Showing 1–50 of 65 results for author: Sheng, H

CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains

Authors: Wenhan Wang, Zhixiang Zhou, Zhongtian Ma, Yanzhu Chen, Ziyu Lin, Hao Sheng, Pengfei Liu, Honglin Ma, Wenqi Shao, Qiaosheng Zhang, Yu Qiao

Abstract: The connoisseurship of antique Chinese porcelain demands extensive historical expertise, material understanding, and aesthetic sensitivity, making it difficult for non-specialists to engage. To democratize cultural-heritage understanding and assist expert connoisseurship, we introduce CiQi-Agent -- a domain-specific Porcelain Connoisseurship Agent for intelligent analysis of antique Chinese porcel… ▽ More The connoisseurship of antique Chinese porcelain demands extensive historical expertise, material understanding, and aesthetic sensitivity, making it difficult for non-specialists to engage. To democratize cultural-heritage understanding and assist expert connoisseurship, we introduce CiQi-Agent -- a domain-specific Porcelain Connoisseurship Agent for intelligent analysis of antique Chinese porcelain. CiQi-Agent supports multi-image porcelain inputs and enables vision tool invocation and multimodal retrieval-augmented generation, performing fine-grained connoisseurship analysis across six attributes: dynasty, reign period, kiln site, glaze color, decorative motif, and vessel shape. Beyond attribute classification, it captures subtle visual details, retrieves relevant domain knowledge, and integrates visual and textual evidence to produce coherent, explainable connoisseurship descriptions. To achieve this capability, we construct a large-scale, expert-annotated dataset CiQi-VQA, comprising 29,596 porcelain specimens, 51,553 images, and 557,940 visual question--answering pairs, and further establish a comprehensive benchmark CiQi-Bench aligned with the previously mentioned six attributes. CiQi-Agent is trained through supervised fine-tuning, reinforcement learning, and a tool-augmented reasoning framework that integrates two categories of tools: a vision tool and multimodal retrieval tools. Experimental results show that CiQi-Agent (7B) outperforms all competitive open- and closed-source models across all six attributes on CiQi-Bench, achieving on average 12.2\% higher accuracy than GPT-5. The model and dataset have been released and are publicly available at https://huggingface.co/datasets/SII-Monument-Valley/CiQi-VQA. △ Less

Submitted 30 March, 2026; originally announced March 2026.

AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References

Authors: Jiahao Wang, Hualian Sheng, Sijia Cai, Yuxiao Yang, Weizhan Zhang, Caixia Yan, Bing Deng, Jieping Ye

Abstract: Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single identity reference. This underlying assumption restricts creative flexibility by inadequately accommodating diverse real-world input formats. Relying on a single sourc… ▽ More Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single identity reference. This underlying assumption restricts creative flexibility by inadequately accommodating diverse real-world input formats. Relying on a single source also constitutes an ill-posed scenario, causing an inherently ambiguous setting that makes it difficult for the model to faithfully reproduce an identity across novel contexts. To address these issues, we present AnyID, an ultra-fidelity identity-preservation video generation framework that features two core contributions. First, we introduce a scalable omni-referenced architecture that effectively unifies heterogeneous identity inputs (e.g., faces, portraits, and videos) into a cohesive representation. Second, we propose a primary-referenced generation paradigm, which designates one reference as a canonical anchor and uses a novel differential prompt to enable precise, attribute-level controllability. We conduct training on a large-scale, meticulously curated dataset to ensure robustness and high fidelity, and then perform a final fine-tuning stage using reinforcement learning. This process leverages a preference dataset constructed from human evaluations, where annotators performed pairwise comparisons of videos based on two key criteria: identity fidelity and prompt controllability. Extensive evaluations validate that AnyID achieves ultra-high identity fidelity as well as superior attribute-level controllability across different task settings. △ Less

Submitted 26 March, 2026; originally announced March 2026.

Video-Based Reward Modeling for Computer-Use Agents

Authors: Linxin Song, Jieyu Zhang, Huanxin Sheng, Taiwei Shi, Gupta Rahul, Yang Liu, Ranjay Krishna, Jian Kang, Jieyu Zhao

Abstract: Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this work, we study reward modeling from execution video: a sequence of keyframes from an agent trajectory that is independent of the agent's internal reasoning or actions. Although video-execution modeling is method-agnosti… ▽ More Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction. In this work, we study reward modeling from execution video: a sequence of keyframes from an agent trajectory that is independent of the agent's internal reasoning or actions. Although video-execution modeling is method-agnostic, it presents key challenges, including highly redundant layouts and subtle, localized cues that determine success. We introduce Execution Video Reward 53k (ExeVR-53k), a dataset of 53k high-quality video--task--reward triplets. We further propose adversarial instruction translation to synthesize negative samples with step-level annotations. To enable learning from long, high-resolution execution videos, we design spatiotemporal token pruning, which removes homogeneous regions and persistent tokens while preserving decisive UI changes. Building on these components, we fine-tune an Execution Video Reward Model (ExeVRM) that takes only a user instruction and a video-execution sequence to predict task success. Our ExeVRM 8B achieves 84.7% accuracy and 87.7% recall on video-execution assessment, outperforming strong proprietary models such as GPT-5.2 and Gemini-3 Pro across Ubuntu, macOS, Windows, and Android, while providing more precise temporal attribution. These results show that video-execution reward modeling can serve as a scalable, model-agnostic evaluator for CUAs. △ Less

Submitted 10 March, 2026; originally announced March 2026.

Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition

Authors: Ming Li, Yong-Jin Liu, Fang Liu, Huankun Sheng, Yeying Fan, Yixiang Wei, Minnan Luo, Weizhan Zhang, Wenping Wang

Abstract: Emotion recognition from multi-modal physiological and behavioral signals plays a pivotal role in affective computing, yet most existing models remain constrained to the prediction of singular emotions in controlled laboratory settings. Real-world human emotional experiences, by contrast, are often characterized by the simultaneous presence of multiple affective states, spurring recent interest in… ▽ More Emotion recognition from multi-modal physiological and behavioral signals plays a pivotal role in affective computing, yet most existing models remain constrained to the prediction of singular emotions in controlled laboratory settings. Real-world human emotional experiences, by contrast, are often characterized by the simultaneous presence of multiple affective states, spurring recent interest in mixed emotion recognition as an emotion distribution learning problem. Current approaches, however, often neglect the valence consistency and structured correlations inherent among coexisting emotions. To address this limitation, we propose a Memory-guided Prototypical Co-occurrence Learning (MPCL) framework that explicitly models emotion co-occurrence patterns. Specifically, we first fuse multi-modal signals via a multi-scale associative memory mechanism. To capture cross-modal semantic relationships, we construct emotion-specific prototype memory banks, yielding rich physiological and behavioral representations, and employ prototype relation distillation to ensure cross-modal alignment in the latent prototype space. Furthermore, inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations across emotion categories. Through this bottom-up hierarchical abstraction process, our model learns affectively informative representations for accurate emotion distribution prediction. Comprehensive experiments on two public datasets demonstrate that MPCL consistently outperforms state-of-the-art methods in mixed emotion recognition, both quantitatively and qualitatively. △ Less

Submitted 23 February, 2026; originally announced February 2026.

Deep Learning-based Method for Expressing Knowledge Boundary of Black-Box LLM

Authors: Haotian Sheng, Heyong Wang, Ming Hong, Hongman He, Junqiu Liu

Abstract: Large Language Models (LLMs) have achieved remarkable success, however, the emergence of content generation distortion (hallucination) limits their practical applications. The core cause of hallucination lies in LLMs' lack of awareness regarding their stored internal knowledge, preventing them from expressing their knowledge state on questions beyond their internal knowledge boundaries, as humans… ▽ More Large Language Models (LLMs) have achieved remarkable success, however, the emergence of content generation distortion (hallucination) limits their practical applications. The core cause of hallucination lies in LLMs' lack of awareness regarding their stored internal knowledge, preventing them from expressing their knowledge state on questions beyond their internal knowledge boundaries, as humans do. However, existing research on knowledge boundary expression primarily focuses on white-box LLMs, leaving methods suitable for black-box LLMs which offer only API access without revealing internal parameters-largely unexplored. Against this backdrop, this paper proposes LSCL (LLM-Supervised Confidence Learning), a deep learning-based method for expressing the knowledge boundaries of black-box LLMs. Based on the knowledge distillation framework, this method designs a deep learning model. Taking the input question, output answer, and token probability from a black-box LLM as inputs, it constructs a mapping between the inputs and the model' internal knowledge state, enabling the quantification and expression of the black-box LLM' knowledge boundaries. Experiments conducted on diverse public datasets and with multiple prominent black-box LLMs demonstrate that LSCL effectively assists black-box LLMs in accurately expressing their knowledge boundaries. It significantly outperforms existing baseline models on metrics such as accuracy and recall rate. Furthermore, considering scenarios where some black-box LLMs do not support access to token probability, an adaptive alternative method is proposed. The performance of this alternative approach is close to that of LSCL and surpasses baseline models. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations

Authors: Yuxuan Yao, Haonan Sheng, Qingsong Lv, Han Wu, Shuqi Liu, Zehua Liu, Zengyan Liu, Jiahui Gao, Haochen Tan, Xiaojin Fu, Haoli Bai, Hing Cheung So, Zhijiang Guo, Linqi Song

Abstract: The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc refinements or focus on mitigating task interference, often failing to capture the dynamic optimization benefits of supervised fine-tuning (SFT). In this work,… ▽ More The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc refinements or focus on mitigating task interference, often failing to capture the dynamic optimization benefits of supervised fine-tuning (SFT). In this work, we propose Streaming Merging, an innovative model updating paradigm that conceptualizes merging as an iterative optimization process. Central to this paradigm is \textbf{ARM} (\textbf{A}ctivation-guided \textbf{R}otation-aware \textbf{M}erging), a strategy designed to approximate gradient descent dynamics. By treating merging coefficients as learning rates and deriving rotation vectors from activation subspaces, ARM effectively steers parameter updates along data-driven trajectories. Unlike conventional linear interpolation, ARM aligns semantic subspaces to preserve the geometric structure of high-dimensional parameter evolution. Remarkably, ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model. Experimental results across model scales (1.7B to 14B) and diverse domains (e.g., math, code) demonstrate that ARM can transcend converged checkpoints. Extensive experiments show that ARM provides a scalable and lightweight framework for efficient model adaptation. △ Less

Submitted 3 February, 2026; originally announced February 2026.

OpenAI GPT-5 System Card

Authors: Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, Alex Makelov, Alex Neitz, Alex Wei, Alexandra Barr, Alexandre Kirchmeyer, Alexey Ivanov , et al. (459 additional authors not shown)

Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in… ▽ More This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach. △ Less

Submitted 19 December, 2025; originally announced January 2026.

EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer

Authors: Yuxiao Yang, Hualian Sheng, Sijia Cai, Jing Lin, Jiahao Wang, Bing Deng, Junzhe Lu, Haoqian Wang, Jieping Ye

Abstract: Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This limitation stems from the intrinsic constraints of pixel-only training objectives, which inherently bias models toward appearance fidelity at the expense of learning underlying kinematic principles. To address this, we int… ▽ More Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This limitation stems from the intrinsic constraints of pixel-only training objectives, which inherently bias models toward appearance fidelity at the expense of learning underlying kinematic principles. To address this, we introduce EchoMotion, a framework designed to model the joint distribution of appearance and human motion, thereby improving the quality of complex human action video generation. EchoMotion extends the DiT (Diffusion Transformer) framework with a dual-branch architecture that jointly processes tokens concatenated from different modalities. Furthermore, we propose MVS-RoPE (Motion-Video Syncronized RoPE), which offers unified 3D positional encoding for both video and motion tokens. By providing a synchronized coordinate system for the dual-modal latent sequence, MVS-RoPE establishes an inductive bias that fosters temporal alignment between the two modalities. We also propose a Motion-Video Two-Stage Training Strategy. This strategy enables the model to perform both the joint generation of complex human action videos and their corresponding motion sequences, as well as versatile cross-modal conditional generation tasks. To facilitate the training of a model with these capabilities, we construct HuMoVe, a large-scale dataset of approximately 80,000 high-quality, human-centric video-motion pairs. Our findings reveal that explicitly representing human motion is complementary to appearance, significantly boosting the coherence and plausibility of human-centric video generation. △ Less

Submitted 21 December, 2025; originally announced December 2025.

Comments: 26 pages, 16 figures

Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance

Authors: Huankun Sheng, Ming Li, Yixiang Wei, Yeying Fan, Yu-Hui Wen, Tieliang Gong, Yong-Jin Liu

Abstract: Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations without supervision. However, existing approaches typically process foreground and background regions indiscriminately, often resulting in background interference and suboptimal instance discovery performance on real-world d… ▽ More Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations without supervision. However, existing approaches typically process foreground and background regions indiscriminately, often resulting in background interference and suboptimal instance discovery performance on real-world data. To address this limitation, we propose Foreground-Aware Slot Attention (FASA), a two-stage framework that explicitly separates foreground from background to enable precise object discovery. In the first stage, FASA performs a coarse scene decomposition to distinguish foreground from background regions through a dual-slot competition mechanism. These slots are initialized via a clustering-based strategy, yielding well-structured representations of salient regions. In the second stage, we introduce a masked slot attention mechanism where the first slot captures the background while the remaining slots compete to represent individual foreground objects. To further address over-segmentation of foreground objects, we incorporate pseudo-mask guidance derived from a patch affinity graph constructed with self-supervised image features to guide the learning of foreground slots. Extensive experiments on both synthetic and real-world datasets demonstrate that FASA consistently outperforms state-of-the-art methods, validating the effectiveness of explicit foreground modeling and pseudo-mask guidance for robust scene decomposition and object-coherent representation. Code will be made publicly available. △ Less

Submitted 10 December, 2025; v1 submitted 2 December, 2025; originally announced December 2025.

Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents

Authors: Lingzhong Dong, Ziqi Zhou, Shuaibo Yang, Haiyue Sheng, Pengzhou Cheng, Zongru Wu, Zheng Wu, Gongshen Liu, Zhuosheng Zhang

Abstract: Mobile-use agents powered by vision-language models (VLMs) have shown great potential in interpreting natural language instructions and generating corresponding actions based on mobile graphical user interface. Recent studies suggest that incorporating chain-of-thought (CoT) reasoning tends to improve the execution accuracy. However, existing evaluations emphasize execution accuracy while neglecti… ▽ More Mobile-use agents powered by vision-language models (VLMs) have shown great potential in interpreting natural language instructions and generating corresponding actions based on mobile graphical user interface. Recent studies suggest that incorporating chain-of-thought (CoT) reasoning tends to improve the execution accuracy. However, existing evaluations emphasize execution accuracy while neglecting whether CoT reasoning aligns with ground-truth actions. This oversight fails to assess potential reasoning-execution gaps, which in turn foster over-trust: users relying on seemingly plausible CoTs may unknowingly authorize harmful actions, potentially resulting in financial loss or trust crisis. In this work, we introduce a new evaluation framework to diagnose reasoning-execution gaps. At its core lies Ground-Truth Alignment (GTA), which measures whether the action implied by a CoT matches the ground-truth action. By combining GTA with the standard Exact Match (EM) metric, we jointly assess both the reasoning accuracy and execution accuracy. This joint perspective reveals two types of reasoning-execution gaps: (i) Execution Gap (EG), where the reasoning correctly identifies the correct action but execution fails, and (ii) Reasoning Gap (RG), where execution succeeds but reasoning process conflicts with the actual execution. Experimental results across a wide range of mobile interaction tasks reveal that reasoning-execution gaps are prevalent, with execution gaps occurring more frequently than reasoning gaps. Moreover, while scaling up model size reduces the overall gap, sizable execution gaps persist even in the largest models. Further analysis shows that our framework reliably reflects systematic EG/RG patterns in state-of-the-art models. These findings offer concrete diagnostics and support the development of more trustworthy mobile-use agents. △ Less

Submitted 2 October, 2025; originally announced October 2025.

The Formation of Trust in Autonomous Vehicles after Interacting with Robotaxis on Public Roads

Authors: Xiang Chang, Zhijie Yi, Yichang Liu, Hongling Sheng, Dengbo He

Abstract: This study investigates how pedestrian trust, receptivity, and behavior evolve during interactions with Level-4 autonomous vehicles (AVs) at uncontrolled urban intersections in a naturalistic setting. While public acceptance is critical for AV adoption, most prior studies relied on simplified simulations or field tests. We conducted a real-world experiment in a commercial Robotaxi operation zone,… ▽ More This study investigates how pedestrian trust, receptivity, and behavior evolve during interactions with Level-4 autonomous vehicles (AVs) at uncontrolled urban intersections in a naturalistic setting. While public acceptance is critical for AV adoption, most prior studies relied on simplified simulations or field tests. We conducted a real-world experiment in a commercial Robotaxi operation zone, where 33 participants repeatedly crossed an uncontrolled intersection with frequent Level-4 Robotaxi traffic. Participants completed the Pedestrian Behavior Questionnaire (PBQ), Pedestrian Receptivity Questionnaire for Fully AVs (PRQF), pre- and post-experiment Trust in AVs Scale, and Personal Innovativeness Scale (PIS). Results showed that trust in AVs significantly increased post-experiment, with the increase positively associated with the Interaction component of PRQF. Additionally, both the Positive and Error subscales of the PBQ significantly influenced trust change. This study reveals how trust forms in real-world pedestrian-AV encounters, offering insights beyond lab-based research by accounting for population heterogeneity. △ Less

Submitted 30 September, 2025; originally announced October 2025.

Comments: Proceedings of the 69th HFES International Annual Meeting

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction

Authors: Huanxin Sheng, Xinyi Liu, Hangfeng He, Jieyu Zhao, Jian Kang

Abstract: LLM-as-a-judge has become a promising paradigm for using large language models (LLMs) to evaluate natural language generation (NLG), but the uncertainty of its evaluation remains underexplored. This lack of reliability may limit its deployment in many applications. This work presents the first framework to analyze the uncertainty by offering a prediction interval of LLM-based scoring via conformal… ▽ More LLM-as-a-judge has become a promising paradigm for using large language models (LLMs) to evaluate natural language generation (NLG), but the uncertainty of its evaluation remains underexplored. This lack of reliability may limit its deployment in many applications. This work presents the first framework to analyze the uncertainty by offering a prediction interval of LLM-based scoring via conformal prediction. Conformal prediction constructs continuous prediction intervals from a single evaluation run, and we design an ordinal boundary adjustment for discrete rating tasks. We also suggest a midpoint-based score within the interval as a low-bias alternative to raw model score and weighted average. We perform extensive experiments and analysis, which show that conformal prediction can provide valid prediction interval with coverage guarantees. We also explore the usefulness of interval midpoint and judge reprompting for better judgment. △ Less

Submitted 23 September, 2025; originally announced September 2025.

Comments: To appear in EMNLP 2025. Our code and data are available at \url{https://github.com/BruceSheng1202/Analyzing_Uncertainty_of_LLM-as-a-Judge

See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles

Authors: Zongru Wu, Rui Mao, Zhiyuan Tian, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Lingzhong Dong, Haiyue Sheng, Zhuosheng Zhang, Gongshen Liu

Abstract: The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key bottleneck. To investigate this, we construct a state control benchmark with binary toggle instructions derived from public datasets. Evaluation results of existing agent… ▽ More The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key bottleneck. To investigate this, we construct a state control benchmark with binary toggle instructions derived from public datasets. Evaluation results of existing agents demonstrate their notable unreliability, particularly when the current toggle state already matches the desired state. To address the challenge, we propose State-aware Reasoning (StaR), a multimodal reasoning method that enables agents to perceive the current toggle state, infer the desired state from the instruction, and act accordingly. Experiments on four multimodal agents demonstrate that StaR can improve toggle instruction execution accuracy by over 30\%. Further evaluations on three public agentic benchmarks show that StaR also enhances general agentic task performance. Finally, evaluations on a dynamic environment highlight the potential of StaR for real-world applications. Code and benchmark: https://github.com/ZrW00/StaR. △ Less

Submitted 18 March, 2026; v1 submitted 16 September, 2025; originally announced September 2025.

Comments: Accepted at CVPR 2026

Double Check My Desired Return: Transformer with Target Alignment for Offline Reinforcement Learning

Authors: Yue Pei, Hongming Zhang, Chao Gao, Martin Müller, Mengxiao Zhu, Hao Sheng, Ziliang Chen, Liang Lin, Haogang Zhu

Abstract: Offline reinforcement learning (RL) has achieved significant advances in domains such as robotic control, autonomous driving, and medical decision-making. Most existing methods primarily focus on training policies that maximize cumulative returns from a given dataset. However, many real-world applications require precise control over policy performance levels, rather than simply pursuing the best… ▽ More Offline reinforcement learning (RL) has achieved significant advances in domains such as robotic control, autonomous driving, and medical decision-making. Most existing methods primarily focus on training policies that maximize cumulative returns from a given dataset. However, many real-world applications require precise control over policy performance levels, rather than simply pursuing the best possible return. Reinforcement learning via supervised learning (RvS) frames offline RL as a sequence modeling task, enabling the extraction of diverse policies by conditioning on different desired returns. Yet, existing RvS-based transformers, such as Decision Transformer (DT), struggle to reliably align the actual achieved returns with specified target returns, especially when interpolating within underrepresented returns or extrapolating beyond the dataset. To address this limitation, we propose Doctor, a novel approach that Double Checks the Transformer with target alignment for Offline RL. Doctor integrates the strengths of supervised learning (SL) and temporal difference (TD) learning by jointly optimizing the action prediction and value estimation. During inference, Doctor introduces a double-check mechanism: actions are first sampled around the desired target returns and then validated with value functions. This ensures more accurate alignment between predicted actions and desired target returns. We evaluate Doctor on the D4RL and EpiCare benchmarks, demonstrating aligned control yields stronger performance and tunable expertise, showing its effectiveness in a wide range of tasks. △ Less

Submitted 28 September, 2025; v1 submitted 22 August, 2025; originally announced August 2025.

Efficient GPU-Centered Singular Value Decomposition Using the Divide-and-Conquer Method

Authors: Shifang Liu, Huiyuan Li, Hongjiao Sheng, Haoyuan Gui, Xiaoyu Zhang

Abstract: Singular Value Decomposition (SVD) is a fundamental matrix factorization technique in linear algebra, widely applied in numerous matrix-related problems. However, traditional SVD approaches are hindered by slow panel factorization and frequent CPU-GPU data transfers in heterogeneous systems, despite advancements in GPU computational capabilities. In this paper, we introduce a GPU-centered SVD algo… ▽ More Singular Value Decomposition (SVD) is a fundamental matrix factorization technique in linear algebra, widely applied in numerous matrix-related problems. However, traditional SVD approaches are hindered by slow panel factorization and frequent CPU-GPU data transfers in heterogeneous systems, despite advancements in GPU computational capabilities. In this paper, we introduce a GPU-centered SVD algorithm, incorporating a novel GPU-based bidiagonal divide-and-conquer (BDC) method. We reformulate the algorithm and data layout of different steps for SVD computation, performing all panel-level computations and trailing matrix updates entirely on GPU to eliminate CPU-GPU data transfers. Furthermore, we integrate related computations to optimize BLAS utilization, thereby increasing arithmetic intensity and fully leveraging the computational capabilities of GPUs. Additionally, we introduce a newly developed GPU-based BDC algorithm that restructures the workflow to eliminate matrix-level CPU-GPU data transfers and enable asynchronous execution between the CPU and GPU. Experimental results on AMD MI210 and NVIDIA V100 GPUs demonstrate that our proposed method achieves speedups of up to 1293.64x/7.47x and 14.10x/12.38x compared to rocSOLVER/cuSOLVER and MAGMA, respectively. △ Less

Submitted 15 August, 2025; originally announced August 2025.

EchoShot: Multi-Shot Portrait Video Generation

Authors: Jiahao Wang, Hualian Sheng, Sijia Cai, Weizhan Zhang, Caixia Yan, Yachuang Feng, Bing Deng, Jieping Ye

Abstract: Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily constrained to single-shot creation, while real-world applications urge for multiple shots with identity consistency and flexible content controllability. In this work, we propose EchoShot, a native and scalable multi-sh… ▽ More Video diffusion models substantially boost the productivity of artistic workflows with high-quality portrait video generative capacity. However, prevailing pipelines are primarily constrained to single-shot creation, while real-world applications urge for multiple shots with identity consistency and flexible content controllability. In this work, we propose EchoShot, a native and scalable multi-shot framework for portrait customization built upon a foundation video diffusion model. To start with, we propose shot-aware position embedding mechanisms within video diffusion transformer architecture to model inter-shot variations and establish intricate correspondence between multi-shot visual content and their textual descriptions. This simple yet effective design enables direct training on multi-shot video data without introducing additional computational overhead. To facilitate model training within multi-shot scenario, we construct PortraitGala, a large-scale and high-fidelity human-centric video dataset featuring cross-shot identity consistency and fine-grained captions such as facial attributes, outfits, and dynamic motions. To further enhance applicability, we extend EchoShot to perform reference image-based personalized multi-shot generation and long video synthesis with infinite shot counts. Extensive evaluations demonstrate that EchoShot achieves superior identity consistency as well as attribute-level controllability in multi-shot portrait video generation. Notably, the proposed framework demonstrates potential as a foundational paradigm for general multi-shot video modeling. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Facilitating Video Story Interaction with Multi-Agent Collaborative System

Authors: Yiwen Zhang, Jianing Hao, Zhan Wang, Hongling Sheng, Wei Zeng

Abstract: Video story interaction enables viewers to engage with and explore narrative content for personalized experiences. However, existing methods are limited to user selection, specially designed narratives, and lack customization. To address this, we propose an interactive system based on user intent. Our system uses a Vision Language Model (VLM) to enable machines to understand video stories, combini… ▽ More Video story interaction enables viewers to engage with and explore narrative content for personalized experiences. However, existing methods are limited to user selection, specially designed narratives, and lack customization. To address this, we propose an interactive system based on user intent. Our system uses a Vision Language Model (VLM) to enable machines to understand video stories, combining Retrieval-Augmented Generation (RAG) and a Multi-Agent System (MAS) to create evolving characters and scene experiences. It includes three stages: 1) Video story processing, utilizing VLM and prior knowledge to simulate human understanding of stories across three modalities. 2) Multi-space chat, creating growth-oriented characters through MAS interactions based on user queries and story stages. 3) Scene customization, expanding and visualizing various story scenes mentioned in dialogue. Applied to the Harry Potter series, our study shows the system effectively portrays emergent character social behavior and growth, enhancing the interactive experience in the video story world. △ Less

Submitted 2 May, 2025; originally announced May 2025.

Comments: Prepared and submitted in 2024

On the workflow, opportunities and challenges of developing foundation model in geophysics

Authors: Hanlin Sheng, Xinming Wu, Hang Gao, Haibin Di, Sergey Fomel, Jintao Li, Xu Si

Abstract: Foundation models, as a mainstream technology in artificial intelligence, have demonstrated immense potential across various domains in recent years, particularly in handling complex tasks and multimodal data. In the field of geophysics, although the application of foundation models is gradually expanding, there is currently a lack of comprehensive reviews discussing the full workflow of integrati… ▽ More Foundation models, as a mainstream technology in artificial intelligence, have demonstrated immense potential across various domains in recent years, particularly in handling complex tasks and multimodal data. In the field of geophysics, although the application of foundation models is gradually expanding, there is currently a lack of comprehensive reviews discussing the full workflow of integrating foundation models with geophysical data. To address this gap, this paper presents a complete framework that systematically explores the entire process of developing foundation models in conjunction with geophysical data. From data collection and preprocessing to model architecture selection, pre-training strategies, and model deployment, we provide a detailed analysis of the key techniques and methodologies at each stage. In particular, considering the diversity, complexity, and physical consistency constraints of geophysical data, we discuss targeted solutions to address these challenges. Furthermore, we discuss how to leverage the transfer learning capabilities of foundation models to reduce reliance on labeled data, enhance computational efficiency, and incorporate physical constraints into model training, thereby improving physical consistency and interpretability. Through a comprehensive summary and analysis of the current technological landscape, this paper not only fills the gap in the geophysics domain regarding a full-process review of foundation models but also offers valuable practical guidance for their application in geophysical data analysis, driving innovation and advancement in the field. △ Less

Submitted 25 April, 2025; v1 submitted 24 April, 2025; originally announced April 2025.

Knitting Robots: A Deep Learning Approach for Reverse-Engineering Fabric Patterns

Authors: Haoliang Sheng, Songpu Cai, Xingyu Zheng, Meng Cheng Lau

Abstract: Knitting, a cornerstone of textile manufacturing, is uniquely challenging to automate, particularly in terms of converting fabric designs into precise, machine-readable instructions. This research bridges the gap between textile production and robotic automation by proposing a novel deep learning-based pipeline for reverse knitting to integrate vision-based robotic systems into textile manufacturi… ▽ More Knitting, a cornerstone of textile manufacturing, is uniquely challenging to automate, particularly in terms of converting fabric designs into precise, machine-readable instructions. This research bridges the gap between textile production and robotic automation by proposing a novel deep learning-based pipeline for reverse knitting to integrate vision-based robotic systems into textile manufacturing. The pipeline employs a two-stage architecture, enabling robots to first identify front labels before inferring complete labels, ensuring accurate, scalable pattern generation. By incorporating diverse yarn structures, including single-yarn (sj) and multi-yarn (mj) patterns, this study demonstrates how our system can adapt to varying material complexities. Critical challenges in robotic textile manipulation, such as label imbalance, underrepresented stitch types, and the need for fine-grained control, are addressed by leveraging specialized deep-learning architectures. This work establishes a foundation for fully automated robotic knitting systems, enabling customizable, flexible production processes that integrate perception, planning, and actuation, thereby advancing textile manufacturing through intelligent robotic automation. △ Less

Submitted 18 April, 2025; originally announced April 2025.

Journal ref: Electronics, 14(8), 1605 (2025)

AROMA: Autonomous Rank-one Matrix Adaptation

Authors: Hao Nan Sheng, Zhi-yong Wang, Mingrui Yang, Hing Cheung So

Abstract: As large language models continue to grow in size, parameter-efficient fine-tuning (PEFT) has become increasingly crucial. While low-rank adaptation (LoRA) offers a solution through low-rank updates, its static rank allocation may yield suboptimal results. Adaptive low-rank adaptation (AdaLoRA) improves this with dynamic allocation but remains sensitive to initial and target rank configurations. W… ▽ More As large language models continue to grow in size, parameter-efficient fine-tuning (PEFT) has become increasingly crucial. While low-rank adaptation (LoRA) offers a solution through low-rank updates, its static rank allocation may yield suboptimal results. Adaptive low-rank adaptation (AdaLoRA) improves this with dynamic allocation but remains sensitive to initial and target rank configurations. We introduce AROMA, a framework that automatically constructs layer-specific updates by iteratively building up rank-one components with very few trainable parameters that gradually diminish to zero. Unlike existing methods that employ rank reduction mechanisms, AROMA introduces a dual-loop architecture for rank growth. The inner loop extracts information from each rank-one subspace, while the outer loop determines the number of rank-one subspaces, i.e., the optimal rank. We reset optimizer states to maintain subspace independence. AROMA significantly reduces parameters compared to LoRA and AdaLoRA while achieving superior performance on natural language understanding and commonsense reasoning tasks, offering new insights into adaptive PEFT. The code is available at \href{https://github.com/ShuDun23/AROMA}{AROMA}. △ Less

Submitted 11 April, 2025; v1 submitted 6 April, 2025; originally announced April 2025.

OpenAI o1 System Card

Authors: OpenAI, :, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, Andre Saraiva, Andrea Vallone, Andrew Duberstein, Andrew Kondrich , et al. (238 additional authors not shown)

Abstract: The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-ar… ▽ More The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations. △ Less

Submitted 21 December, 2024; originally announced December 2024.

EVA-S3PC: Efficient, Verifiable, Accurate Secure Matrix Multiplication Protocol Assembly and Its Application in Regression

Authors: Shizhao Peng, Tianrui Liu, Tianle Tao, Derun Zhao, Hao Sheng, Haogang Zhu

Abstract: Efficient multi-party secure matrix multiplication is crucial for privacy-preserving machine learning, but existing mixed-protocol frameworks often face challenges in balancing security, efficiency, and accuracy. This paper presents an efficient, verifiable and accurate secure three-party computing (EVA-S3PC) framework that addresses these challenges with elementary 2-party and 3-party matrix oper… ▽ More Efficient multi-party secure matrix multiplication is crucial for privacy-preserving machine learning, but existing mixed-protocol frameworks often face challenges in balancing security, efficiency, and accuracy. This paper presents an efficient, verifiable and accurate secure three-party computing (EVA-S3PC) framework that addresses these challenges with elementary 2-party and 3-party matrix operations based on data obfuscation techniques. We propose basic protocols for secure matrix multiplication, inversion, and hybrid multiplication, ensuring privacy and result verifiability. Experimental results demonstrate that EVA-S3PC achieves up to 14 significant decimal digits of precision in Float64 calculations, while reducing communication overhead by up to $54.8\%$ compared to state of art methods. Furthermore, 3-party regression models trained using EVA-S3PC on vertically partitioned data achieve accuracy nearly identical to plaintext training, which illustrates its potential in scalable, efficient, and accurate solution for secure collaborative modeling across domains. △ Less

Submitted 5 November, 2024; originally announced November 2024.

Comments: 18 pages,22 figures

MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset

Authors: Xin Shen, Heming Du, Hongwei Sheng, Shuyun Wang, Hui Chen, Huiqiang Chen, Zhuojie Wu, Xiaobiao Du, Jiaying Ying, Ruihan Lu, Qingzheng Xu, Xin Yu

Abstract: Isolated Sign Language Recognition (ISLR) focuses on identifying individual sign language glosses. Considering the diversity of sign languages across geographical regions, developing region-specific ISLR datasets is crucial for supporting communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale word-level dataset for the ISLR task. To fill t… ▽ More Isolated Sign Language Recognition (ISLR) focuses on identifying individual sign language glosses. Considering the diversity of sign languages across geographical regions, developing region-specific ISLR datasets is crucial for supporting communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale word-level dataset for the ISLR task. To fill this gap, we curate \underline{\textbf{the first}} large-scale Multi-view Multi-modal Word-Level Australian Sign Language recognition dataset, dubbed MM-WLAuslan. Compared to other publicly available datasets, MM-WLAuslan exhibits three significant advantages: (1) the largest amount of data, (2) the most extensive vocabulary, and (3) the most diverse of multi-modal camera views. Specifically, we record 282K+ sign videos covering 3,215 commonly used Auslan glosses presented by 73 signers in a studio environment. Moreover, our filming system includes two different types of cameras, i.e., three Kinect-V2 cameras and a RealSense camera. We position cameras hemispherically around the front half of the model and simultaneously record videos using all four cameras. Furthermore, we benchmark results with state-of-the-art methods for various multi-modal ISLR settings on MM-WLAuslan, including multi-view, cross-camera, and cross-view. Experiment results indicate that MM-WLAuslan is a challenging ISLR dataset, and we hope this dataset will contribute to the development of Auslan and the advancement of sign languages worldwide. All datasets and benchmarks are available at MM-WLAuslan. △ Less

Submitted 25 October, 2024; originally announced October 2024.

A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys

Authors: Hang Gao, Xinming Wu, Luming Liang, Hanlin Sheng, Xu Si, Gao Hui, Yaxing Li

Abstract: Seismic geobody interpretation is crucial for structural geology studies and various engineering applications. Existing deep learning methods show promise but lack support for multi-modal inputs and struggle to generalize to different geobody types or surveys. We introduce a promptable foundation model for interpreting any geobodies across seismic surveys. This model integrates a pre-trained visio… ▽ More Seismic geobody interpretation is crucial for structural geology studies and various engineering applications. Existing deep learning methods show promise but lack support for multi-modal inputs and struggle to generalize to different geobody types or surveys. We introduce a promptable foundation model for interpreting any geobodies across seismic surveys. This model integrates a pre-trained vision foundation model (VFM) with a sophisticated multi-modal prompt engine. The VFM, pre-trained on massive natural images and fine-tuned on seismic data, provides robust feature extraction for cross-survey generalization. The prompt engine incorporates multi-modal prior information to iteratively refine geobody delineation. Extensive experiments demonstrate the model's superior accuracy, scalability from 2D to 3D, and generalizability to various geobody types, including those unseen during training. To our knowledge, this is the first highly scalable and versatile multi-modal foundation model capable of interpreting any geobodies across surveys while supporting real-time interactions. Our approach establishes a new paradigm for geoscientific data interpretation, with broad potential for transfer to other tasks. △ Less

Submitted 13 September, 2024; v1 submitted 7 September, 2024; originally announced September 2024.

The Transferability of Downsamped Sparse Graph Convolutional Networks

Authors: Qinji Shu, Hang Sheng, Feng Ji, Hui Feng, Bo Hu

Abstract: To accelerate the training of graph convolutional networks (GCNs) on real-world large-scale sparse graphs, downsampling methods are commonly employed as a preprocessing step. However, the effects of graph sparsity and topological structure on the transferability of downsampling methods have not been rigorously analyzed or theoretically guaranteed, particularly when the topological structure is aff… ▽ More To accelerate the training of graph convolutional networks (GCNs) on real-world large-scale sparse graphs, downsampling methods are commonly employed as a preprocessing step. However, the effects of graph sparsity and topological structure on the transferability of downsampling methods have not been rigorously analyzed or theoretically guaranteed, particularly when the topological structure is affected by graph sparsity. In this paper, we introduce a novel downsampling method based on a sparse random graph model and derive an expected upper bound for the transfer error. Our findings show that smaller original graph sizes, higher expected average degrees, and increased sampling rates contribute to reducing this upper bound. Experimental results validate the theoretical predictions. By incorporating both sparsity and topological similarity into the model, this study establishes an upper bound on the transfer error for downsampling in the training of large-scale sparse graphs and provides insight into the influence of topological structure on transfer performance. △ Less

Submitted 8 September, 2024; v1 submitted 30 August, 2024; originally announced August 2024.

Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis

Authors: Zhixiang Guo, Xinming Wu, Luming Liang, Hanlin Sheng, Nuo Chen, Zhengfa Bi

Abstract: We explore adapting foundation models (FMs) from the computer vision domain to geoscience. FMs, large neural networks trained on massive datasets, excel in diverse tasks with remarkable adaptability and generality. However, geoscience faces challenges like lacking curated training datasets and high computational costs for developing specialized FMs. This study considers adapting FMs from computer… ▽ More We explore adapting foundation models (FMs) from the computer vision domain to geoscience. FMs, large neural networks trained on massive datasets, excel in diverse tasks with remarkable adaptability and generality. However, geoscience faces challenges like lacking curated training datasets and high computational costs for developing specialized FMs. This study considers adapting FMs from computer vision to geoscience, analyzing their scale, adaptability, and generality for geoscientific data analysis. We introduce a workflow that leverages existing computer vision FMs, fine-tuning them for geoscientific tasks, reducing development costs while enhancing accuracy. Through experiments, we demonstrate this workflow's effectiveness in broad applications to process and interpret geoscientific data of lunar images, seismic data, DAS arrays and so on. Our findings introduce advanced ML techniques to geoscience, proving the feasibility and advantages of cross-domain FMs adaptation, driving further advancements in geoscientific data analysis and offering valuable insights for FMs applications in other scientific domains. △ Less

Submitted 22 August, 2024; originally announced August 2024.

FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning

Authors: Jinhui Pang, Changqing Lin, Xiaoshuai Hao, Rong Yin, Zixuan Wang, Zhihui Zhang, Jinglin He, Huang Tai Sheng

Abstract: Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experience replay (ER) method receives widespread attention due to its superior performance. However, existing ER methods focus on identifying samples by feature significance or topological relevance, which limits their utiliz… ▽ More Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experience replay (ER) method receives widespread attention due to its superior performance. However, existing ER methods focus on identifying samples by feature significance or topological relevance, which limits their utilization of comprehensive graph data. In addition, the topology-based ER methods only consider local topological information and add neighboring nodes to the buffer, which ignores the global topological information and increases memory overhead. To bridge these gaps, we propose a novel method called Feature-Topology Fusion-based Experience Replay (FTF-ER) to effectively mitigate the catastrophic forgetting issue with enhanced efficiency. Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes. Moreover, to further utilize global topological information, we propose Hodge Potential Score (HPS) as a novel module to calculate the topological importance of nodes. HPS derives a global node ranking via Hodge decomposition on graphs, providing more accurate global topological information compared to neighbor sampling. By excluding neighbor sampling, HPS significantly reduces buffer storage costs for acquiring topological information and simultaneously decreases training time. Compared with state-of-the-art methods, FTF-ER achieves a significant improvement of 3.6% in AA and 7.1% in AF on the OGB-Arxiv dataset, demonstrating its superior performance in the class-incremental learning setting. △ Less

Submitted 8 August, 2024; v1 submitted 28 July, 2024; originally announced July 2024.

Comments: Accepted by ACM Multimedia 2024

PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models

Authors: Jinhua Zhang, Hualian Sheng, Sijia Cai, Bing Deng, Qiao Liang, Wen Li, Ying Fu, Jieping Ye, Shuhang Gu

Abstract: Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or Contr… ▽ More Controllable generation is considered a potentially vital approach to address the challenge of annotating 3D data, and the precision of such controllable generation becomes particularly imperative in the context of data production for autonomous driving. Existing methods focus on the integration of diverse generative information into controlling inputs, utilizing frameworks such as GLIGEN or ControlNet, to produce commendable outcomes in controllable generation. However, such approaches intrinsically restrict generation performance to the learning capacities of predefined network architectures. In this paper, we explore the innovative integration of controlling information and introduce PerLDiff (\textbf{Per}spective-\textbf{L}ayout \textbf{Diff}usion Models), a novel method for effective street view image generation that fully leverages perspective 3D geometric information. Our PerLDiff employs 3D geometric priors to guide the generation of street view images with precise object-level control within the network learning process, resulting in a more robust and controllable output. Moreover, it demonstrates superior controllability compared to alternative layout control methods. Empirical results justify that our PerLDiff markedly enhances the precision of controllable generation on the NuScenes and KITTI datasets. △ Less

Submitted 15 July, 2025; v1 submitted 8 July, 2024; originally announced July 2024.

Comments: Accepted by ICCV 2025

CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer

Authors: Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Qiao Liang, Min-Jian Zhao, Jieping Ye

Abstract: The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of flexibility and scalability, with ample room for advancements in performance. In this paper, our objective is to address these limitations by introducing two fram… ▽ More The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of flexibility and scalability, with ample room for advancements in performance. In this paper, our objective is to address these limitations by introducing two frameworks for 3D object detection with minimal hand-crafted design. Firstly, we propose CT3D, which sequentially performs raw-point-based embedding, a standard Transformer encoder, and a channel-wise decoder for point features within each proposal. Secondly, we present an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information. Additionally, CT3D ++ utilizes a point-to-key bidirectional encoder for more efficient feature encoding with reduced computational cost. By replacing the corresponding components of CT3D with these novel modules, CT3D++ achieves state-of-the-art performance on both the KITTI dataset and the large-scale Way\-mo Open Dataset. The source code for our frameworks will be made accessible at https://github.com/hlsheng1/CT3D-plusplus. △ Less

Submitted 12 June, 2024; originally announced June 2024.

Comments: 19 pages, 8 figures

3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views

Authors: Xiaobiao Du, Yida Wang, Haiyang Sun, Zhuojie Wu, Hongwei Sheng, Shuyun Wang, Jiaying Ying, Ming Lu, Tianqing Zhu, Kun Zhan, Xin Yu

Abstract: 3D cars are commonly used in self-driving systems, virtual/augmented reality, and games. However, existing 3D car datasets are either synthetic or low-quality, limiting their applications in practical scenarios and presenting a significant gap toward high-quality real-world 3D car datasets. In this paper, we propose the first large-scale 3D real car dataset, termed 3DRealCar, offering three distin… ▽ More 3D cars are commonly used in self-driving systems, virtual/augmented reality, and games. However, existing 3D car datasets are either synthetic or low-quality, limiting their applications in practical scenarios and presenting a significant gap toward high-quality real-world 3D car datasets. In this paper, we propose the first large-scale 3D real car dataset, termed 3DRealCar, offering three distinctive features. (1) \textbf{High-Volume}: 2,500 cars are meticulously scanned by smartphones, obtaining car images and point clouds with real-world dimensions; (2) \textbf{High-Quality}: Each car is captured in an average of 200 dense, high-resolution 360-degree RGB-D views, enabling high-fidelity 3D reconstruction; (3) \textbf{High-Diversity}: The dataset contains various cars from over 100 brands, collected under three distinct lighting conditions, including reflective, standard, and dark. Additionally, we offer detailed car parsing maps for each instance to promote research in car parsing tasks. Moreover, we remove background point clouds and standardize the car orientation to a unified axis for the reconstruction only on cars and controllable rendering without background. We benchmark 3D reconstruction results with state-of-the-art methods across different lighting conditions in 3DRealCar. Extensive experiments demonstrate that the standard lighting condition part of 3DRealCar can be used to produce a large number of high-quality 3D cars, improving various 2D and 3D tasks related to cars. Notably, our dataset brings insight into the fact that recent 3D reconstruction methods face challenges in reconstructing high-quality 3D cars under reflective and dark lighting conditions. \textcolor{red}{\href{https://xiaobiaodu.github.io/3drealcar/}{Our dataset is here.}} △ Less

Submitted 29 June, 2025; v1 submitted 7 June, 2024; originally announced June 2024.

Comments: Project Page: https://xiaobiaodu.github.io/3drealcar

Journal ref: ICCV2025

Know in AdVance: Linear-Complexity Forecasting of Ad Campaign Performance with Evolving User Interest

Authors: XiaoYu Wang, YongHui Guo, Hui Sheng, Peili Lv, Chi Zhou, Wei Huang, ShiQin Ta, Dongbo Huang, XiuJin Yang, Lan Xu, Hao Zhou, Yusheng Ji

Abstract: Real-time Bidding (RTB) advertisers wish to \textit{know in advance} the expected cost and yield of ad campaigns to avoid trial-and-error expenses. However, Campaign Performance Forecasting (CPF), a sequence modeling task involving tens of thousands of ad auctions, poses challenges of evolving user interest, auction representation, and long context, making coarse-grained and static-modeling method… ▽ More Real-time Bidding (RTB) advertisers wish to \textit{know in advance} the expected cost and yield of ad campaigns to avoid trial-and-error expenses. However, Campaign Performance Forecasting (CPF), a sequence modeling task involving tens of thousands of ad auctions, poses challenges of evolving user interest, auction representation, and long context, making coarse-grained and static-modeling methods sub-optimal. We propose \textit{AdVance}, a time-aware framework that integrates local auction-level and global campaign-level modeling. User preference and fatigue are disentangled using a time-positioned sequence of clicked items and a concise vector of all displayed items. Cross-attention, conditioned on the fatigue vector, captures the dynamics of user interest toward each candidate ad. Bidders compete with each other, presenting a complete graph similar to the self-attention mechanism. Hence, we employ a Transformer Encoder to compress each auction into embedding by solving auxiliary tasks. These sequential embeddings are then summarized by a conditional state space model (SSM) to comprehend long-range dependencies while maintaining global linear complexity. Considering the irregular time intervals between auctions, we make SSM's parameters dependent on the current auction embedding and the time interval. We further condition SSM's global predictions on the accumulation of local results. Extensive evaluations and ablation studies demonstrate its superiority over state-of-the-art methods. AdVance has been deployed on the Tencent Advertising platform, and A/B tests show a remarkable 4.5\% uplift in Average Revenue per User (ARPU). △ Less

Submitted 17 May, 2024; originally announced May 2024.

Comments: 12 pages, 4 figures, accepted at ACM SIGKDD 2024

RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception

Authors: Xiaosu Zhu, Hualian Sheng, Sijia Cai, Bing Deng, Shaopeng Yang, Qiao Liang, Ken Chen, Lianli Gao, Jingkuan Song, Jieping Ye

Abstract: We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes. The highlights of RoScenes include significantly large perception area, full scene coverage and crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D annotations within… ▽ More We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes. The highlights of RoScenes include significantly large perception area, full scene coverage and crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D annotations within 64,000 $m^2$. To relieve the expensive costs of roadside 3D labeling, we present a novel BEV-to-3D joint annotation pipeline to efficiently collect such a large volume of data. After that, we organize a comprehensive study for current BEV methods on RoScenes in terms of effectiveness and efficiency. Tested methods suffer from the vast perception area and variation of sensor layout across scenes, resulting in performance levels falling below expectations. To this end, we propose RoBEV that incorporates feature-guided position embedding for effective 2D-3D feature assignment. With its help, our method outperforms state-of-the-art by a large margin without extra computational overhead on validation set. Our dataset and devkit will be made available at https://github.com/xiaosu-zhu/RoScenes. △ Less

Submitted 4 July, 2024; v1 submitted 16 May, 2024; originally announced May 2024.

Comments: ECCV 2024. Extended version. 33 pages, 21 figures, 13 tables. https://github.com/xiaosu-zhu/RoScenes

BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning

Authors: Haoyue Sheng, Linrui Ma, Jean-Francois Samson, Dianbo Liu

Abstract: Background: Chest X-ray imaging-based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficien… ▽ More Background: Chest X-ray imaging-based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, by developing a self-supervised learning strategy called "BarlwoTwins-CXR". Methods: We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). Results: Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. Conclusion: BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. △ Less

Submitted 9 February, 2024; originally announced February 2024.

Comments: 15 pages, 7 figures, 3 tables

ACM Class: I.2.1; J.3; I.4.9

Divide and Ensemble: Progressively Learning for the Unknown

Authors: Hu Zhang, Xin Shen, Heming Du, Huiqiang Chen, Chen Liu, Hongwei Sheng, Qingzheng Xu, MD Wahiduzzaman Khan, Qingtao Yu, Tianqing Zhu, Scott Chapman, Zi Huang, Xin Yu

Abstract: In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions. We find that (1) test images are provided in the challenge; (2) samples are equipped with their collection dates; (3) the samples of different dates show notable discrepancies. Based on the findings, we partition the dataset into discrete groups by th… ▽ More In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions. We find that (1) test images are provided in the challenge; (2) samples are equipped with their collection dates; (3) the samples of different dates show notable discrepancies. Based on the findings, we partition the dataset into discrete groups by the dates and train models on each divided group. We then adopt the pseudo-labeling approach to label the test data and incorporate those with high confidence into the training set. In pseudo-labeling, we leverage models ensemble with different architectures to enhance the reliability of predictions. The pseudo-labeling and ensembled model training are iteratively conducted until all test samples are labeled. Finally, the separated models for each group are unified to obtain the model for the whole dataset. Our method achieves an average of 93.6\% Top-1 test accuracy~(94.0\% on WW2020 and 93.2\% on WR2021) and wins the 1$st$ place in the Deep Nutrient Deficiency Challenge~\footnote{https://cvppa2023.github.io/challenges/}. △ Less

Submitted 9 October, 2023; originally announced October 2023.

SeisCLIP: A seismology foundation model pre-trained by multi-modal data for multi-purpose seismic feature extraction

Authors: Xu Si, Xinming Wu, Hanlin Sheng, Jun Zhu, Zefeng Li

Abstract: Training specific deep learning models for particular tasks is common across various domains within seismology. However, this approach encounters two limitations: inadequate labeled data for certain tasks and limited generalization across regions. To address these challenges, we develop SeisCLIP, a seismology foundation model trained through contrastive learning from multi-modal data. It consists… ▽ More Training specific deep learning models for particular tasks is common across various domains within seismology. However, this approach encounters two limitations: inadequate labeled data for certain tasks and limited generalization across regions. To address these challenges, we develop SeisCLIP, a seismology foundation model trained through contrastive learning from multi-modal data. It consists of a transformer encoder for extracting crucial features from time-frequency seismic spectrum and an MLP encoder for integrating the phase and source information of the same event. These encoders are jointly pre-trained on a vast dataset and the spectrum encoder is subsequently fine-tuned on smaller datasets for various downstream tasks. Notably, SeisCLIP's performance surpasses that of baseline methods in event classification, localization, and focal mechanism analysis tasks, employing distinct datasets from different regions. In conclusion, SeisCLIP holds significant potential as a foundational model in the field of seismology, paving the way for innovative directions in foundation-model-based seismology research. △ Less

Submitted 5 September, 2023; originally announced September 2023.

Comments: 27 pages, 9 figures, 4 tables

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

Authors: MD Wahiduzzaman Khan, Hongwei Sheng, Hu Zhang, Heming Du, Sen Wang, Minas Theodore Coroneo, Farshid Hajati, Sahar Shariflou, Michael Kalloniatis, Jack Phu, Ashish Agar, Zi Huang, Mojtaba Golzan, Xin Yu

Abstract: Retinal vessel segmentation is generally grounded in image-based datasets collected with bench-top devices. The static images naturally lose the dynamic characteristics of retina fluctuation, resulting in diminished dataset richness, and the usage of bench-top devices further restricts dataset scalability due to its limited accessibility. Considering these limitations, we introduce the first video… ▽ More Retinal vessel segmentation is generally grounded in image-based datasets collected with bench-top devices. The static images naturally lose the dynamic characteristics of retina fluctuation, resulting in diminished dataset richness, and the usage of bench-top devices further restricts dataset scalability due to its limited accessibility. Considering these limitations, we introduce the first video-based retinal dataset by employing handheld devices for data acquisition. The dataset comprises 635 smartphone-based fundus videos collected from four different clinics, involving 415 patients from 50 to 75 years old. It delivers comprehensive and precise annotations of retinal structures in both spatial and temporal dimensions, aiming to advance the landscape of vasculature segmentation. Specifically, the dataset provides three levels of spatial annotations: binary vessel masks for overall retinal structure delineation, general vein-artery masks for distinguishing the vein and artery, and fine-grained vein-artery masks for further characterizing the granularities of each artery and vein. In addition, the dataset offers temporal annotations that capture the vessel pulsation characteristics, assisting in detecting ocular diseases that require fine-grained recognition of hemodynamic fluctuation. In application, our dataset exhibits a significant domain shift with respect to data captured by bench-top devices, thus posing great challenges to existing methods. In the experiments, we provide evaluation metrics and benchmark results on our dataset, reflecting both the potential and challenges it offers for vessel segmentation tasks. We hope this challenging dataset would significantly contribute to the development of eye disease diagnosis and early prevention. △ Less

Submitted 13 July, 2023; originally announced July 2023.

Discriminating Human-authored from ChatGPT-Generated Code Via Discernable Feature Analysis

Authors: Li Ke, Hong Sheng, Fu Cai, Zhang Yunhe, Liu Ming

Abstract: The ubiquitous adoption of Large Language Generation Models (LLMs) in programming has underscored the importance of differentiating between human-written code and code generated by intelligent models. This paper specifically aims to distinguish code generated by ChatGPT from that authored by humans. Our investigation reveals disparities in programming style, technical level, and readability betwee… ▽ More The ubiquitous adoption of Large Language Generation Models (LLMs) in programming has underscored the importance of differentiating between human-written code and code generated by intelligent models. This paper specifically aims to distinguish code generated by ChatGPT from that authored by humans. Our investigation reveals disparities in programming style, technical level, and readability between these two sources. Consequently, we develop a discriminative feature set for differentiation and evaluate its efficacy through ablation experiments. Additionally, we devise a dataset cleansing technique, which employs temporal and spatial segmentation, to mitigate the dearth of datasets and to secure high-caliber, uncontaminated datasets. To further enrich data resources, we employ "code transformation," "feature transformation," and "feature customization" techniques, generating an extensive dataset comprising 10,000 lines of ChatGPT-generated code. The salient contributions of our research include: proposing a discriminative feature set yielding high accuracy in differentiating ChatGPT-generated code from human-authored code in binary classification tasks; devising methods for generating extensive ChatGPT-generated codes; and introducing a dataset cleansing strategy that extracts immaculate, high-grade code datasets from open-source repositories, thus achieving exceptional accuracy in code authorship attribution tasks. △ Less

Submitted 4 July, 2023; v1 submitted 25 June, 2023; originally announced June 2023.

Comments: 11 pages, 8 figures, 3 tables

Sentence-level Event Detection without Triggers via Prompt Learning and Machine Reading Comprehension

Authors: Tongtao Ling, Lei Chen, Huangxu Sheng, Zicheng Cai, Hai-Lin Liu

Abstract: The traditional way of sentence-level event detection involves two important subtasks: trigger identification and trigger classifications, where the identified event trigger words are used to classify event types from sentences. However, trigger classification highly depends on abundant annotated trigger words and the accuracy of trigger identification. In a real scenario, annotating trigger words… ▽ More The traditional way of sentence-level event detection involves two important subtasks: trigger identification and trigger classifications, where the identified event trigger words are used to classify event types from sentences. However, trigger classification highly depends on abundant annotated trigger words and the accuracy of trigger identification. In a real scenario, annotating trigger words is time-consuming and laborious. For this reason, we propose a trigger-free event detection model, which transforms event detection into a two-tower model based on machine reading comprehension and prompt learning. Compared to existing trigger-based and trigger-free methods, experimental studies on two event detection benchmark datasets (ACE2005 and MAVEN) have shown that the proposed approach can achieve competitive performance. △ Less

Submitted 25 June, 2023; originally announced June 2023.

Comments: 14 pages, accepted by ADMA 2023

Autonomous Stabilization of Retinal Videos for Streamlining Assessment of Spontaneous Venous Pulsations

Authors: Hongwei Sheng, Xin Yu, Feiyu Wang, MD Wahiduzzaman Khan, Hexuan Weng, Sahar Shariflou, S. Mojtaba Golzan

Abstract: Spontaneous retinal Venous Pulsations (SVP) are rhythmic changes in the caliber of the central retinal vein and are observed in the optic disc region (ODR) of the retina. Its absence is a critical indicator of various ocular or neurological abnormalities. Recent advances in imaging technology have enabled the development of portable smartphone-based devices for observing the retina and assessment… ▽ More Spontaneous retinal Venous Pulsations (SVP) are rhythmic changes in the caliber of the central retinal vein and are observed in the optic disc region (ODR) of the retina. Its absence is a critical indicator of various ocular or neurological abnormalities. Recent advances in imaging technology have enabled the development of portable smartphone-based devices for observing the retina and assessment of SVPs. However, the quality of smartphone-based retinal videos is often poor due to noise and image jitting, which in return, can severely obstruct the observation of SVPs. In this work, we developed a fully automated retinal video stabilization method that enables the examination of SVPs captured by various mobile devices. Specifically, we first propose an ODR Spatio-Temporal Localization (ODR-STL) module to localize visible ODR and remove noisy and jittering frames. Then, we introduce a Noise-Aware Template Matching (NATM) module to stabilize high-quality video segments at a fixed position in the field of view. After the processing, the SVPs can be easily observed in the stabilized videos, significantly facilitating user observations. Furthermore, our method is cost-effective and has been tested in both subjective and objective evaluations. Both of the evaluations support its effectiveness in facilitating the observation of SVPs. This can improve the timely diagnosis and treatment of associated diseases, making it a valuable tool for eye health professionals. △ Less

Submitted 10 May, 2023; originally announced May 2023.

Comments: EMBC, 4 pages, 6 figures

Detecting Neighborhood Gentrification at Scale via Street-level Visual Data

Authors: Tianyuan Huang, Timothy Dai, Zhecheng Wang, Hesu Yoon, Hao Sheng, Andrew Y. Ng, Ram Rajagopal, Jackelyn Hwang

Abstract: Neighborhood gentrification plays a significant role in shaping the social and economic well-being of both individuals and communities at large. While some efforts have been made to detect gentrification in cities, existing approaches rely mainly on estimated measures from survey data, require substantial work of human labeling, and are limited in characterizing the neighborhood as a whole. We pro… ▽ More Neighborhood gentrification plays a significant role in shaping the social and economic well-being of both individuals and communities at large. While some efforts have been made to detect gentrification in cities, existing approaches rely mainly on estimated measures from survey data, require substantial work of human labeling, and are limited in characterizing the neighborhood as a whole. We propose a novel approach to detecting neighborhood gentrification at a large-scale based on the physical appearance of neighborhoods by incorporating historical street-level visual data. We show the effectiveness of the proposed method by comparing results from our approach with gentrification measures from previous literature and case studies. Our approach has the potential to supplement existing indicators of gentrification and become a valid resource for urban researchers and policy makers. △ Less

Submitted 4 January, 2023; originally announced January 2023.

HHLPy: Practical Verification of Hybrid Systems using Hoare Logic

Authors: Huanhuan Sheng, Alexander Bentkamp, Bohua Zhan

Abstract: We present a tool for verification of hybrid systems expressed in the sequential fragment of HCSP (Hybrid Communicating Sequential Processes). The tool permits annotating HCSP programs with pre- and postconditions, invariants, and proof rules for reasoning about ordinary differential equations. Verification conditions are generated from the annotations following the rules of hybrid Hoare logic. We… ▽ More We present a tool for verification of hybrid systems expressed in the sequential fragment of HCSP (Hybrid Communicating Sequential Processes). The tool permits annotating HCSP programs with pre- and postconditions, invariants, and proof rules for reasoning about ordinary differential equations. Verification conditions are generated from the annotations following the rules of hybrid Hoare logic. We designed labeling and highlighting mechanisms to distinguish and visualize different verification conditions. The tool is implemented in Python and has a web-based user interface. We evaluated the effectiveness of the tool on translations of Simulink/Stateflow models and on KeYmaera X benchmarks. △ Less

Submitted 21 February, 2023; v1 submitted 31 October, 2022; originally announced October 2022.

Optimal Probabilistic Constellation Shaping for Covert Communications

Authors: Shuai Ma, Yunqi Zhang, Haihong Sheng, Hang Li, Jia Shi, Long Yang, Youlong Wu, Naofal Al-Dhahir, Shiyin Li

Abstract: In this paper, we investigate the optimal probabilistic constellation shaping design for covert communication systems from a practical view. Different from conventional covert communications with equiprobable constellations modulation, we propose nonequiprobable constellations modulation schemes to further enhance the covert rate. Specifically, we derive covert rate expressions for practical discr… ▽ More In this paper, we investigate the optimal probabilistic constellation shaping design for covert communication systems from a practical view. Different from conventional covert communications with equiprobable constellations modulation, we propose nonequiprobable constellations modulation schemes to further enhance the covert rate. Specifically, we derive covert rate expressions for practical discrete constellation inputs for the first time. Then, we study the covert rate maximization problem by jointly optimizing the constellation distribution and power allocation. In particular, an approximate gradient descent method is proposed for obtaining the optimal probabilistic constellation shaping. To strike a balance between the computational complexity and the transmission performance, we further develop a framework that maximizes a lower bound on the achievable rate where the optimal probabilistic constellation shaping problem can be solved efficiently using the Frank-Wolfe method. Extensive numerical results show that the optimized probabilistic constellation shaping strategies provide significant gains in the achievable covert rate over the state-of-the-art schemes. △ Less

Submitted 30 August, 2022; originally announced August 2022.

Covert Beamforming Design for Integrated Radar Sensing and Communication Systems

Authors: Shuai Ma, Haihong Sheng, Ruixin Yang, Hang Li, Youlong Wu, Chao Shen, Naofal Al-Dhahir, Shiyin Li

Abstract: We propose covert beamforming design frameworks for integrated radar sensing and communication (IRSC) systems, where the radar can covertly communicate with legitimate users under the cover of the probing waveforms without being detected by the eavesdropper. Specifically, by jointly designing the target detection beamformer and communication beamformer, we aim to maximize the radar detection mutua… ▽ More We propose covert beamforming design frameworks for integrated radar sensing and communication (IRSC) systems, where the radar can covertly communicate with legitimate users under the cover of the probing waveforms without being detected by the eavesdropper. Specifically, by jointly designing the target detection beamformer and communication beamformer, we aim to maximize the radar detection mutual information (MI) (or the communication rate) subject to the covert constraint, the communication rate constraint (or the radar detection MI constraint), and the total power constraint. For the perfect eavesdropper's channel state information (CSI) scenario, we transform the covert beamforming design problems into a series of convex subproblems, by exploiting semidefinite relaxation, which can be solved via the bisection search method. Considering the high complexity of iterative optimization, we further propose a single-iterative covert beamformer design scheme based on the zero-forcing criterion. For the imperfect eavesdropper's CSI scenario, we develop a relaxation and restriction method to tackle the robust covert beamforming design problems. Simulation results demonstrate the effectiveness of the proposed covert beamforming schemes for perfect and imperfect CSI scenarios. △ Less

Submitted 11 August, 2022; originally announced August 2022.

Rethinking IoU-based Optimization for Single-stage 3D Object Detection

Authors: Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Min-Jian Zhao, Gim Hee Lee

Abstract: Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors. Recently, several 3D object detection methods adopt IoU-based optimization and directly replace the 2D IoU with 3D IoU. However, such a direct computation in 3D is… ▽ More Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors. Recently, several 3D object detection methods adopt IoU-based optimization and directly replace the 2D IoU with 3D IoU. However, such a direct computation in 3D is very costly due to the complex implementation and inefficient backward operations. Moreover, 3D IoU-based optimization is sub-optimal as it is sensitive to rotation and thus can cause training instability and detection performance deterioration. In this paper, we propose a novel Rotation-Decoupled IoU (RDIoU) method that can mitigate the rotation-sensitivity issue, and produce more efficient optimization objectives compared with 3D IoU during the training stage. Specifically, our RDIoU simplifies the complex interactions of regression parameters by decoupling the rotation variable as an independent term, yet preserving the geometry of 3D IoU. By incorporating RDIoU into both the regression and classification branches, the network is encouraged to learn more precise bounding boxes and concurrently overcome the misalignment issue between classification and regression. Extensive experiments on the benchmark KITTI and Waymo Open Dataset validate that our RDIoU method can bring substantial improvement for the single-stage 3D object detection. △ Less

Submitted 20 July, 2022; v1 submitted 19 July, 2022; originally announced July 2022.

Comments: Accepted by ECCV2022. The code is available at https://github.com/hlsheng1/RDIoU

Extracting Built Environment Features for Planning Research with Computer Vision: A Review and Discussion of State-of-the-Art Approaches

Authors: Meiqing Li, Hao Sheng

Abstract: This is an extended abstract for a presentation at The 17th International Conference on CUPUM - Computational Urban Planning and Urban Management in June 2021. This study presents an interdisciplinary synthesis of the state-of-the-art approaches in computer vision technologies to extract built environment features that could improve the robustness of empirical research in planning. We discussed th… ▽ More This is an extended abstract for a presentation at The 17th International Conference on CUPUM - Computational Urban Planning and Urban Management in June 2021. This study presents an interdisciplinary synthesis of the state-of-the-art approaches in computer vision technologies to extract built environment features that could improve the robustness of empirical research in planning. We discussed the findings from the review of studies in both planning and computer science. △ Less

Submitted 21 March, 2022; v1 submitted 29 January, 2022; originally announced January 2022.

Comments: CUPUM 2021 (The 17th International Conference on Computational Urban Planning and Urban Management)

Improving 3D Object Detection with Channel-wise Transformer

Authors: Hualian Sheng, Sijia Cai, Yuan Liu, Bing Deng, Jianqiang Huang, Xian-Sheng Hua, Min-Jian Zhao

Abstract: Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on human-designed components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerfu… ▽ More Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on human-designed components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerful 3D object representations. Such methods, however, have limited ability to capture rich contextual dependencies among points. In this paper, we leverage the high-quality region proposal network and a Channel-wise Transformer architecture to constitute our two-stage 3D object detection framework (CT3D) with minimal hand-crafted design. The proposed CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation for the point features within each proposal. Specifically, CT3D uses proposal's keypoints for spatial contextual modelling and learns attention propagation in the encoding module, mapping the proposal to point embeddings. Next, a new channel-wise decoding module enriches the query-key interaction via channel-wise re-weighting to effectively merge multi-level contexts, which contributes to more accurate object predictions. Extensive experiments demonstrate that our CT3D method has superior performance and excellent scalability. Remarkably, CT3D achieves the AP of 81.77% in the moderate car category on the KITTI test 3D detection benchmark, outperforms state-of-the-art 3D detectors. △ Less

Submitted 14 September, 2021; v1 submitted 22 August, 2021; originally announced August 2021.

Comments: Accepted by ICCV2021

Probability Paths and the Structure of Predictions over Time

Authors: Zhiyuan Jerry Lin, Hao Sheng, Sharad Goel

Abstract: In settings ranging from weather forecasts to political prognostications to financial projections, probability estimates of future binary outcomes often evolve over time. For example, the estimated likelihood of rain on a specific day changes by the hour as new information becomes available. Given a collection of such probability paths, we introduce a Bayesian framework -- which we call the Gaussi… ▽ More In settings ranging from weather forecasts to political prognostications to financial projections, probability estimates of future binary outcomes often evolve over time. For example, the estimated likelihood of rain on a specific day changes by the hour as new information becomes available. Given a collection of such probability paths, we introduce a Bayesian framework -- which we call the Gaussian latent information martingale, or GLIM -- for modeling the structure of dynamic predictions over time. Suppose, for example, that the likelihood of rain in a week is 50 %, and consider two hypothetical scenarios. In the first, one expects the forecast to be equally likely to become either 25 % or 75 % tomorrow; in the second, one expects the forecast to stay constant for the next several days. A time-sensitive decision-maker might select a course of action immediately in the latter scenario, but may postpone their decision in the former, knowing that new information is imminent. We model these trajectories by assuming predictions update according to a latent process of information flow, which is inferred from historical data. In contrast to general methods for time series analysis, this approach preserves important properties of probability paths such as the martingale structure and appropriate amount of volatility and better quantifies future uncertainties around probability paths. We show that GLIM outperforms three popular baseline methods, producing better estimated posterior probability path distributions measured by three different metrics. By elucidating the dynamic structure of predictions over time, we hope to help individuals make more informed choices. △ Less

Submitted 4 November, 2021; v1 submitted 11 June, 2021; originally announced June 2021.

Journal ref: 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

Learning Neighborhood Representation from Multi-Modal Multi-Graph: Image, Text, Mobility Graph and Beyond

Authors: Tianyuan Huang, Zhecheng Wang, Hao Sheng, Andrew Y. Ng, Ram Rajagopal

Abstract: Recent urbanization has coincided with the enrichment of geotagged data, such as street view and point-of-interest (POI). Region embedding enhanced by the richer data modalities has enabled researchers and city administrators to understand the built environment, socioeconomics, and the dynamics of cities better. While some efforts have been made to simultaneously use multi-modal inputs, existing m… ▽ More Recent urbanization has coincided with the enrichment of geotagged data, such as street view and point-of-interest (POI). Region embedding enhanced by the richer data modalities has enabled researchers and city administrators to understand the built environment, socioeconomics, and the dynamics of cities better. While some efforts have been made to simultaneously use multi-modal inputs, existing methods can be improved by incorporating different measures of 'proximity' in the same embedding space - leveraging not only the data that characterizes the regions (e.g., street view, local businesses pattern) but also those that depict the relationship between regions (e.g., trips, road network). To this end, we propose a novel approach to integrate multi-modal geotagged inputs as either node or edge features of a multi-graph based on their relations with the neighborhood region (e.g., tiles, census block, ZIP code region, etc.). We then learn the neighborhood representation based on a contrastive-sampling scheme from the multi-graph. Specifically, we use street view images and POI features to characterize neighborhoods (nodes) and use human mobility to characterize the relationship between neighborhoods (directed edges). We show the effectiveness of the proposed methods with quantitative downstream tasks as well as qualitative analysis of the embedding space: The embedding we trained outperforms the ones using only unimodal data as regional inputs. △ Less

Submitted 6 May, 2021; originally announced May 2021.

Surveilling Surveillance: Estimating the Prevalence of Surveillance Cameras with Street View Data

Authors: Hao Sheng, Keniel Yao, Sharad Goel

Abstract: The use of video surveillance in public spaces -- both by government agencies and by private citizens -- has attracted considerable attention in recent years, particularly in light of rapid advances in face-recognition technology. But it has been difficult to systematically measure the prevalence and placement of cameras, hampering efforts to assess the implications of surveillance on privacy and… ▽ More The use of video surveillance in public spaces -- both by government agencies and by private citizens -- has attracted considerable attention in recent years, particularly in light of rapid advances in face-recognition technology. But it has been difficult to systematically measure the prevalence and placement of cameras, hampering efforts to assess the implications of surveillance on privacy and public safety. Here, we combine computer vision, human verification, and statistical analysis to estimate the spatial distribution of surveillance cameras. Specifically, we build a camera detection model and apply it to 1.6 million street view images sampled from 10 large U.S. cities and 6 other major cities around the world, with positive model detections verified by human experts. After adjusting for the estimated recall of our model, and accounting for the spatial coverage of our sampled images, we are able to estimate the density of surveillance cameras visible from the road. Across the 16 cities we consider, the estimated number of surveillance cameras per linear kilometer ranges from 0.2 (in Los Angeles) to 0.9 (in Seoul). In a detailed analysis of the 10 U.S. cities, we find that cameras are concentrated in commercial, industrial, and mixed zones, and in neighborhoods with higher shares of non-white residents -- a pattern that persists even after adjusting for land use. These results help inform ongoing discussions on the use of surveillance technology, including its potential disparate impacts on communities of color. △ Less

Submitted 30 August, 2021; v1 submitted 4 May, 2021; originally announced May 2021.

Comments: We now credit Turtiainen et al. (2020) both for creating a state-of-the-art camera detection model and for suggesting that computer vision could, in theory, be applied to street view data to map surveillance cameras. Also, we discovered a coding error in our image sampling strategy that corrupted our analysis of camera density over time. We have now removed the results of that analysis

Multi-Task Time Series Forecasting With Shared Attention

Authors: Zekai Chen, Jiaze E, Xiao Zhang, Hao Sheng, Xiuzheng Cheng

Abstract: Time series forecasting is a key component in many industrial and business decision processes and recurrent neural network (RNN) based models have achieved impressive progress on various time series forecasting tasks. However, most of the existing methods focus on single-task forecasting problems by learning separately based on limited supervised objectives, which often suffer from insufficient tr… ▽ More Time series forecasting is a key component in many industrial and business decision processes and recurrent neural network (RNN) based models have achieved impressive progress on various time series forecasting tasks. However, most of the existing methods focus on single-task forecasting problems by learning separately based on limited supervised objectives, which often suffer from insufficient training instances. As the Transformer architecture and other attention-based models have demonstrated its great capability of capturing long term dependency, we propose two self-attention based sharing schemes for multi-task time series forecasting which can train jointly across multiple tasks. We augment a sequence of paralleled Transformer encoders with an external public multi-head attention function, which is updated by all data of all tasks. Experiments on a number of real-world multi-task time series forecasting tasks show that our proposed architectures can not only outperform the state-of-the-art single-task forecasting baselines but also outperform the RNN-based multi-task forecasting method. △ Less

Submitted 23 January, 2021; originally announced January 2021.

Comments: Accepted by ICDMW 2020