Yang Jiao

Yang Jiao, Zequn Jie, Shaoxiang Chen et al.

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features from two drastically different modalities. Recent approaches aim at exploring the semantic densities of camera features through lifting points in 2D camera images (referred to as seeds) into 3D space, and then incorporate 2D semantics via cross-modal interaction or fusion techniques. However, depth information is under-investigated in these approaches when lifting points into 3D space, thus 2D semantics can not be reliably fused with 3D points. Moreover, their multi-modal fusion strategy, which is implemented as concatenation or attention, either can not effectively fuse 2D and 3D information or is unable to perform fine-grained interactions in the voxel space. To this end, we propose a novel framework with better utilization of the depth information and fine-grained cross-modal interaction between LiDAR and camera, which consists of two important components. First, a Multi-Depth Unprojection (MDU) method with depth-aware designs is used to enhance the depth quality of the lifted points at each interaction level. Second, a Gated Modality-Aware Convolution (GMA-Conv) block is applied to modulate voxels involved with the camera modality in a fine-grained manner and then aggregate multi-modal features into a unified space. Together they provide the detection head with more comprehensive features from LiDAR and camera. On the nuScenes test benchmark, our proposed method, abbreviated as MSMDFusion, achieves state-of-the-art 3D object detection results with 71.5% mAP and 74.0% NDS, and strong tracking results with 74.0% AMOTA without using test-time-augmentation and ensemble techniques. The code is available at https://github.com/SxJyJay/MSMDFusion.

Yang Jiao, Shaoxiang Chen, Zequn Jie et al.

3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation mining model, to support generating more descriptive and comprehensive captions. Technically, our MORE encodes object relations in a progressive manner since complex relations can be deduced from a limited number of basic ones. We first devise a novel Spatial Layout Graph Convolution (SLGC), which semantically encodes several first-order relations as edges of a graph constructed over 3D object proposals. Next, from the resulting graph, we further extract multiple triplets which encapsulate basic first-order relations as the basic unit, and construct several Object-centric Triplet Attention Graphs (OTAG) to infer multi-order relations for every target object. The updated node features from OTAG are aggregated and fed into the caption decoder to provide abundant relational cues, so that captions including diverse relations with context objects can be generated. Extensive experiments on the Scan2Cap dataset prove the effectiveness of our proposed MORE and its components, and we also outperform the current state-of-the-art method. Our code is available at https://github.com/SxJyJay/MORE.

Jiacheng Zhang, Yang Jiao, Shaoxiang Chen et al.

Recently, Multimodal Large Language Models (MLLMs) have made significant progress in the video comprehension field. Despite remarkable content reasoning and instruction following capabilities they demonstrated, the hallucination problem of these VideoLLMs is less explored compared with its counterpart in the image domain. To mitigate this gap, we propose EventHallusion, a novel benchmark that focuses on assessing the VideoLLMs' hallucination toward event, the crux of video analysis. From a hallucination attribution perspective, our EventHallusion benchmark is curated to assess a VideoLLM's susceptibility toward language priors and vision-language biases. On the other hand, we also propose a simple yet effective method, called Temporal Contrastive Decoding (TCD), to tackle the hallucination problems of VideoLLMs. The proposed TCD method rectifies the model's bias toward its priors during the decoding stage by comparing the original video with a modified version, in which temporal cues are disrupted. Through comprehensive evaluation of eight open-source and two closed-source VideoLLMs on the proposed EventHallusion benchmark, we observe that the open-source models suffer significantly from hallucination problems, whereas the closed-source ones perform markedly better. By further equipping open-source VideoLLMs with the proposed TCD approach, evident performance improvements are achieved across most metrics in the EventHallusion benchmark. Our codes and benchmark data are available at https://github.com/Stevetich/EventHallusion.

Yang Jiao, Zequn Jie, Jingjing Chen et al.

Recently, one-stage visual grounders attract high attention due to their comparable accuracy but significantly higher efficiency than two-stage grounders. However, inter-object relation modeling has not been well studied for one-stage grounders. Inter-object relationship modeling, though important, is not necessarily performed among all objects, as only part of them are related to the text query and may confuse the model. We call these objects suspected objects. However, exploring their relationships in the one-stage paradigm is non-trivial because: First, no object proposals are available as the basis on which to select suspected objects and perform relationship modeling. Second, suspected objects are more confusing than others, as they may share similar semantics, be entangled with certain relationships, etc, and thereby more easily mislead the model prediction. Toward this end, we propose a Suspected Object Transformation mechanism (SOT), which can be seamlessly integrated into existing CNN and Transformer-based one-stage visual grounders to encourage the target object selection among the suspected ones. Suspected objects are dynamically discovered from a learned activation map adapted to the model current discrimination ability during training. Afterward, on top of suspected objects, a Keyword-Aware Discrimination module (KAD) and an Exploration by Random Connection strategy (ERC) are concurrently proposed to help the model rethink its initial prediction. On the one hand, KAD leverages keywords contributing high to suspected object discrimination. On the other hand, ERC allows the model to seek the correct object instead of being trapped in a situation that always exploits the current false prediction. Extensive experiments demonstrate the effectiveness of our proposed method.

Yang Jiao, Kai Yang, Tiancheng Wu et al.

Bilevel optimization plays an essential role in many machine learning tasks, ranging from hyperparameter optimization to meta-learning. Existing studies on bilevel optimization, however, focus on either centralized or synchronous distributed setting. The centralized bilevel optimization approaches require collecting massive amount of data to a single server, which inevitably incur significant communication expenses and may give rise to data privacy risks. Synchronous distributed bilevel optimization algorithms, on the other hand, often face the straggler problem and will immediately stop working if a few workers fail to respond. As a remedy, we propose Asynchronous Distributed Bilevel Optimization (ADBO) algorithm. The proposed ADBO can tackle bilevel optimization problems with both nonconvex upper-level and lower-level objective functions, and its convergence is theoretically guaranteed. Furthermore, it is revealed through theoretic analysis that the iteration complexity of ADBO to obtain the $ε$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{ε^2})$. Thorough empirical studies on public datasets have been conducted to elucidate the effectiveness and efficiency of the proposed ADBO.

Yang Jiao, Kai Yang, Dongjin Song

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the distributed distributionally robust optimization (DDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance.

Yang Jiao, Hananeh Derakhshan, Barbara St. Pierre Schneider et al.

White blood cells (WBCs) are the most diverse cell types observed in the healing process of injured skeletal muscles. In the course of healing, WBCs exhibit dynamic cellular response and undergo multiple protein expression changes. The progress of healing can be analyzed by quantifying the number of WBCs or the amount of specific proteins in light microscopic images obtained at different time points after injury. In this paper, we propose an automated quantifying and analysis framework to analyze WBCs using light microscopic images of uninjured and injured muscles. The proposed framework is based on the Localized Iterative Otsu's threshold method with muscle edge detection and region of interest extraction. Compared with the threshold methods used in ImageJ, the LI Otsu's threshold method has high resistance to background area and achieves better accuracy. The CD68-positive cell results are presented for demonstrating the effectiveness of the proposed work.

Yian Li, Yang Jiao, Bin Zhu et al.

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs. Effective spatial reasoning requires low-level geometric structure to be faithfully preserved and updated throughout the reasoning process, whereas textual representations tend to abstract away precisely these critical details. To address this issue, we propose SpatialImaginer, a unified multimodal generation framework that integrates textual reasoning with visual imagination. Our framework adopts a divide-and-conquer strategy, using text chain-of-thought for high-level semantic planning and the visual imagination for geometry-sensitive state transformation and consistency preservation. To support this capability, we further introduce a difficulty-aware data engine with closed-loop verification to train the model to invoke visual imagination selectively when stable spatial state tracking is required. Extensive experiments on diverse spatial intelligence benchmarks show that SpatialImaginer achieves state-of-the-art performance and substantially improves robustness on complex multi-step spatial reasoning tasks.

Yang Jiao, Kai Yang, Dongjin Song

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network behavior analysis, risk management, etc. However, existing DRO techniques face three key challenges: 1) how to deal with the asynchronous updating in a distributed environment; 2) how to leverage the prior distribution effectively; 3) how to properly adjust the degree of robustness according to different scenarios. To this end, we propose an asynchronous distributed algorithm, named Asynchronous Single-looP alternatIve gRadient projEction (ASPIRE) algorithm with the itErative Active SEt method (EASE) to tackle the federated distributionally robust optimization (FDRO) problem. Furthermore, a new uncertainty set, i.e., constrained D-norm uncertainty set, is developed to effectively leverage the prior distribution and flexibly control the degree of robustness. Finally, our theoretical analysis elucidates that the proposed algorithm is guaranteed to converge and the iteration complexity is also analyzed. Extensive empirical studies on real-world datasets demonstrate that the proposed method can not only achieve fast convergence, and remain robust against data heterogeneity as well as malicious attacks, but also tradeoff robustness with performance.

Qi'ao Xu, Tianwen Qian, Yuqian Fu et al.

A core capability towards general embodied intelligence lies in localizing task-relevant objects from an egocentric perspective, formulated as Spatio-Temporal Video Grounding (STVG). Despite recent progress, existing STVG studies remain largely confined to object-centric and descriptive instructions, neglecting the task-oriented reasoning that is crucial for embodied agents to accomplish goal-directed interactions. To bridge this gap, we introduce \textbf{ToG-Bench}, the first task-oriented spatio-temporal video grounding benchmark for egocentric videos. ToG-Bench is characterized by three key features: (1) \textbf{Task-oriented Grounding}, which requires identifying and localizing objects based on intended tasks rather than straightforward descriptions; (2) \textbf{Explicit-Implicit Dual Grounding}, where target objects can be either explicitly mentioned or implicitly inferred by contextual reasoning; (3) \textbf{One-to-Many Grounding}, where a single instruction may correspond to multiple objects involved in task execution. Built upon videos sourced from ScanNet, ToG-Bench comprises 100 annotated clips with 2,704 task-oriented grounding instructions, constructed via a semi-automated pipeline that combines foundation model annotation and human refinement. In addition, we introduce a set of task-level evaluation metrics tailored for multi-object and explicit-implicit object grounding, and systematically benchmark seven state-of-the-art MLLMs. Extensive experiments reveal the intrinsic challenges of task-oriented STVG and substantial performance gaps across explicit-implicit and multi-object grounding, highlighting the difficulty of bridging perception and interaction in embodied scenarios. Data and code will be released at: \href{https://github.com/qaxuDev/ToG-Bench}{https://github.com/qaxuDev/ToG-Bench}..

Feng Han, Yibin Wang, Chenglin Li et al.

Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects.

Jiacheng Zhang, Yang Jiao, Shaoxiang Chen et al.

Recently, Multimodal Large Language Models (MLLMs) have sparked great research interests owing to their exceptional content-reasoning and instruction-following capabilities. To effectively instruct an MLLM, in addition to conventional language expressions, the practice of referring to objects by painting with brushes on images has emerged as a prevalent tool (referred to as "referring visual prompts") due to its efficacy in aligning the user's intention with specific image regions. To accommodate the most common referring visual prompts, namely points, boxes, and masks, existing approaches initially utilize specialized feature encoding modules to capture the semantics of the highlighted areas indicated by these prompts. Subsequently, these encoded region features are adapted to MLLMs through fine-tuning on a meticulously curated multimodal instruction dataset. However, such designs suffer from redundancy in architecture. Moreover, they face challenges in effectively generalizing when encountering a diverse range of arbitrary referring visual prompts in real-life scenarios. To address the above issues, we propose EAGLE, a novel MLLM that empowers comprehension of arbitrary referring visual prompts with less training efforts than existing approaches. Specifically, our EAGLE maintains the innate format of the referring visual prompts as colored patches rendered on the given image for conducting the instruction tuning. Our approach embeds referring visual prompts as spatial concepts conveying specific spatial areas comprehensible to the MLLM, with the semantic comprehension of these regions originating from the MLLM itself. Besides, we also propose a Geometry-Agnostic Learning paradigm (GAL) to further disentangle the MLLM's region-level comprehension with the specific formats of referring visual prompts. Extensive experiments are conducted to prove the effectiveness of our proposed method.

Yang Jiao, Shaoxiang Chen, Zequn Jie et al.

Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities of LMMs. The current methods follow the paradigm of adapting the visual task outputs to the format of the language model, which is the main component of a LMM. This adaptation leads to convenient development of such LMMs with minimal modifications, however, it overlooks the intrinsic characteristics of diverse visual tasks and hinders the learning of perception capabilities. To address this issue, we propose a novel LMM architecture named Lumen, a Large multimodal model with versatile vision-centric capability enhancement. We decouple the LMM's learning of perception capabilities into task-agnostic and task-specific stages. Lumen first promotes fine-grained vision-language concept alignment, which is the fundamental capability for various visual tasks. Thus the output of the task-agnostic stage is a shared representation for all the tasks we address in this paper. Then the task-specific decoding is carried out by flexibly routing the shared representation to lightweight task decoders with negligible training efforts. Comprehensive experimental results on a series of vision-centric and VQA benchmarks indicate that our Lumen model not only achieves or surpasses the performance of existing LMM-based approaches in a range of vision-centric tasks while maintaining general visual understanding and instruction following capabilities. The code will be released at https://github.com/SxJyJay/Lumen.

Yang Jiao, Haibo Qiu, Zequn Jie et al.

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth experiments, we uncover key principles for developing a unified model capable of both visual understanding and image generation. Extensive evaluations across a diverse range of prominent benchmarks demonstrate that UniToken achieves state-of-the-art performance, surpassing existing approaches. These results establish UniToken as a robust foundation for future research in this domain. The code and models are available at https://github.com/SxJyJay/UniToken.

Shaoyu Dou, Kai Yang, Yang Jiao et al.

Time series analysis has achieved great success in diverse applications such as network security, environmental monitoring, and medical informatics. Learning similarities among different time series is a crucial problem since it serves as the foundation for downstream analysis such as clustering and anomaly detection. It often remains unclear what kind of distance metric is suitable for similarity learning due to the complex temporal dynamics of the time series generated from event-triggered sensing, which is common in diverse applications, including automated driving, interactive healthcare, and smart home automation. The overarching goal of this paper is to develop an unsupervised learning framework that is capable of learning task-aware similarities among unlabeled event-triggered time series. From the machine learning vantage point, the proposed framework harnesses the power of both hierarchical multi-scale sequence autoencoders and Gaussian Mixture Model (GMM) to effectively learn the low-dimensional representations from the time series. Finally, the obtained similarity measure can be easily visualized for explaining. The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series. Through extensive qualitative and quantitative experiments, it is revealed that the proposed method outperforms state-of-the-art methods considerably.

Tianchen Zhou, Jia Liu, Yang Jiao et al.

Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years. Among the existing approaches for ONL2R, a natural modeling architecture is the multi-armed bandit framework coupled with the position-based click model. However, developing efficient online learning policies for MAB-based ONL2R with position-based click models is highly challenging due to the combinatorial nature of the problem, and partial observability in the position-based click model. To date, results in MAB-based ONL2R with position-based click models remain rather limited, which motivates us to fill this gap in this work. Our main contributions in this work are threefold: i) We propose the first general MAB framework that captures all key ingredients of ONL2R with position-based click models. Our model considers personalized and equal treatments in ONL2R ranking recommendations, both of which are widely used in practice; ii) Based on the above analytical framework, we develop two unified greed- and UCB-based policies called GreedyRank and UCBRank, each of which can be applied to personalized and equal ranking treatments; and iii) We show that both GreedyRank and UCBRank enjoy $O(\sqrt{t}\ln t)$ and $O(\sqrt{t\ln t})$ anytime sublinear regret for personalized and equal treatment, respectively. For the fundamentally hard equal ranking treatment, we identify classes of collective utility functions and their associated sufficient conditions under which $O(\sqrt{t}\ln t)$ and $O(\sqrt{t\ln t})$ anytime sublinear regrets are still achievable for GreedyRank and UCBRank, respectively. Our numerical experiments also verify our theoretical results and demonstrate the efficiency of GreedyRank and UCBRank in seeking the optimal action under various problem settings.

Lingjing Kong, Shaoan Xie, Yang Jiao et al.

Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experiences. While effective, the data structures and principles that enable this crucial capability remain poorly understood. We propose that compositional generalization fundamentally requires decomposing high-level concepts into basic, low-level concepts that can be recombined across similar contexts, similar to how humans draw analogies between concepts. For example, someone who has never seen a peacock eating rice can envision this scene by relating it to their previous observations of a chicken eating rice. In this work, we formalize these intuitive processes using principles of causal modularity and minimal changes. We introduce a hierarchical data-generating process that naturally encodes different levels of concepts and their interaction mechanisms. Theoretically, we demonstrate that this approach enables compositional generalization supporting complex relations between composed concepts, advancing beyond prior work that assumes simpler interactions like additive effects. Critically, we also prove that this latent hierarchical structure is provably recoverable (identifiable) from observable data like text-image pairs, a necessary step for learning such a generative process. To validate our theory, we apply insights from our theoretical framework and achieve significant improvements on benchmark datasets.

Xiaoyang Liu, Kangjie Bao, Jiashuo Zhang et al.

Autoformalization, the automatic translation of mathematical content from natural language into machine-verifiable formal languages, has seen significant progress driven by advances in large language models (LLMs). Nonetheless, a primary barrier to further improvements is the limited availability of parallel corpora that map informal mathematical text to its formal counterpart. To address this limitation, we propose ATLAS (Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data), a novel data generation framework designed to produce large-scale, high-quality parallel corpora of theorem statements. Distinct from prior approaches, ATLAS begins with a concept repository, accelerates the improvement of the student model through expert iteration combined with knowledge distillation, and introduces two novel augmentation strategies that exploit the structural characteristics of formal languages. Running the proposed ATLAS framework for 10 iterations, we construct an undergraduate-level dataset of 117k theorem statements and develop the ATLAS Translator by fine-tuning Llama3.1-8B-Instruct with LoRA. This model establishes a new state of the art, demonstrating statistically significant improvements over both the Herald Translator and the Kimina-Autoformalizer across all benchmarks (p<0.05, two-sided t-test). Furthermore, we demonstrate that the full-parameter fine-tuning of a stronger base model on the ATLAS dataset leads to superior performance. The datasets, model, and code are available at https://github.com/XiaoyangLiu-sjtu/ATLAS.

Yian Li, Wentao Tian, Yang Jiao et al.

Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a \textbf{M}ultimodal \textbf{A}ssumptive \textbf{R}ea\textbf{s}oning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), a novel reinforcement learning paradigm to encourage the model to actively perform composite deduction before reaching a final decision. Equipped with the proposed AD method, a MLLM demonstrates significant improvements in assumptive reasoning abilities without compromising its general-purpose question-answering performance. We also provide extensive evaluations of both open-source and private MLLMs on MARS-Bench, along with experimental analyses of the AD method.

Mingzhe Cui, Tao Chen, Yang Jiao et al.

Developing foundation models for electroencephalography (EEG) remains challenging due to the signal's low signal-to-noise ratio and complex spectro-temporal non-stationarity. Existing approaches often overlook the hierarchical latent structure inherent in neural dynamics, leading to suboptimal reconstruction of fine-grained information. In this work, we propose BrainRVQ, a general-purpose EEG foundation model pre-trained on a large-scale corpus of clinical EEG data. Unlike standard masked modeling, BrainRVQ features a Dual-Domain Residual Vector Quantization (DD-RVQ) tokenizer that disentangles temporal waveforms and spectral patterns into hierarchical discrete codes. We further introduce a hierarchical autoregressive pre-training objective that learns to reconstruct these codes in a coarse-to-fine manner, utilizing an importance-guided curriculum masking strategy to prioritize information-rich neural events over background noise. Extensive experiments across 8 diverse downstream datasets demonstrate that BrainRVQ consistently outperforms state-of-the-art baselines, validating its effectiveness in learning robust and generalizable neural representations. Our code and model weights are available:https://github.com/keqicmz/BrainRVQ

Kailing Li, Qi'ao Xu, Tianwen Qian et al.

Embodied Visual Reasoning (EVR) seeks to follow complex, free-form instructions based on egocentric video, enabling semantic understanding and spatiotemporal reasoning in dynamic environments. Despite its promising potential, EVR encounters significant challenges stemming from the diversity of complex instructions and the intricate spatiotemporal dynamics in long-term egocentric videos. Prior solutions either employ Large Language Models (LLMs) over static video captions, which often omit critical visual details, or rely on end-to-end Vision-Language Models (VLMs) that struggle with stepwise compositional reasoning. Consider the complementary strengths of LLMs in reasoning and VLMs in perception, we propose CLiViS. It is a novel training-free framework that leverages LLMs for high-level task planning and orchestrates VLM-driven open-world visual perception to iteratively update the scene context. Building on this synergy, the core of CLiViS is a dynamic Cognitive Map that evolves throughout the reasoning process. This map constructs a structured representation of the embodied scene, bridging low-level perception and high-level reasoning. Extensive experiments across multiple benchmarks demonstrate the effectiveness and generality of CLiViS, especially in handling long-term visual dependencies. Code is available at https://github.com/Teacher-Tom/CLiViS.

Feng Han, Yang Jiao, Shaoxiang Chen et al.

The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the semantic gap between input text prompts with sparse semantics and the target images, often over-relying on low-level control signals to infer regional details. To address this challenge, we propose ControlThinker, a novel framework that employs a "comprehend-then-generate" paradigm. Firstly, by incentivizing the visual reasoning capability of a MLLM, latent semantics from control images are mined to enrich text prompts. This enriched semantic understanding then seamlessly aids in image generation without the need for additional complex modifications. To further tackle the uncertainty arising from the ambiguity of control images, we encourage broader exploration of reasoning trajectories and select the optimal one using a metric-based output reward model (ORM). Extensive experimental results demonstrate that ControlThinker effectively mitigates the semantic gap between raw text prompts and target images, resulting in improved visual quality and semantic consistency across a wide range of benchmarks. The code and models are available at https://github.com/Maplebb/ControlThinker.

Shuo Yang, Yang Jiao, Shaoyu Dou et al.

The hyperparameter optimization of neural network can be expressed as a bilevel optimization problem. The bilevel optimization is used to automatically update the hyperparameter, and the gradient of the hyperparameter is the approximate gradient based on the best response function. Finding the best response function is very time consuming. In this paper we propose CPMLHO, a new hyperparameter optimization method using cutting plane method and mixed-level objective function.The cutting plane is added to the inner layer to constrain the space of the response function. To obtain more accurate hypergradient,the mixed-level can flexibly adjust the loss function by using the loss of the training set and the verification set. Compared to existing methods, the experimental results show that our method can automatically update the hyperparameters in the training process, and can find more superior hyperparameters with higher accuracy and faster convergence.

Zongheng Guo, Tao Chen, Yang Jiao et al.

Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We also incorporate a semantic consistency constraint via vector quantization to ensure that physiologically identical waveforms (even those altered by recording artifacts or minor perturbations) map to shared indices. This enhances codebook semantic density and eliminates redundant feature structures. Pre-trained on over 120,000 hours of data, SIGMA-PPG achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks. The code is available at https://github.com/ZonghengGuo/SigmaPPG.

Guoyizhe Wei, Yang Jiao, Nan Xi et al.

Composed Image Retrieval (CIR) uses a reference image plus a natural-language edit to retrieve images that apply the requested change while preserving other relevant visual content. Classic fusion pipelines typically rely on supervised triplets and can lose fine-grained cues, while recent zero-shot approaches often caption the reference image and merge the caption with the edit, which may miss implicit user intent and return repetitive results. We present Pix2Key, which represents both queries and candidates as open-vocabulary visual dictionaries, enabling intent-aware constraint matching and diversity-aware reranking in a unified embedding space. A self-supervised pretraining component, V-Dict-AE, further improves the dictionary representation using only images, strengthening fine-grained attribute understanding without CIR-specific supervision. On the DFMM-Compose benchmark, Pix2Key improves Recall@10 up to 3.2 points, and adding V-Dict-AE yields an additional 2.3-point gain while improving intent consistency and maintaining high list diversity.

Jiayu Wang, Yang Jiao, Yue Yu et al.

Recent breakthroughs in large multimodal models (LMMs), such as the impressive GPT-4o-Native, have demonstrated remarkable proficiency in following general-purpose instructions for image generation. However, current benchmarks often lack the necessary breadth and depth to fully evaluate the diverse capabilities of these models. To overcome this limitation, we introduce OmniGenBench, a novel and comprehensive benchmark meticulously designed to assess the instruction-following abilities of state-of-the-art LMMs across both perception-centric and cognition-centric dimensions. Our OmniGenBench includes 57 diverse sub-tasks grounded in real-world scenarios, systematically categorized according to the specific model capabilities they demand. For rigorous evaluation, we further employ a dual-mode protocol. This protocol utilizes off-the-shelf visual parsing tools for perception-centric tasks and a powerful LLM-based judger for cognition-centric tasks to assess the alignment between generated images and user instructions. Using OmniGenBench, we evaluate mainstream generative models, including prevalent models like GPT-4o, Gemini-2.0-Flash, and Seedream, and provide in-depth comparisons and analyses of their performance.Code and data are available at https://github.com/emilia113/OmniGenBench.

Tianwen Qian, Jingjing Chen, Linhai Zhuo et al.

We introduce a novel visual question answering (VQA) task in the context of autonomous driving, aiming to answer natural language questions based on street-view clues. Compared to traditional VQA tasks, VQA in autonomous driving scenario presents more challenges. Firstly, the raw visual data are multi-modal, including images and point clouds captured by camera and LiDAR, respectively. Secondly, the data are multi-frame due to the continuous, real-time acquisition. Thirdly, the outdoor scenes exhibit both moving foreground and static background. Existing VQA benchmarks fail to adequately address these complexities. To bridge this gap, we propose NuScenes-QA, the first benchmark for VQA in the autonomous driving scenario, encompassing 34K visual scenes and 460K question-answer pairs. Specifically, we leverage existing 3D detection annotations to generate scene graphs and design question templates manually. Subsequently, the question-answer pairs are generated programmatically based on these templates. Comprehensive statistics prove that our NuScenes-QA is a balanced large-scale benchmark with diverse question formats. Built upon it, we develop a series of baselines that employ advanced 3D detection and VQA techniques. Our extensive experiments highlight the challenges posed by this new task. Codes and dataset are available at https://github.com/qiantianwen/NuScenes-QA.

Tangtangfang Fang, Yang Jiao, Xiangjian He et al.

Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.

Guoshan Liu, Yang Jiao, Jingjing Chen et al.

The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant research attention in recent years. Prominent benchmarks, such as Food-101 and VIREO Food-172, provide abundant food image resources that catalyze the prosperity of research in this field. Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. This discrepancy poses great challenges in effectively transferring classifiers trained on these canteen datasets to broader daily-life scenarios encountered by humans. Toward this end, we present two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from everyday meals. These two datasets are used to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain. In addition, we also propose a simple yet effective baseline method named Multi-Cluster Reference Learning (MCRL) to tackle the aforementioned domain gap. MCRL is motivated by the observation that food images in daily-life scenarios exhibit greater intra-class appearance variance compared with those in well-curated benchmarks. Notably, MCRL can be seamlessly coupled with existing approaches, yielding non-trivial performance enhancements. We hope our new benchmarks can inspire the community to explore the transferability of food recognition models trained on well-curated datasets toward practical real-life applications.

Pengchao Han, Shiqiang Wang, Yang Jiao et al.

While providing machine learning model as a service to process users' inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients' limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients' inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL's global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients' decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%.

Yang Jiao, Kai Yang, Tiancheng Wu et al.

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $μ$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $μ$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $μ$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $ε$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{ε^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$.

Yang Jiao, Zequn Jie, Shaoxiang Chen et al.

Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction relies on reliable depth estimation for multi-camera images. However, existing approaches exhaustively predict depths for every pixel without prioritizing objects, which are precisely the entities requiring detection in the 3D space. To this end, we propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector. First, a category-specific structural priors mining approach is proposed for enhancing the efficacy of monocular depth generation. Besides, a self-boosting learning strategy is further proposed to encourage the model to place more emphasis on challenging objects in computation-expensive temporal stereo matching. Together they provide advanced depth estimation results for high-quality BEV features construction, benefiting the ultimate 3D detection. The proposed method achieves state-of-the-art performances on the challenging nuScenes benchmark, and extensive experimental results demonstrate the effectiveness of our designs.

Yang Jiao, Xiaodong Wang, Kai Yang

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generation. However, they also exhibit inherent limitations, such as outdated knowledge and susceptibility to hallucinations. Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to address these issues, but it also introduces new vulnerabilities. Recent efforts have focused on the security of RAG-based LLMs, yet existing attack methods face three critical challenges: (1) their effectiveness declines sharply when only a limited number of poisoned texts can be injected into the knowledge database, (2) they lack sufficient stealth, as the attacks are often detectable by anomaly detection systems, which compromises their effectiveness, and (3) they rely on heuristic approaches to generate poisoned texts, lacking formal optimization frameworks and theoretic guarantees, which limits their effectiveness and applicability. To address these issues, we propose coordinated Prompt-RAG attack (PR-attack), a novel optimization-driven attack that introduces a small number of poisoned texts into the knowledge database while embedding a backdoor trigger within the prompt. When activated, the trigger causes the LLM to generate pre-designed responses to targeted queries, while maintaining normal behavior in other contexts. This ensures both high effectiveness and stealth. We formulate the attack generation process as a bilevel optimization problem leveraging a principled optimization framework to develop optimal poisoned texts and triggers. Extensive experiments across diverse LLMs and datasets demonstrate the effectiveness of PR-Attack, achieving a high attack success rate even with a limited number of poisoned texts and significantly improved stealth compared to existing methods.

Zirui Tang, Weizheng Wang, Zihang Zhou et al.

Large language models (LLMs) and agent techniques have brought a fundamental shift in the functionality and development paradigm of data analysis tasks (a.k.a LLM/Agent-as-Data-Analyst), demonstrating substantial impact across both academia and industry. In comparison with traditional rule or small-model based approaches, (agentic) LLMs enable complex data understanding, natural language interfaces, semantic analysis functions, and autonomous pipeline orchestration. From a modality perspective, we review LLM-based techniques for (i) structured data (e.g., NL2SQL, NL2GQL, ModelQA), (ii) semi-structured data (e.g., markup languages understanding, semi-structured table question answering), (iii) unstructured data (e.g., chart understanding, text/image document understanding), and (iv) heterogeneous data (e.g., data retrieval and modality alignment in data lakes). The technical evolution further distills four key design goals for intelligent data analysis agents, namely semantic-aware design, autonomous pipelines, tool-augmented workflows, and support for open-world tasks. Finally, we outline the remaining challenges and propose several insights and practical directions for advancing LLM/Agent-powered data analysis.

Shaoyu Dou, Kai Yang, Yang Jiao et al.

Time series analysis has achieved great success in cyber security such as intrusion detection and device identification. Learning similarities among multiple time series is a crucial problem since it serves as the foundation for downstream analysis. Due to the complex temporal dynamics of the event-triggered time series, it often remains unclear which similarity metric is appropriate for security-related tasks, such as anomaly detection and clustering. The overarching goal of this paper is to develop an unsupervised learning framework that is capable of learning similarities among a set of event-triggered time series. From the machine learning vantage point, the proposed framework harnesses the power of both hierarchical multi-resolution sequential autoencoders and the Gaussian Mixture Model (GMM) to effectively learn the low-dimensional representations from the time series. Finally, the obtained similarity measure can be easily visualized for the explanation. The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series. Through extensive qualitative and quantitative experiments, it is revealed that the proposed method outperforms state-of-the-art methods considerably.

Hui Ma, Kai Yang, Yang Jiao

Network traffic prediction plays a crucial role in intelligent network operation. Traditional prediction methods often rely on centralized training, necessitating the transfer of vast amounts of traffic data to a central server. This approach can lead to latency and privacy concerns. To address these issues, federated learning integrated with differential privacy has emerged as a solution to improve data privacy and model robustness in distributed settings. Nonetheless, existing federated learning protocols are vulnerable to Byzantine attacks, which may significantly compromise model robustness. Developing a robust and privacy-preserving prediction model in the presence of Byzantine clients remains a significant challenge. To this end, we propose an asynchronous differential federated learning framework based on distributionally robust optimization. The proposed framework utilizes multiple clients to train the prediction model collaboratively with local differential privacy. In addition, regularization techniques have been employed to further improve the Byzantine robustness of the models. We have conducted extensive experiments on three real-world datasets, and the results elucidate that our proposed distributed algorithm can achieve superior performance over existing methods.

Yang Jiao, Kai Yang, Chengtao Jian

Trilevel learning (TLL) found diverse applications in numerous machine learning applications, ranging from robust hyperparameter optimization to domain adaptation. However, existing researches primarily focus on scenarios where TLL can be addressed with first order information available at each level, which is inadequate in many situations involving zeroth order constraints, such as when black-box models are employed. Moreover, in trilevel learning, data may be distributed across various nodes, necessitating strategies to address TLL problems without centralizing data on servers to uphold data privacy. To this end, an effective distributed trilevel zeroth order learning framework DTZO is proposed in this work to address the TLL problems with level-wise zeroth order constraints in a distributed manner. The proposed DTZO is versatile and can be adapted to a wide range of (grey-box) TLL problems with partial zeroth order constraints. In DTZO, the cascaded polynomial approximation can be constructed without relying on gradients or sub-gradients, leveraging a novel cut, i.e., zeroth order cut. Furthermore, we theoretically carry out the non-asymptotic convergence rate analysis for the proposed DTZO in achieving the $ε$-stationary point. Extensive experiments have been conducted to demonstrate and validate the superior performance of the proposed DTZO, e.g., it approximately achieves up to a 40$\%$ improvement in performance.

Jieqiong Ding, Yumo Zhang, Xiuqi Tommy Zhu et al.

Meaningful social interaction is vital to well-being, yet Blind and Low Vision (BLV) individuals face persistent barriers when collaborating with sighted peers due to inaccessible visual cues. While most wearable assistive technologies emphasize individual tasks, smart glasses introduce opportunities for real-time, contextual support in social settings. To explore how smart glasses affect interpersonal dynamics and support inclusion in mixed-vision groups, we developed a smart glasses-based system, CollabLens, as a technology probe and employed it in four workshop sessions. We found that smart glasses can meaningfully support inclusive collaboration through expanding BLV participants' assistive networks with more flexible, independent access to visual information. While sighted participants viewed smart glasses as a promising medium that fosters interpersonal connection, they revealed uncertainty in adapting their helping behaviors. We concluded by discussing and synthesizing challenges and opportunities for designing smart glasses that provide seamless interaction experiences and enhance reciprocal mixed-vision social inclusion.

ELita Lobo, Xu Chen, Jingjing Meng et al.

Recent advances in large language models (LLMs) have enabled agentic systems for sequential decision-making. Such agents must perceive their environment, reason across multiple time steps, and take actions that optimize long-term objectives. However, existing web agents struggle on complex, long-horizon tasks due to limited in-context memory for tracking history, weak planning abilities, and greedy behaviors that lead to premature termination. To address these challenges, we propose STRUCTUREDAGENT, a hierarchical planning framework with two core components: (1) an online hierarchical planner that uses dynamic AND/OR trees for efficient search and (2) a structured memory module that tracks and maintains candidate solutions to improve constraint satisfaction in information-seeking tasks. The framework also produces interpretable hierarchical plans, enabling easier debugging and facilitating human intervention when needed. Our results on WebVoyager, WebArena, and custom shopping benchmarks show that STRUCTUREDAGENT improves performance on long-horizon web-browsing tasks compared to standard LLM-based agents.

Guangyu Nie, Yang Jiao, Yi Ren

Effective properties of composite materials are defined as the ensemble average of property-specific PDE solutions over the underlying microstructure distributions. Traditionally, predicting such properties can be done by solving PDEs derived from microstructure samples or building data-driven models that directly map microstructure samples to properties. The former has a higher running cost, but provides explainable sensitivity information that may guide material design; the latter could be more cost-effective if the data overhead is amortized, but its learned sensitivities are often less explainable. With a focus on properties governed by linear self-adjoint PDEs (e.g., Laplace, Helmholtz, and Maxwell curl-curl) defined on bi-phase microstructures, we propose a structure-property model that is both cost-effective and explainable. Our method is built on top of the strong contrast expansion (SCE) formalism, which analytically maps $N$-point correlations of an unbounded random field to its effective properties. Since real-world material samples have finite sizes and analytical PDE kernels are not always available, we propose Neural Contrast Expansion (NCE), an SCE-inspired architecture to learn surrogate PDE kernels from structure-property data. For static conduction and electromagnetic wave propagation cases, we show that NCE models reveal accurate and insightful sensitivity information useful for material design. Compared with other PDE kernel learning methods, our method does not require measurements about the PDE solution fields, but rather only requires macroscopic property measurements that are more accessible in material development contexts.

Yang Jiao, Mei Yang, Mo Weng

In spite of being a valuable tool to simultaneously visualize multiple types of subcellular structures using spectrally distinct fluorescent labels, a standard fluoresce microscope is only able to identify a few microscopic objects; such a limit is largely imposed by the number of fluorescent labels available to the sample. In order to simultaneously visualize more objects, in this paper, we propose to use video-to-video translation that mimics the development process of microscopic objects. In essence, we use a microscopy video-to-video translation framework namely Spatial-temporal Generative Adversarial Network (STGAN) to reveal the spatial and temporal relationships between the microscopic objects, after which a microscopy video of one object can be translated to another object in a different domain. The experimental results confirm that the proposed STGAN is effective in microscopy video-to-video translation that mitigates the spectral conflicts caused by the limited fluorescent labels, allowing multiple microscopic objects be simultaneously visualized.

Zhan Zhang, Qin Zhang, Yang Jiao et al.

AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncertain Causality Graph (DUCG) approach is causality-driven, explainable, and invariant across different application scenarios, without problems of data collection, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption. Through close collaboration between clinical experts and DUCG technicians, 46 DUCG models covering 54 chief complaints were constructed. Over 1,000 diseases can be diagnosed without triage. Before being applied in real-world, the 46 DUCG models were retrospectively verified by third-party hospitals. The verified diagnostic precisions were no less than 95%, in which the diagnostic precision for every disease including uncommon ones was no less than 80%. After verifications, the 46 DUCG models were applied in the real-world in China. Over one million real diagnosis cases have been performed, with only 17 incorrect diagnoses identified. Due to DUCG's transparency, the mistakes causing the incorrect diagnoses were found and corrected. The diagnostic abilities of the clinicians who applied DUCG frequently were improved significantly. Following the introduction to the earlier presented DUCG methodology, the recommendation algorithm for potential medical checks is presented and the key idea of DUCG is extracted.

Yang Jiao, Gloria Wong-Padoongpatt, Mei Yang

Analytic features in gambling study are performed based on the amount of data monitoring on user daily actions. While performing the detection of problem gambling, existing datasets provide relatively rich analytic features for building machine learning based model. However, considering the complexity and cost of collecting the analytic features in real applications, conducting precise detection with less features will tremendously reduce the cost of data collection. In this study, we propose a deep neural networks PGN4 that performs well when using limited analytic features. Through the experiment on two datasets, we discover that PGN4 only experiences a mere performance drop when cutting 102 features to 5 features. Besides, we find the commonality within the top 5 features from two datasets.

Naresh S. Iyer, Amir M. Mirzendehdel, Sathyanarayanan Raghavan et al.

In this paper, we propose PATO-a producibility-aware topology optimization (TO) framework to help efficiently explore the design space of components fabricated using metal additive manufacturing (AM), while ensuring manufacturability with respect to cracking. Specifically, parts fabricated through Laser Powder Bed Fusion are prone to defects such as warpage or cracking due to high residual stress values generated from the steep thermal gradients produced during the build process. Maturing the design for such parts and planning their fabrication can span months to years, often involving multiple handoffs between design and manufacturing engineers. PATO is based on the a priori discovery of crack-free designs, so that the optimized part can be built defect-free at the outset. To ensure that the design is crack free during optimization, producibility is explicitly encoded within the standard formulation of TO, using a crack index. Multiple crack indices are explored and using experimental validation, maximum shear strain index (MSSI) is shown to be an accurate crack index. Simulating the build process is a coupled, multi-physics computation and incorporating it in the TO loop can be computationally prohibitive. We leverage the current advances in deep convolutional neural networks and present a high-fidelity surrogate model based on an Attention-based U-Net architecture to predict the MSSI values as a spatially varying field over the part's domain. Further, we employ automatic differentiation to directly compute the gradient of maximum MSSI with respect to the input design variables and augment it with the performance-based sensitivity field to optimize the design while considering the trade-off between weight, manufacturability, and functionality. We demonstrate the effectiveness of the proposed method through benchmark studies in 3D as well as experimental validation.

Yang Jiao, Zequn Jie, Weixin Luo et al.

Referring Image Segmentation (RIS) aims at segmenting the target object from an image referred by one given natural language expression. The diverse and flexible expressions as well as complex visual contents in the images raise the RIS model with higher demands for investigating fine-grained matching behaviors between words in expressions and objects presented in images. However, such matching behaviors are hard to be learned and captured when the visual cues of referents (i.e. referred objects) are insufficient, as the referents with weak visual cues tend to be easily confused by cluttered background at boundary or even overwhelmed by salient objects in the image. And the insufficient visual cues issue can not be handled by the cross-modal fusion mechanisms as done in previous work. In this paper, we tackle this problem from a novel perspective of enhancing the visual information for the referents by devising a Two-stage Visual cues enhancement Network (TV-Net), where a novel Retrieval and Enrichment Scheme (RES) and an Adaptive Multi-resolution feature Fusion (AMF) module are proposed. Through the two-stage enhancement, our proposed TV-Net enjoys better performances in learning fine-grained matching behaviors between the natural language expression and image, especially when the visual information of the referent is inadequate, thus produces better segmentation results. Extensive experiments are conducted to validate the effectiveness of the proposed method on the RIS task, with our proposed TV-Net surpassing the state-of-the-art approaches on four benchmark datasets.

Sheng Cheng, Yang Jiao, Yi Ren

This paper considers the open challenge of identifying complete, concise, and explainable quantitative microstructure representations for disordered heterogeneous material systems. Completeness and conciseness have been achieved through existing data-driven methods, e.g., deep generative models, which, however, do not provide mathematically explainable latent representations. This study investigates representations composed of three-point correlation functions, which are a special type of spatial convolutions. We show that a variety of microstructures can be characterized by a concise subset of three-point correlations, and the identification of such subsets can be achieved by Bayesian optimization. Lastly, we show that the proposed representation can directly be used to compute material properties based on the effective medium theory.

Yang Jiao, Guangming Shi, Trac D. Tran

Optical flow estimation with occlusion or large displacement is a problematic challenge due to the lost of corresponding pixels between consecutive frames. In this paper, we discover that the lost information is related to a large quantity of motion features (more than 40%) computed from the popular discriminative cost-volume feature would completely vanish due to invalid sampling, leading to the low efficiency of optical flow learning. We call this phenomenon the Vanishing Cost Volume Problem. Inspired by the fact that local motion tends to be highly consistent within a short temporal window, we propose a novel iterative Motion Feature Recovery (MFR) method to address the vanishing cost volume via modeling motion consistency across multiple frames. In each MFR iteration, invalid entries from original motion features are first determined based on the current flow. Then, an efficient network is designed to adaptively learn the motion correlation to recover invalid features for lost-information restoration. The final optical flow is then decoded from the recovered motion features. Experimental results on Sintel and KITTI show that our method achieves state-of-the-art performances. In fact, MFR currently ranks second on Sintel public website.

Yang Jiao, Yi Niu, Trac D. Tran et al.

In 2D+3D facial expression recognition (FER), existing methods generate multi-view geometry maps to enhance the depth feature representation. However, this may introduce false estimations due to local plane fitting from incomplete point clouds. In this paper, we propose a novel Map Generation technique from the viewpoint of information theory, to boost the slight 3D expression differences from strong personality variations. First, we examine the HDR depth data to extract the discriminative dynamic range $r_{dis}$, and maximize the entropy of $r_{dis}$ to a global optimum. Then, to prevent the large deformation caused by over-enhancement, we introduce a depth distortion constraint and reduce the complexity from $O(KN^2)$ to $O(KNτ)$. Furthermore, the constrained optimization is modeled as a $K$-edges maximum weight path problem in a directed acyclic graph, and we solve it efficiently via dynamic programming. Finally, we also design an efficient Facial Attention structure to automatically locate subtle discriminative facial parts for multi-scale learning, and train it with a proposed loss function $\mathcal{L}_{FA}$ without any facial landmarks. Experimental results on different datasets show that the proposed method is effective and outperforms the state-of-the-art 2D+3D FER methods in both FER accuracy and the output entropy of the generated maps.

Yang Jiao, Trac D. Tran, Guangming Shi

This paper addresses the challenging unsupervised scene flow estimation problem by jointly learning four low-level vision sub-tasks: optical flow $\textbf{F}$, stereo-depth $\textbf{D}$, camera pose $\textbf{P}$ and motion segmentation $\textbf{S}$. Our key insight is that the rigidity of the scene shares the same inherent geometrical structure with object movements and scene depth. Hence, rigidity from $\textbf{S}$ can be inferred by jointly coupling $\textbf{F}$, $\textbf{D}$ and $\textbf{P}$ to achieve more robust estimation. To this end, we propose a novel scene flow framework named EffiScene with efficient joint rigidity learning, going beyond the existing pipeline with independent auxiliary structures. In EffiScene, we first estimate optical flow and depth at the coarse level and then compute camera pose by Perspective-$n$-Points method. To jointly learn local rigidity, we design a novel Rigidity From Motion (RfM) layer with three principal components: \emph{}{(i)} correlation extraction; \emph{}{(ii)} boundary learning; and \emph{}{(iii)} outlier exclusion. Final outputs are fused based on the rigid map $M_R$ from RfM at finer levels. To efficiently train EffiScene, two new losses $\mathcal{L}_{bnd}$ and $\mathcal{L}_{unc}$ are designed to prevent trivial solutions and to regularize the flow boundary discontinuity. Extensive experiments on scene flow benchmark KITTI show that our method is effective and significantly improves the state-of-the-art approaches for all sub-tasks, i.e. optical flow ($5.19 \rightarrow 4.20$), depth estimation ($3.78 \rightarrow 3.46$), visual odometry ($0.012 \rightarrow 0.011$) and motion segmentation ($0.57 \rightarrow 0.62$).

Yang Jiao

We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping problem, which is general enough for a variety of front-end speech enhancement tasks. The proposed method is inspired by the excellent sequence modeling capability of bidirectional encoder representation from transformers (BERT). Instead of utilizing explicit representations from pretraining in a self-supervised manner, we utilizes transformer encoded hidden representations in a supervised manner. Both multichannel spectral magnitude and spectral phase information of varying length utterances are encoded. Experimental result demonstrates the effectiveness of the proposed method.