-precision models, leaving a gap in understanding how bit-width reduction can affect privacy leakage. We present the firs… ▽ More Deep neural networks are widely deployed with quantization techniques to reduce memory and computational costs by lowering the numerical precision of their parameters. While quantization alters model parameters and their outputs, existing privacy analyses primarily focus on full-precision models, leaving a gap in understanding how bit-width reduction can affect privacy leakage. We present the first systematic study of the privacy-utility relationship in post-training quantization (PTQ), a versatile family of methods that can be applied to pretrained models without further training. Using membership inference attacks as our evaluation framework, we analyze three popular PTQ algorithms-AdaRound, BRECQ, and OBC-across multiple precision levels (4-bit, 2-bit, and 1.58-bit) on CIFAR-10, CIFAR-100, and TinyImageNet datasets. Our findings consistently show that low-precision PTQs can reduce privacy leakage. In particular, lower-precision models demonstrate up to an order of magnitude reduction in membership inference vulnerability compared to their full-precision counterparts, albeit at the cost of decreased utility. Additional ablation studies on the 1.58-bit quantization level show that quantizing only the last layer at higher precision enables fine-grained control over the privacy-utility trade-off. These results offer actionable insights for practitioners to balance efficiency, utility, and privacy protection in real-world deployments. △ Less

Submitted 17 December, 2025; originally announced December 2025.

Comments: accepted at TrustCom 2025

Demystifying Feature Engineering in Malware Analysis of API Call Sequences

Authors: Tianheng Qu, Hongsong Zhu, Limin Sun, Haining Wang, Haiqiang Fei, Zheng He, Zhi Li

Abstract: Machine learning (ML) has been widely used to analyze API call sequences in malware analysis, which typically requires the expertise of domain specialists to extract relevant features from raw data. The extracted features play a critical role in malware analysis. Traditional feature extraction is based on human domain knowledge, while there is a trend of using natural language processing (NLP) for… ▽ More Machine learning (ML) has been widely used to analyze API call sequences in malware analysis, which typically requires the expertise of domain specialists to extract relevant features from raw data. The extracted features play a critical role in malware analysis. Traditional feature extraction is based on human domain knowledge, while there is a trend of using natural language processing (NLP) for automatic feature extraction. This raises a question: how do we effectively select features for malware analysis based on API call sequences? To answer it, this paper presents a comprehensive study of investigating the impact of feature engineering upon malware classification.We first conducted a comparative performance evaluation under three models, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Transformer, with respect to knowledge-based and NLP-based feature engineering methods. We observed that models with knowledge-based feature engineering inputs generally outperform those using NLP-based across all metrics, especially under smaller sample sizes. Then we analyzed a complete set of data features from API call sequences, our analysis reveals that models often focus on features such as handles and virtual addresses, which vary across executions and are difficult for human analysts to interpret. △ Less

Submitted 1 December, 2025; originally announced December 2025.

RIA: A Ranking-Infused Approach for Optimized listwise CTR Prediction

Authors: Guoxiao Zhang, Tan Qu, Ao Li, DongLin Ni, Qianlong Xie, Xingxing Wang

Abstract: Reranking improves recommendation quality by modeling item interactions. However, existing methods often decouple ranking and reranking, leading to weak listwise evaluation models that suffer from combinatorial sparsity and limited representational power under strict latency constraints. In this paper, we propose RIA (Ranking-Infused Architecture), a unified, end-to-end framework that seamlessly i… ▽ More Reranking improves recommendation quality by modeling item interactions. However, existing methods often decouple ranking and reranking, leading to weak listwise evaluation models that suffer from combinatorial sparsity and limited representational power under strict latency constraints. In this paper, we propose RIA (Ranking-Infused Architecture), a unified, end-to-end framework that seamlessly integrates pointwise and listwise evaluation. RIA introduces four key components: (1) the User and Candidate DualTransformer (UCDT) for fine-grained user-item-context modeling; (2) the Context-aware User History and Target (CUHT) module for position-sensitive preference learning; (3) the Listwise Multi-HSTU (LMH) module to capture hierarchical item dependencies; and (4) the Embedding Cache (EC) module to bridge efficiency and effectiveness during inference. By sharing representations across ranking and reranking, RIA enables rich contextual knowledge transfer while maintaining low latency. Extensive experiments show that RIA outperforms state-of-the-art models on both public and industrial datasets, achieving significant gains in AUC and LogLoss. Deployed in Meituan advertising system, RIA yields a +1.69% improvement in Click-Through Rate (CTR) and a +4.54% increase in Cost Per Mille (CPM) in online A/B tests. △ Less

Submitted 26 November, 2025; originally announced November 2025.

FITRep: Attention-Guided Item Representation via MLLMs

Authors: Guoxiao Zhang, Ao Li, Tan Qu, Qianlong Xie, Xingxing Wang

Abstract: Online platforms usually suffer from user experience degradation due to near-duplicate items with similar visuals and text. While Multimodal Large Language Models (MLLMs) enable multimodal embedding, existing methods treat representations as black boxes, ignoring structural relationships (e.g., primary vs. auxiliary elements), leading to local structural collapse problem. To address this, inspired… ▽ More Online platforms usually suffer from user experience degradation due to near-duplicate items with similar visuals and text. While Multimodal Large Language Models (MLLMs) enable multimodal embedding, existing methods treat representations as black boxes, ignoring structural relationships (e.g., primary vs. auxiliary elements), leading to local structural collapse problem. To address this, inspired by Feature Integration Theory (FIT), we propose FITRep, the first attention-guided, white-box item representation framework for fine-grained item deduplication. FITRep consists of: (1) Concept Hierarchical Information Extraction (CHIE), using MLLMs to extract hierarchical semantic concepts; (2) Structure-Preserving Dimensionality Reduction (SPDR), an adaptive UMAP-based method for efficient information compression; and (3) FAISS-Based Clustering (FBC), a FAISS-based clustering that assigns each item a unique cluster id using FAISS. Deployed on Meituan's advertising system, FITRep achieves +3.60% CTR and +4.25% CPM gains in online A/B tests, demonstrating both effectiveness and real-world impact. △ Less

Submitted 26 November, 2025; originally announced November 2025.

PDA-LSTM: Knowledge-driven page data arrangement based on LSTM for LCM supression in QLC 3D NAND flash memories

Authors: Qianhui Li, Weiya Wang, Qianqi Zhao, Tong Qu, Jing He, Xuhong Qiang, Jingwen Hou, Ke Chen, Bao Zhang, Qi Wang

Abstract: Quarter level cell (QLC) 3D NAND flash memory is emerging as the predominant storage solution in the era of artificial intelligence. QLC 3D NAND flash stores 4 bit per cell to expand the storage density, resulting in narrower read margins. Constrained to read margins, QLC always suffers from lateral charge migration (LCM), which caused by non-uniform charge density across adjacent memory cells. To… ▽ More Quarter level cell (QLC) 3D NAND flash memory is emerging as the predominant storage solution in the era of artificial intelligence. QLC 3D NAND flash stores 4 bit per cell to expand the storage density, resulting in narrower read margins. Constrained to read margins, QLC always suffers from lateral charge migration (LCM), which caused by non-uniform charge density across adjacent memory cells. To suppress charge density gap between cells, there are some algorithm in form of intra-page data mapping such as WBVM, DVDS. However, we observe inter-page data arrangements also approach the suppression. Thus, we proposed an intelligent model PDA-LSTM to arrange intra-page data for LCM suppression, which is a physics-knowledge-driven neural network model. PDA-LSTM applies a long-short term memory (LSTM) neural network to compute a data arrangement probability matrix from input page data pattern. The arrangement is to minimize the global impacts derived from the LCM among wordlines. Since each page data can be arranged only once, we design a transformation from output matrix of LSTM network to non-repetitive sequence generation probability matrix to assist training process. The arranged data pattern can decrease the bit error rate (BER) during data retention. In addition, PDA-LSTM do not need extra flag bits to record data transport of 3D NAND flash compared with WBVM, DVDS. The experiment results show that the PDA-LSTM reduces the average BER by 80.4% compared with strategy without data arrangement, and by 18.4%, 15.2% compared respectively with WBVM and DVDS with code-length 64. △ Less

Submitted 29 October, 2025; originally announced November 2025.

A Surrogate model for High Temperature Superconducting Magnets to Predict Current Distribution with Neural Network

Authors: Mianjun Xiao, Peng Song, Yulong Liu, Cedric Korte, Ziyang Xu, Jiale Gao, Jiaqi Lu, Haoyang Nie, Qiantong Deng, Timing Qu

Abstract: Finite element methods (FEM) for high-temperature superconducting (HTS) magnets become time-consuming at larger scales, restricting the rapid optimization of meter-scale REBCO solenoids. In this work, a surrogate model based on a fully connected residual neural network (FCRN) is developed to predict the current density distribution in REBCO solenoids. Trained on datasets generated from FEM simulat… ▽ More Finite element methods (FEM) for high-temperature superconducting (HTS) magnets become time-consuming at larger scales, restricting the rapid optimization of meter-scale REBCO solenoids. In this work, a surrogate model based on a fully connected residual neural network (FCRN) is developed to predict the current density distribution in REBCO solenoids. Trained on datasets generated from FEM simulations by the T-A formulation, the FCRN model is evaluated under both fast ramping and steady-state scenarios, showing a lower validation loss than the fully connected network (FCN). When extrapolating geometric parameters beyond the training set, the model achieves a relative error of below 10 % for magnetization losses in Case 1 and an average error of 1.2 % for the central magnetic field in Case 2. Furthermore, deploying the steady-state surrogate model for rapid magnet design found the optimal solution within the parameter space under constraints, with a relative central magnetic field error of 0.2 % compared to FEM results. With rapid predictions, this surrogate model offers an efficient tool for the intelligent design of large-scale HTS magnets. △ Less

Submitted 10 March, 2026; v1 submitted 7 September, 2025; originally announced September 2025.

Distributed optimization: designed for federated learning

Authors: Wenyou Guo, Ting Qu, Chunrong Pan, George Q. Huang

Abstract: Federated learning (FL), as a distributed collaborative machine learning (ML) framework under privacy-preserving constraints, has garnered increasing research attention in cross-organizational data collaboration scenarios. This paper proposes a class of distributed optimization algorithms based on the augmented Lagrangian technique, designed to accommodate diverse communication topologies in both… ▽ More Federated learning (FL), as a distributed collaborative machine learning (ML) framework under privacy-preserving constraints, has garnered increasing research attention in cross-organizational data collaboration scenarios. This paper proposes a class of distributed optimization algorithms based on the augmented Lagrangian technique, designed to accommodate diverse communication topologies in both centralized and decentralized FL settings. Furthermore, we develop multiple termination criteria and parameter update mechanisms to enhance computational efficiency, accompanied by rigorous theoretical guarantees of convergence. By generalizing the augmented Lagrangian relaxation through the incorporation of proximal relaxation and quadratic approximation, our framework systematically recovers a broad of classical unconstrained optimization methods, including proximal algorithm, classic gradient descent, and stochastic gradient descent, among others. Notably, the convergence properties of these methods can be naturally derived within the proposed theoretical framework. Numerical experiments demonstrate that the proposed algorithm exhibits strong performance in large-scale settings with significant statistical heterogeneity across clients. △ Less

Submitted 30 October, 2025; v1 submitted 11 August, 2025; originally announced August 2025.

Comments: 16 pages, 6 figures

A Recipe for Causal Graph Regression: Confounding Effects Revisited

Authors: Yujia Yin, Tianyi Qu, Zihao Wang, Yifan Chen

Abstract: Through recognizing causal subgraphs, causal graph learning (CGL) has risen to be a promising approach for improving the generalizability of graph neural networks under out-of-distribution (OOD) scenarios. However, the empirical successes of CGL techniques are mostly exemplified in classification settings, while regression tasks, a more challenging setting in graph learning, are overlooked. We thu… ▽ More Through recognizing causal subgraphs, causal graph learning (CGL) has risen to be a promising approach for improving the generalizability of graph neural networks under out-of-distribution (OOD) scenarios. However, the empirical successes of CGL techniques are mostly exemplified in classification settings, while regression tasks, a more challenging setting in graph learning, are overlooked. We thus devote this work to tackling causal graph regression (CGR); to this end we reshape the processing of confounding effects in existing CGL studies, which mainly deal with classification. Specifically, we reflect on the predictive power of confounders in graph-level regression, and generalize classification-specific causal intervention techniques to regression through a lens of contrastive learning. Extensive experiments on graph OOD benchmarks validate the efficacy of our proposals for CGR. The model implementation and the code are provided on https://github.com/causal-graph/CGR. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: ICML 2025 accepted

Mitigating Negative Interference in Multilingual Sequential Knowledge Editing through Null-Space Constraints

Authors: Wei Sun, Tingyu Qu, Mingxiao Li, Jesse Davis, Marie-Francine Moens

Abstract: Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems for each language might seem viable, this approach incurs substantial costs due to the need to manage multiple models. A more efficient solution involves integrat… ▽ More Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems for each language might seem viable, this approach incurs substantial costs due to the need to manage multiple models. A more efficient solution involves integrating knowledge updates across all languages into a unified model. However, performing sequential edits across languages often leads to destructive parameter interference, significantly degrading multilingual generalization and the accuracy of injected knowledge. To address this challenge, we propose LangEdit, a novel null-space constrained framework designed to precisely isolate language-specific knowledge updates. The core innovation of LangEdit lies in its ability to project parameter updates for each language onto the orthogonal complement of previous updated subspaces. This approach mathematically guarantees update independence while preserving multilingual generalization capabilities. We conduct a comprehensive evaluation across three model architectures, six languages, and four downstream tasks, demonstrating that LangEdit effectively mitigates parameter interference and outperforms existing state-of-the-art editing methods. Our results highlight its potential for enabling efficient and accurate multilingual knowledge updates in LLMs. The code is available at https://github.com/VRCMF/LangEdit.git. △ Less

Submitted 12 June, 2025; originally announced June 2025.

Comments: ACL 2025 Findings

OASIS: Online Sample Selection for Continual Visual Instruction Tuning

Authors: Minjae Lee, Minhyuk Seo, Tingyu Qu, Tinne Tuytelaars, Jonghyun Choi

Abstract: In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can mitigate this overhead, but existing strategies often rely on pretrained reference models, which are impractical in CIT setups since future data are unknown. Recent r… ▽ More In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can mitigate this overhead, but existing strategies often rely on pretrained reference models, which are impractical in CIT setups since future data are unknown. Recent reference model-free online sample selection methods address this, but typically select a fixed number of samples per batch (e.g., top-k), making them vulnerable to distribution shifts where informativeness varies across batches. To address these limitations, we propose OASIS, an adaptive online sample selection approach for CIT that (1) selects informative samples by estimating each sample's informativeness relative to all previously seen data, beyond batch-level constraints, and (2) minimizes informative redundancy of selected samples through iterative selection score updates. Experiments on various large foundation models show that OASIS, using only 25 percent of the data, achieves comparable performance to full-data training and outperforms the state-of-the-art sampling methods. △ Less

Submitted 9 October, 2025; v1 submitted 27 May, 2025; originally announced June 2025.

From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving

Authors: Xinyu Xia, Xingjun Ma, Yunfeng Hu, Ting Qu, Hong Chen, Xun Gong

Abstract: Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario generation and selection methods often lack adaptivity and semantic relevance, limiting their impact on performance improvement. In this paper, we propose \textb… ▽ More Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario generation and selection methods often lack adaptivity and semantic relevance, limiting their impact on performance improvement. In this paper, we propose \textbf{SERA}, an LLM-powered framework that enables autonomous driving systems to self-evolve by repairing failure cases through targeted scenario recommendation. By analyzing performance logs, SERA identifies failure patterns and dynamically retrieves semantically aligned scenarios from a structured bank. An LLM-based reflection mechanism further refines these recommendations to maximize relevance and diversity. The selected scenarios are used for few-shot fine-tuning, enabling targeted adaptation with minimal data. Experiments on the benchmark show that SERA consistently improves key metrics across multiple autonomous driving baselines, demonstrating its effectiveness and generalizability under safety-critical conditions. △ Less

Submitted 28 May, 2025; originally announced May 2025.

RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models

Authors: Yuqi Liu, Qin Jin, Tianyuan Qu, Xuan Liu, Yang Du, Bei Yu, Jiaya Jia

Abstract: Understanding accurate atomic temporal event is essential for video comprehension. However, current video-language benchmarks often fall short to evaluate Large Multi-modal Models' (LMMs) temporal event understanding capabilities, as they can be effectively addressed using image-language models. In this paper, we introduce RTime-QA, a novel benchmark specifically designed to assess the atomic temp… ▽ More Understanding accurate atomic temporal event is essential for video comprehension. However, current video-language benchmarks often fall short to evaluate Large Multi-modal Models' (LMMs) temporal event understanding capabilities, as they can be effectively addressed using image-language models. In this paper, we introduce RTime-QA, a novel benchmark specifically designed to assess the atomic temporal event understanding ability of LMMs. RTime-QA comprises 822 high-quality, carefully-curated video-text questions, each meticulously annotated by human experts. Each question features a video depicting an atomic temporal event, paired with both correct answers and temporal negative descriptions, specifically designed to evaluate temporal understanding. To advance LMMs' temporal event understanding ability, we further introduce RTime-IT, a 14k instruction-tuning dataset that employs a similar annotation process as RTime-QA. Extensive experimental analysis demonstrates that RTime-QA presents a significant challenge for LMMs: the state-of-the-art model Qwen2-VL achieves only 34.6 on strict-ACC metric, substantially lagging behind human performance. Furthermore, our experiments reveal that RTime-IT effectively enhance LMMs' capacity in temporal understanding. By fine-tuning on RTime-IT, our Qwen2-VL achieves 65.9 on RTime-QA. △ Less

Submitted 25 May, 2025; originally announced May 2025.

VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

Authors: Yuqi Liu, Tianyuan Qu, Zhisheng Zhong, Bohao Peng, Shu Liu, Bei Yu, Jiaya Jia

Abstract: Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks within a shared model. Specifically, by designing a unified reward mechanism and multi-object cognitive learning strategies, VisionReasoner enhances its reasoning capab… ▽ More Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks within a shared model. Specifically, by designing a unified reward mechanism and multi-object cognitive learning strategies, VisionReasoner enhances its reasoning capabilities to analyze visual inputs, and addresses diverse perception tasks within a unified model. VisionReasoner generates a structured reasoning process before delivering the desired outputs responding to user queries. Human evaluation reveals the reasoning process of VisionReasoner is faithful and reliable even without annotated reasoning train data. To rigorously assess unified visual perception capabilities, we evaluate VisionReasoner on ten diverse tasks spanning three critical domains: detection, segmentation, and counting. Experimental results show that VisionReasoner achieves superior performance as a unified model, outperforming the baseline Qwen2.5VL by relative margins of 29.1\% on COCO (detection), 22.1\% on ReasonSeg (segmentation), and 13.2\% on CountBench (counting). △ Less

Submitted 8 February, 2026; v1 submitted 17 May, 2025; originally announced May 2025.

Towards scientific machine learning for granular material simulations -- challenges and opportunities

Authors: Marc Fransen, Andreas Fürst, Deepak Tunuguntla, Daniel N. Wilke, Benedikt Alkin, Daniel Barreto, Johannes Brandstetter, Miguel Angel Cabrera, Xinyan Fan, Mengwu Guo, Bram Kieskamp, Krishna Kumar, John Morrissey, Jonathan Nuttall, Jin Ooi, Luisa Orozco, Stefanos-Aldo Papanicolopulos, Tongming Qu, Dingena Schott, Takayuki Shuku, WaiChing Sun, Thomas Weinhart, Dongwei Ye, Hongyang Cheng

Abstract: Micro-scale mechanisms, such as inter-particle and particle-fluid interactions, govern the behaviour of granular systems. While particle-scale simulations provide detailed insights into these interactions, their computational cost is often prohibitive. Attended by researchers from both the granular materials (GM) and machine learning (ML) communities, a recent Lorentz Center Workshop on "Machine L… ▽ More Micro-scale mechanisms, such as inter-particle and particle-fluid interactions, govern the behaviour of granular systems. While particle-scale simulations provide detailed insights into these interactions, their computational cost is often prohibitive. Attended by researchers from both the granular materials (GM) and machine learning (ML) communities, a recent Lorentz Center Workshop on "Machine Learning for Discrete Granular Media" brought the ML community up to date with GM challenges. This position paper emerged from the workshop discussions. We define granular materials and identify seven key challenges that characterise their distinctive behaviour across various scales and regimes, ranging from gas-like to fluid-like and solid-like. Addressing these challenges is essential for developing robust and efficient digital twins for granular systems in various industrial applications. To showcase the potential of ML to the GM community, we present classical and emerging machine/deep learning techniques that have been, or could be, applied to granular materials. We reviewed sequence-based learning models for path-dependent constitutive behaviour, followed by encoder-decoder type models for representing high-dimensional data. We then explore graph neural networks and recent advances in neural operator learning. Lastly, we discuss model-order reduction and probabilistic learning techniques for high-dimensional parameterised systems, which are crucial for quantifying uncertainties arising from physics-based and data-driven models. We present a workflow aimed at unifying data structures and modelling pipelines and guiding readers through the selection, training, and deployment of ML surrogates for granular material simulations. Finally, we illustrate the workflow's practical use with two representative examples, focusing on granular materials in solid-like and fluid-like regimes. △ Less

Submitted 1 April, 2025; originally announced April 2025.

Comments: 35 pages, 17 figures

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Authors: Tianyuan Qu, Longxiang Tang, Bohao Peng, Senqiao Yang, Bei Yu, Jiaya Jia

Abstract: The rise of Large Vision-Language Models (LVLMs) has significantly advanced video understanding. However, efficiently processing long videos remains a challenge due to the ``Sampling Dilemma'': low-density sampling risks missing critical information, while high-density sampling introduces redundancy. To address this issue, we introduce LSDBench, the first benchmark designed to evaluate LVLMs on lo… ▽ More The rise of Large Vision-Language Models (LVLMs) has significantly advanced video understanding. However, efficiently processing long videos remains a challenge due to the ``Sampling Dilemma'': low-density sampling risks missing critical information, while high-density sampling introduces redundancy. To address this issue, we introduce LSDBench, the first benchmark designed to evaluate LVLMs on long-video tasks by constructing high Necessary Sampling Density (NSD) questions, where NSD represents the minimum sampling density required to accurately answer a given question. LSDBench focuses on dense, short-duration actions to rigorously assess the sampling strategies employed by LVLMs. To tackle the challenges posed by high-NSD questions, we propose a novel Reasoning-Driven Hierarchical Sampling (RHS) framework, which combines global localization of question-relevant cues with local dense sampling for precise inference. Additionally, we develop a lightweight Semantic-Guided Frame Selector to prioritize informative frames, enabling RHS to achieve comparable or superior performance with significantly fewer sampled frames. Together, our LSDBench and RHS framework address the unique challenges of high-NSD long-video tasks, setting a new standard for evaluating and improving LVLMs in this domain. Our benchmark and evaluation codes has been released at: https://github.com/dvlab-research/LSDBench △ Less

Submitted 27 March, 2025; v1 submitted 16 March, 2025; originally announced March 2025.

TA-V2A: Textually Assisted Video-to-Audio Generation

Authors: Yuhuan You, Xihong Wu, Tianshu Qu

Abstract: As artificial intelligence-generated content (AIGC) continues to evolve, video-to-audio (V2A) generation has emerged as a key area with promising applications in multimedia editing, augmented reality, and automated content creation. While Transformer and Diffusion models have advanced audio generation, a significant challenge persists in extracting precise semantic information from videos, as curr… ▽ More As artificial intelligence-generated content (AIGC) continues to evolve, video-to-audio (V2A) generation has emerged as a key area with promising applications in multimedia editing, augmented reality, and automated content creation. While Transformer and Diffusion models have advanced audio generation, a significant challenge persists in extracting precise semantic information from videos, as current models often lose sequential context by relying solely on frame-based features. To address this, we present TA-V2A, a method that integrates language, audio, and video features to improve semantic representation in latent space. By incorporating large language models for enhanced video comprehension, our approach leverages text guidance to enrich semantic expression. Our diffusion model-based system utilizes automated text modulation to enhance inference quality and efficiency, providing personalized control through text-guided interfaces. This integration enhances semantic expression while ensuring temporal alignment, leading to more accurate and coherent video-to-audio generation. △ Less

Submitted 12 March, 2025; originally announced March 2025.

Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Bias

Authors: Mingxiao Li, Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens

Abstract: Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a user-provided subject while maintaining both consistency of the subject and flexibility to accommodate various textual descriptions of that subject. However, current… ▽ More Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a user-provided subject while maintaining both consistency of the subject and flexibility to accommodate various textual descriptions of that subject. However, current methods face challenges in ensuring fidelity to the text prompt while not overfitting to the training data. In this work, we introduce a novel training pipeline that incorporates an attractor to filter out distractions in training images, allowing the model to focus on learning an effective representation of the personalized subject. Moreover, current evaluation methods struggle due to the lack of a dedicated test set. The evaluation set-up typically relies on the training data of the personalization task to compute text-image and image-image similarity scores, which, while useful, tend to overestimate performance. Although human evaluations are commonly used as an alternative, they often suffer from bias and inconsistency. To address these issues, we curate a diverse and high-quality test set with well-designed prompts. With this new benchmark, automatic evaluation metrics can reliably assess model performance △ Less

Submitted 9 March, 2025; originally announced March 2025.

Comments: 18

Catch Causal Signals from Edges for Label Imbalance in Graph Classification

Authors: Fengrui Zhang, Yujia Yin, Hongzong Li, Yifan Chen, Tianyi Qu

Abstract: Despite significant advancements in causal research on graphs and its application to cracking label imbalance, the role of edge features in detecting the causal effects within graphs has been largely overlooked, leaving existing methods with untapped potential for further performance gains. In this paper, we enhance the causal attention mechanism through effectively leveraging edge information to… ▽ More Despite significant advancements in causal research on graphs and its application to cracking label imbalance, the role of edge features in detecting the causal effects within graphs has been largely overlooked, leaving existing methods with untapped potential for further performance gains. In this paper, we enhance the causal attention mechanism through effectively leveraging edge information to disentangle the causal subgraph from the original graph, as well as further utilizing edge features to reshape graph representations. Capturing more comprehensive causal signals, our design leads to improved performance on graph classification tasks with label imbalance issues. We evaluate our approach on real-word datasets PTC, Tox21, and ogbg-molhiv, observing improvements over baselines. Overall, we highlight the importance of edge features in graph causal detection and provide a promising direction for addressing label imbalance challenges in graph-level tasks. The model implementation details and the codes are available on https://github.com/fengrui-z/ECAL △ Less

Submitted 7 January, 2025; v1 submitted 3 January, 2025; originally announced January 2025.

Comments: ICASSP 2025

Versatile Locomotion Skills for Hexapod Robots

Authors: Tomson Qu, Dichen Li, Avideh Zakhor, Wenhao Yu, Tingnan Zhang

Abstract: Hexapod robots are potentially suitable for carrying out tasks in cluttered environments since they are stable, compact, and light weight. They also have multi-joint legs and variable height bodies that make them good candidates for tasks such as stairs climbing and squeezing under objects in a typical home environment or an attic. Expanding on our previous work on joist climbing in attics, we tra… ▽ More Hexapod robots are potentially suitable for carrying out tasks in cluttered environments since they are stable, compact, and light weight. They also have multi-joint legs and variable height bodies that make them good candidates for tasks such as stairs climbing and squeezing under objects in a typical home environment or an attic. Expanding on our previous work on joist climbing in attics, we train a legged hexapod equipped with a depth camera and visual inertial odometry (VIO) to perform three tasks: climbing stairs, avoiding obstacles, and squeezing under obstacles such as a table. Our policies are trained with simulation data only and can be deployed on lowcost hardware not requiring real-time joint state feedback. We train our model in a teacher-student model with 2 phases: In phase 1, we use reinforcement learning with access to privileged information such as height maps and joint feedback. In phase 2, we use supervised learning to distill the model into one with access to only onboard observations, consisting of egocentric depth images and robot pose captured by a tracking VIO camera. By manipulating available privileged information, constructing simulation terrains, and refining reward functions during phase 1 training, we are able to train the robots with skills that are robust in non-ideal physical environments. We demonstrate successful sim-to-real transfer and achieve high success rates across all three tasks in physical experiments. △ Less

Submitted 13 December, 2024; originally announced December 2024.

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

Authors: Zhisheng Zhong, Chengyao Wang, Yuqi Liu, Senqiao Yang, Longxiang Tang, Yuechen Zhang, Jingyao Li, Tianyuan Qu, Yanwei Li, Yukang Chen, Shaozuo Yu, Sitong Wu, Eric Lo, Shu Liu, Jiaya Jia

Abstract: As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension,… ▽ More As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction. To achieve efficiency and speech-centric capabilities, Lyra employs three strategies: (1) leveraging existing open-source large models and a proposed multi-modality LoRA to reduce training costs and data requirements; (2) using a latent multi-modality regularizer and extractor to strengthen the relationship between speech and other modalities, thereby enhancing model performance; and (3) constructing a high-quality, extensive dataset that includes 1.5M multi-modal (language, vision, audio) data samples and 12K long speech samples, enabling Lyra to handle complex long speech inputs and achieve more robust omni-cognition. Compared to other omni-methods, Lyra achieves state-of-the-art performance on various vision-language, vision-speech, and speech-language benchmarks, while also using fewer computational resources and less training data. △ Less

Submitted 12 December, 2024; originally announced December 2024.

Comments: Tech report

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

Authors: Tingyu Qu, Mingxiao Li, Tinne Tuytelaars, Marie-Francine Moens

Abstract: Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Co… ▽ More Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Consequently, extending image LLMs for video understanding tasks presents an appealing alternative. Developing effective strategies for compressing visual tokens from multiple frames is a promising way to leverage the powerful pre-trained image LLM. In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM. The findings lead to our method TS-LLaVA, which constructs visual tokens through a Thumbnail-and-Sampling strategy. Given a video, we select few equidistant frames from all input frames to construct a Thumbnail image as a detailed visual cue, complemented by Sampled visual tokens from all input frames. Our method establishes the new state-of-the-art performance among training-free video LLMs on various benchmarks. Notably, our 34B model outperforms GPT-4V on the MVBench benchmark, and achieves performance comparable to the 72B training-based video LLM, Video-LLaMA2, on the challenging MLVU benchmark. Code is available at https://github.com/tingyu215/TS-LLaVA. △ Less

Submitted 17 November, 2024; originally announced November 2024.

Comments: work in progress

Machine Learning Aided Modeling of Granular Materials: A Review

Authors: Mengqi Wang, Krishna Kumar, Y. T. Feng, Tongming Qu, Min Wang

Abstract: Artificial intelligence (AI) has become a buzz word since Google's AlphaGo beat a world champion in 2017. In the past five years, machine learning as a subset of the broader category of AI has obtained considerable attention in the research community of granular materials. This work offers a detailed review of the recent advances in machine learning-aided studies of granular materials from the par… ▽ More Artificial intelligence (AI) has become a buzz word since Google's AlphaGo beat a world champion in 2017. In the past five years, machine learning as a subset of the broader category of AI has obtained considerable attention in the research community of granular materials. This work offers a detailed review of the recent advances in machine learning-aided studies of granular materials from the particle-particle interaction at the grain level to the macroscopic simulations of granular flow. This work will start with the application of machine learning in the microscopic particle-particle interaction and associated contact models. Then, different neural networks for learning the constitutive behaviour of granular materials will be reviewed and compared. Finally, the macroscopic simulations of practical engineering or boundary value problems based on the combination of neural networks and numerical methods are discussed. We hope readers will have a clear idea of the development of machine learning-aided modelling of granular materials via this comprehensive review work. △ Less

Submitted 18 October, 2024; originally announced October 2024.

Comments: Submitted to Archives of Computational Methods in Engineering

Leveraging Sound Source Trajectories for Universal Sound Separation

Authors: Donghang Wu, Xihong Wu, Tianshu Qu

Abstract: Existing methods utilizing spatial information for sound source separation require prior knowledge of the direction of arrival (DOA) of the source or utilize estimated but imprecise localization results, which impairs the separation performance, especially when the sound sources are moving. In fact, sound source localization and separation are interconnected problems, that is, sound source localiz… ▽ More Existing methods utilizing spatial information for sound source separation require prior knowledge of the direction of arrival (DOA) of the source or utilize estimated but imprecise localization results, which impairs the separation performance, especially when the sound sources are moving. In fact, sound source localization and separation are interconnected problems, that is, sound source localization facilitates sound separation while sound separation contributes to refined source localization. This paper proposes a method utilizing the mutual facilitation mechanism between sound source localization and separation for moving sources. The proposed method comprises three stages. The first stage is initial tracking, which tracks each sound source from the audio mixture based on the source signal envelope estimation. These tracking results may lack sufficient accuracy. The second stage involves mutual facilitation: Sound separation is conducted using preliminary sound source tracking results. Subsequently, sound source tracking is performed on the separated signals, thereby refining the tracking precision. The refined trajectories further improve separation performance. This mutual facilitation process can be iterated multiple times. In the third stage, a neural beamformer estimates precise single-channel separation results based on the refined tracking trajectories and multi-channel separation outputs. Simulation experiments conducted under reverberant conditions and with moving sound sources demonstrate that the proposed method can achieve more accurate separation based on refined tracking results. △ Less

Submitted 12 June, 2026; v1 submitted 7 September, 2024; originally announced September 2024.

Comments: Published in IEEE Transactions on Audio, Speech and Language Processing(TASLP)

Journal ref: IEEE Transactions on Audio, Speech and Language Processing, vol. 33, pp. 2337-2348, 2025

Cross-attention Inspired Selective State Space Models for Target Sound Extraction

Authors: Donghang Wu, Yiwen Wang, Xihong Wu, Tianshu Qu

Abstract: The Transformer model, particularly its cross-attention module, is widely used for feature fusion in target sound extraction which extracts the signal of interest based on given clues. Despite its effectiveness, this approach suffers from low computational efficiency. Recent advancements in state space models, notably the latest work Mamba, have shown comparable performance to Transformer-based me… ▽ More The Transformer model, particularly its cross-attention module, is widely used for feature fusion in target sound extraction which extracts the signal of interest based on given clues. Despite its effectiveness, this approach suffers from low computational efficiency. Recent advancements in state space models, notably the latest work Mamba, have shown comparable performance to Transformer-based methods while significantly reducing computational complexity in various tasks. However, Mamba's applicability in target sound extraction is limited due to its inability to capture dependencies between different sequences as the cross-attention does. In this paper, we propose CrossMamba for target sound extraction, which leverages the hidden attention mechanism of Mamba to compute dependencies between the given clues and the audio mixture. The calculation of Mamba can be divided to the query, key and value. We utilize the clue to generate the query and the audio mixture to derive the key and value, adhering to the principle of the cross-attention mechanism in Transformers. Experimental results from two representative target sound extraction methods validate the efficacy of the proposed CrossMamba. △ Less

Submitted 25 June, 2025; v1 submitted 7 September, 2024; originally announced September 2024.

Comments: This is the preprint version of the paper published in ICASSP 2025. The final version is available at IEEE Xplore: https://ieeexplore.ieee.org/document/10890178

Journal ref: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5

Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction

Authors: Qi Liu, Xingyuan Tang, Jianqiang Huang, Xiangqian Yu, Haoran Jin, Jin Chen, Yuanhao Pu, Defu Lian, Tan Qu, Zhe Wang, Jia Cheng, Jun Lei

Abstract: Natural content and advertisement coexist in industrial recommendation systems but differ in data distribution. Concretely, traffic related to the advertisement is considerably sparser compared to that of natural content, which motivates the development of transferring knowledge from the richer source natural content domain to the sparser advertising domain. The challenges include the inefficienci… ▽ More Natural content and advertisement coexist in industrial recommendation systems but differ in data distribution. Concretely, traffic related to the advertisement is considerably sparser compared to that of natural content, which motivates the development of transferring knowledge from the richer source natural content domain to the sparser advertising domain. The challenges include the inefficiencies arising from the management of extensive source data and the problem of 'catastrophic forgetting' that results from the CTR model's daily updating. To this end, we propose a novel tri-level asynchronous framework, i.e., Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction (E-CDCTR), to transfer comprehensive knowledge of natural content to advertisement CTR models. This framework consists of three key components: Tiny Pre-training Model ((TPM), which trains a tiny CTR model with several basic features on long-term natural data; Complete Pre-training Model (CPM), which trains a CTR model holding network structure and input features the same as target advertisement on short-term natural data; Advertisement CTR model (A-CTR), which derives its parameter initialization from CPM together with multiple historical embeddings from TPM as extra feature and then fine-tunes on advertisement data. TPM provides richer representations of user and item for both the CPM and A-CTR, effectively alleviating the forgetting problem inherent in the daily updates. CPM further enhances the advertisement model by providing knowledgeable initialization, thereby alleviating the data sparsity challenges typically encountered by advertising CTR models. Such a tri-level cross-domain transfer learning framework offers an efficient solution to address both data sparsity and `catastrophic forgetting', yielding remarkable improvements. △ Less

Submitted 28 August, 2024; originally announced August 2024.

Null Compliance: NYC Local Law 144 and the Challenges of Algorithm Accountability

Authors: Lucas Wright, Roxana Mike Muenster, Briana Vecchione, Tianyao Qu, Pika, Cai, COMM/INFO 2450 Student Investigators, Jacob Metcalf, J. Nathan Matias

Abstract: In July 2023, New York City became the first jurisdiction globally to mandate bias audits for commercial algorithmic systems, specifically for automated employment decisions systems (AEDTs) used in hiring and promotion. Local Law 144 (LL 144) requires AEDTs to be independently audited annually for race and gender bias, and the audit report must be publicly posted. Additionally, employers are oblig… ▽ More In July 2023, New York City became the first jurisdiction globally to mandate bias audits for commercial algorithmic systems, specifically for automated employment decisions systems (AEDTs) used in hiring and promotion. Local Law 144 (LL 144) requires AEDTs to be independently audited annually for race and gender bias, and the audit report must be publicly posted. Additionally, employers are obligated to post a transparency notice with the job listing. In this study, 155 student investigators recorded 391 employers' compliance with LL 144 and the user experience for prospective job applicants. Among these employers, 18 posted audit reports and 13 posted transparency notices. These rates could potentially be explained by a significant limitation in the accountability mechanisms enacted by LL 144. Since the law grants employers substantial discretion over whether their system is in scope of the law, a null result cannot be said to indicate non-compliance, a condition we call ``null compliance." Employer discretion may also explain our finding that nearly all audits reported an impact factor over 0.8, a rule of thumb often used in employment discrimination cases. We also find that the benefit of LL 144 to ordinary job seekers is limited due to shortcomings in accessibility and usability. Our findings offer important lessons for policy-makers as they consider regulating algorithmic systems, particularly the degree of discretion to grant to regulated parties and the limitations of relying on transparency and end-user accountability. △ Less

Submitted 3 June, 2024; originally announced June 2024.

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks

Authors: Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens

Abstract: Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter, project a model's hidden states to a lower dimension, allowing pre-trained models to adapt to new data through this low-rank bottleneck. However, PEFT tasks involving multiple modalities, like vision-language (VL) tasks, require not only adaptation to new data but also learning the relationship between different mo… ▽ More Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter, project a model's hidden states to a lower dimension, allowing pre-trained models to adapt to new data through this low-rank bottleneck. However, PEFT tasks involving multiple modalities, like vision-language (VL) tasks, require not only adaptation to new data but also learning the relationship between different modalities. Targeting at VL PEFT tasks, we propose a family of operations, called routing functions, to enhance VL alignment in the low-rank bottlenecks. These feature routing functions adopt linear operations and do not introduce new trainable parameters. In-depth analyses are conducted to study their behavior. In various VL PEFT settings, the routing functions significantly improve performance of the original PEFT methods, achieving over 20\% improvement on VQAv2 ($\text{RoBERTa}_{\text{large}}$+ViT-L/16) and 30\% on COCO Captioning (GPT2-medium+ViT-L/16). Also when fine-tuning a pre-trained multimodal model such as CLIP-BART, we observe smaller but consistent improvements across a range of VL PEFT tasks. Our code is available at https://github.com/tingyu215/Routing_VLPEFT. △ Less

Submitted 12 July, 2024; v1 submitted 14 March, 2024; originally announced March 2024.

Comments: Accepted at ECCV 2024

LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model

Authors: Senqiao Yang, Tianyuan Qu, Xin Lai, Zhuotao Tian, Bohao Peng, Shu Liu, Jiaya Jia

Abstract: While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats. In this work, we introduce LISA++, an update to the existing LISA model, focusing on improving core functionalities while kee… ▽ More While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats. In this work, we introduce LISA++, an update to the existing LISA model, focusing on improving core functionalities while keeping the base architecture intact. The main enhancements in LISA++ include: \textbf{1) Enhanced Segmentation}: The instance segmentation ability has been added, providing a more detailed scene analysis along with the existing multi-region semantic segmentation. \textbf{2) More Natural Conversation}: Improved capability for multi-turn dialogue, with the ability to incorporate segmentation results directly into text responses, i.e., Segmentation in Dialogue (SiD). These improvements are achieved by curating the existing samples of generic segmentation datasets, aimed specifically at enhancing the segmentation and conversational skills without structural change and additional data sources. Comparative analysis with the original LISA model shows significant advancements in these areas, positioning LISA++ as a notable upgrade in visual understanding and interaction. LISA++'s adaptability and improved features highlight the versatility of the mask-as-embedding paradigm proposed by LISA, and the potential as a foundational model for diverse applications. △ Less

Submitted 22 January, 2024; v1 submitted 28 December, 2023; originally announced December 2023.

Comments: Typo fixed

FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models

Authors: Wan Xu, Tianyu Huang, Tianyu Qu, Guanglei Yang, Yiwen Guo, Wangmeng Zuo

Abstract: Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works lack effective exploration of prior knowledge, rendering them unable to effectively address the domain gap issue in the context of 3D FSCIL, thereby leading to catastrophic forgetting. The Contrastive Vision-Language Pre-… ▽ More Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works lack effective exploration of prior knowledge, rendering them unable to effectively address the domain gap issue in the context of 3D FSCIL, thereby leading to catastrophic forgetting. The Contrastive Vision-Language Pre-Training (CLIP) model serves as a highly suitable backbone for addressing the challenges of 3D FSCIL due to its abundant shape-related prior knowledge. Unfortunately, its direct application to 3D FSCIL still faces the incompatibility between 3D data representation and the 2D features, primarily manifested as feature space misalignment and significant noise. To address the above challenges, we introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise. RFE aligns the feature spaces of input point clouds and their embeddings by performing a unique dimensionality reduction on the feature space of pre-trained models (PTMs), effectively eliminating redundant information without compromising semantic integrity. On the other hand, SNC is a graph-based 3D model designed to capture robust geometric information within point clouds, thereby augmenting the knowledge lost due to projection, particularly when processing real-world scanned data. Moreover, traditional accuracy metrics are proven to be biased due to the imbalance in existing 3D datasets. Therefore we propose 3D FSCIL benchmark FSCIL3D-XL and novel evaluation metrics that offer a more nuanced assessment of a 3D FSCIL model. Experimental results on both established and our proposed benchmarks demonstrate that our approach significantly outperforms existing state-of-the-art methods. △ Less

Submitted 8 January, 2025; v1 submitted 28 December, 2023; originally announced December 2023.

Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation

Authors: Zhen Liu, Hang Gao, Hao Ma, Shuo Cai, Yunfeng Hu, Ting Qu, Hong Chen, Xun Gong

Abstract: Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement lear… ▽ More Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV. △ Less

Submitted 14 October, 2023; v1 submitted 29 September, 2023; originally announced October 2023.

Comments: We find there is expression error in III.A. A correction edition will be offered

Visually-Aware Context Modeling for News Image Captioning

Authors: Tingyu Qu, Tinne Tuytelaars, Marie-Francine Moens

Abstract: News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence pattern in existing datasets, we propose a face-naming module for learning better name embeddings. Apart from names, which can be directly linked to an image ar… ▽ More News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence pattern in existing datasets, we propose a face-naming module for learning better name embeddings. Apart from names, which can be directly linked to an image area (faces), news image captions mostly contain context information that can only be found in the article. We design a retrieval strategy using CLIP to retrieve sentences that are semantically close to the image, mimicking human thought process of linking articles to images. Furthermore, to tackle the problem of the imbalanced proportion of article context and image context in captions, we introduce a simple yet effective method Contrasting with Language Model backbone (CoLaM) to the training pipeline. We conduct extensive experiments to demonstrate the efficacy of our framework. We out-perform the previous state-of-the-art (without external data) by 7.97/5.80 CIDEr scores on GoodNews/NYTimes800k. Our code is available at https://github.com/tingyu215/VACNIC. △ Less

Submitted 21 March, 2024; v1 submitted 16 August, 2023; originally announced August 2023.

Comments: Accepted at NAACL 2024 Main Conference

Deep Context Interest Network for Click-Through Rate Prediction

Authors: Xuyang Hou, Zhe Wang, Qi Liu, Tan Qu, Jia Cheng, Jun Lei

Abstract: Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on an item, is essential in industrial applications, such as online advertising. Many works focus on user behavior modeling to improve CTR prediction performance. However, most of those methods only model users' positive interests from users' click items while ignoring the context information, which is the display i… ▽ More Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on an item, is essential in industrial applications, such as online advertising. Many works focus on user behavior modeling to improve CTR prediction performance. However, most of those methods only model users' positive interests from users' click items while ignoring the context information, which is the display items around the clicks, resulting in inferior performance. In this paper, we highlight the importance of context information on user behavior modeling and propose a novel model named Deep Context Interest Network (DCIN), which integrally models the click and its display context to learn users' context-aware interests. DCIN consists of three key modules: 1) Position-aware Context Aggregation Module (PCAM), which performs aggregation of display items with an attention mechanism; 2) Feedback-Context Fusion Module (FCFM), which fuses the representation of clicks and display contexts through non-linear feature interaction; 3) Interest Matching Module (IMM), which activates interests related with the target item. Moreover, we provide our hands-on solution to implement our DCIN model on large-scale industrial systems. The significant improvements in both offline and online evaluations demonstrate the superiority of our proposed DCIN method. Notably, DCIN has been deployed on our online advertising system serving the main traffic, which brings 1.5% CTR and 1.5% RPM lift. △ Less

Submitted 11 August, 2023; originally announced August 2023.

Comments: accepted by CIKM 2023

Can Machines Garden? Systematically Comparing the AlphaGarden vs. Professional Horticulturalists

Authors: Simeon Adebola, Rishi Parikh, Mark Presten, Satvik Sharma, Shrey Aeron, Ananth Rao, Sandeep Mukherjee, Tomson Qu, Christina Wistrom, Eugen Solowjow, Ken Goldberg

Abstract: The AlphaGarden is an automated testbed for indoor polyculture farming which combines a first-order plant simulator, a gantry robot, a seed planting algorithm, plant phenotyping and tracking algorithms, irrigation sensors and algorithms, and custom pruning tools and algorithms. In this paper, we systematically compare the performance of the AlphaGarden to professional horticulturalists on the staf… ▽ More The AlphaGarden is an automated testbed for indoor polyculture farming which combines a first-order plant simulator, a gantry robot, a seed planting algorithm, plant phenotyping and tracking algorithms, irrigation sensors and algorithms, and custom pruning tools and algorithms. In this paper, we systematically compare the performance of the AlphaGarden to professional horticulturalists on the staff of the UC Berkeley Oxford Tract Greenhouse. The humans and the machine tend side-by-side polyculture gardens with the same seed arrangement. We compare performance in terms of canopy coverage, plant diversity, and water consumption. Results from two 60-day cycles suggest that the automated AlphaGarden performs comparably to professional horticulturalists in terms of coverage and diversity, and reduces water consumption by as much as 44%. Code, videos, and datasets are available at https://sites.google.com/berkeley.edu/systematiccomparison. △ Less

Submitted 29 June, 2023; originally announced June 2023.

Comments: International Conference on Robotics and Automation(ICRA) 2023 Oral

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

Authors: Mingxiao Li, Tingyu Qu, Ruicong Yao, Wei Sun, Marie-Francine Moens

Abstract: Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could exaggerate the problem of exposure bias due to the training and inference discrepancy. Previous work has attempted to mitigate this issue by perturbing inputs during… ▽ More Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could exaggerate the problem of exposure bias due to the training and inference discrepancy. Previous work has attempted to mitigate this issue by perturbing inputs during training, which consequently mandates the retraining of the DPM. In this work, we conduct a systematic study of exposure bias in DPM and, intriguingly, we find that the exposure bias could be alleviated with a novel sampling method that we propose, without retraining the model. We empirically and theoretically show that, during inference, for each backward time step $t$ and corresponding state $\hat{x}_t$, there might exist another time step $t_s$ which exhibits superior coupling with $\hat{x}_t$. Based on this finding, we introduce a sampling method named Time-Shift Sampler. Our framework can be seamlessly integrated to existing sampling algorithms, such as DDPM, DDIM and other high-order solvers, inducing merely minimal additional computations. Experimental results show our method brings significant and consistent improvements in FID scores on different datasets and sampling methods. For example, integrating Time-Shift Sampler to F-PNDM yields a FID=3.88, achieving 44.49\% improvements as compared to F-PNDM, on CIFAR-10 with 10 sampling steps, which is more performant than the vanilla DDIM with 100 sampling steps. Our code is available at https://github.com/Mingxiao-Li/TS-DPM. △ Less

Submitted 16 June, 2024; v1 submitted 24 May, 2023; originally announced May 2023.

Comments: Accepted at International Conference on Learning Representations (ICLR2024); typo correction

TT-Net: Dual-path transformer based sound field translation in the spherical harmonic domain

Authors: Yiwen Wang, Zijian Lan, Xihong Wu, Tianshu Qu

Abstract: In the current method for the sound field translation tasks based on spherical harmonic (SH) analysis, the solution based on the additive theorem usually faces the problem of singular values caused by large matrix condition numbers. The influence of different distances and frequencies of the spherical radial function on the stability of the translation matrix will affect the accuracy of the SH coe… ▽ More In the current method for the sound field translation tasks based on spherical harmonic (SH) analysis, the solution based on the additive theorem usually faces the problem of singular values caused by large matrix condition numbers. The influence of different distances and frequencies of the spherical radial function on the stability of the translation matrix will affect the accuracy of the SH coefficients at the selected point. Due to the problems mentioned above, we propose a neural network scheme based on the dual-path transformer. More specifically, the dual-path network is constructed by the self-attention module along the two dimensions of the frequency and order axes. The transform-average-concatenate layer and upscaling layer are introduced in the network, which provides solutions for multiple sampling points and upscaling. Numerical simulation results indicate that both the working frequency range and the distance range of the translation are extended. More accurate higher-order SH coefficients are obtained with the proposed dual-path network. △ Less

Submitted 30 October, 2022; originally announced October 2022.

Comments: Submitted to ICASSP 2023