Xin Chen

Zibo Zhao, Wen Liu, Xin Chen et al. · deepmind, tencent-ai

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional generative model from images or texts to 3D shapes is prone to producing inconsistent results with the conditions because 3D shapes have an additional dimension whose distribution significantly differs from that of 2D images and texts. To bridge the domain gap among the three modalities and facilitate multi-modal-conditioned 3D shape generation, we explore representing 3D shapes in a shape-image-text-aligned space. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM). The former model encodes the 3D shapes into the shape latent space aligned to the image and text and reconstructs the fine-grained 3D neural fields corresponding to given shape embeddings via the transformer-based decoder. The latter model learns a probabilistic mapping function from the image or text space to the latent shape space. Our extensive experiments demonstrate that our proposed approach can generate higher-quality and more diverse 3D shapes that better semantically conform to the visual or textural conditional inputs, validating the effectiveness of the shape-image-text-aligned space for cross-modality 3D shape generation.

Xin Chen, Emiliano Dall'Anese, Changhong Zhao et al.

With a large-scale integration of distributed energy resources (DERs), distribution systems are expected to be capable of providing capacity support for the transmission grid. To effectively harness the collective flexibility from massive DER devices, this paper studies distribution-level power aggregation strategies for transmission-distribution interaction. In particular, this paper proposes a method to model and quantify the aggregate power flexibility, i.e., the net power injection achievable at the substation, in unbalanced distribution systems over time. Incorporating the network constraints and multi-phase unbalanced modeling, the proposed method obtains an effective approximate feasible region of the net power injection. For any aggregate power trajectory within this region, it is proved that there exists a feasible disaggregation solution. In addition, a distributed model predictive control (MPC) framework is developed for the practical implementation of the transmission-distribution interaction. At last, we demonstrate the performances of the proposed method via numerical tests on a real-world distribution feeder with 126 multi-phase nodes.

Xin Chen, Hengheng Zhang, Xiaotao Gu et al.

The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two critical drawbacks, 1) tremendous inner-node and inter-node communication overhead introduced by all-to-all dispatching and gathering, and 2) limited scalability for the backbone because of the bound data parallel and expert parallel to scale in the expert dimension. In this paper, we systematically analyze these drawbacks in terms of training efficiency in the parallel framework view and propose a novel MoE architecture called Pipeline MoE (PPMoE) to tackle them. PPMoE builds expert parallel incorporating with tensor parallel and replaces communication-intensive all-to-all dispatching and gathering with a simple tensor index slicing and inner-node all-reduce. Besides, it is convenient for PPMoE to integrate pipeline parallel to further scale the backbone due to its flexible parallel architecture. Extensive experiments show that PPMoE not only achieves a more than $1.75\times$ speed up compared to existing MoE architectures but also reaches $90\%$ throughput of its corresponding backbone model that is $20\times$ smaller.

Zhendi Gong, Andrew P. French, Guoping Qiu et al.

Convolutional neural networks (CNNs) achieved the state-of-the-art performance in medical image segmentation due to their ability to extract highly complex feature representations. However, it is argued in recent studies that traditional CNNs lack the intelligence to capture long-term dependencies of different image regions. Following the success of applying Transformer models on natural language processing tasks, the medical image segmentation field has also witnessed growing interest in utilizing Transformers, due to their ability to capture long-range contextual information. However, unlike CNNs, Transformers lack the ability to learn local feature representations. Thus, to fully utilize the advantages of both CNNs and Transformers, we propose a hybrid encoder-decoder segmentation model (ConvTransSeg). It consists of a multi-layer CNN as the encoder for feature learning and the corresponding multi-level Transformer as the decoder for segmentation prediction. The encoder and decoder are interconnected in a multi-resolution manner. We compared our method with many other state-of-the-art hybrid CNN and Transformer segmentation models on binary and multiple class image segmentation tasks using several public medical image datasets, including skin lesion, polyp, cell and brain tissue. The experimental results show that our method achieves overall the best performance in terms of Dice coefficient and average symmetric surface distance measures with low model complexity and memory consumption. In contrast to most Transformer-based methods that we compared, our method does not require the use of pre-trained models to achieve similar or better performance. The code is freely available for research purposes on Github: (the link will be added upon acceptance).

Zijian Lv, Xin Chen, Zijian Feng

Accurate online transient stability prediction is critical for ensuring power system stability when facing disturbances. While traditional transient stablity analysis replies on the time domain simulations can not be quickly adapted to the power grid toplogy change. In order to vectorize high-dimensional power grid topological structure information into low-dimensional node-based graph embedding streaming data, graph embedding dynamic feature (GEDF) has been proposed. The transient stability GEDF-based supervised contrastive learning (GEDF-SCL) model uses supervised contrastive learning to predict transient stability with GEDFs, considering power grid topology information. To evaluate the performance of the proposed GEDF-SCL model, power grids of varying topologies were generated based on the IEEE 39-bus system model. Transient operational data was obtained by simulating N-1 and N-$\bm{m}$-1 contingencies on these generated power system topologies. Test result demonstrated that the GEDF-SCL model can achieve high accuracy in transient stability prediction and adapt well to changing power grid topologies.

Biao Jiang, Xin Chen, Chi Zhang et al.

Recent advancements in language models have demonstrated their adeptness in conducting multi-turn dialogues and retaining conversational context. However, this proficiency remains largely unexplored in other multimodal generative models, particularly in human motion models. By integrating multi-turn conversations in controlling continuous virtual human movements, generative human motion models can achieve an intuitive and step-by-step process of human task execution for humanoid robotics, game agents, or other embodied systems. In this work, we present MotionChain, a conversational human motion controller to generate continuous and long-term human motion through multimodal prompts. Specifically, MotionChain consists of multi-modal tokenizers that transform various data types such as text, image, and motion, into discrete tokens, coupled with a Vision-Motion-aware Language model. By leveraging large-scale language, vision-language, and vision-motion data to assist motion-related generation tasks, MotionChain thus comprehends each instruction in multi-turn conversation and generates human motions followed by these prompts. Extensive experiments validate the efficacy of MotionChain, demonstrating state-of-the-art performance in conversational motion generation, as well as more intuitive manners of controlling and interacting with virtual humans.

Xinyi Wang, Grazziela Figueredo, Ruizhe Li et al.

Automatic radiology report generation can alleviate the workload for physicians and minimize regional disparities in medical resources, therefore becoming an important topic in the medical image analysis field. It is a challenging task, as the computational model needs to mimic physicians to obtain information from multi-modal input data (i.e., medical images, clinical information, medical knowledge, etc.), and produce comprehensive and accurate reports. Recently, numerous works have emerged to address this issue using deep-learning-based methods, such as transformers, contrastive learning, and knowledge-base construction. This survey summarizes the key techniques developed in the most recent works and proposes a general workflow for deep-learning-based report generation with five main components, including multi-modality data acquisition, data preparation, feature learning, feature fusion and interaction, and report generation. The state-of-the-art methods for each of these components are highlighted. Additionally, we summarize the latest developments in large model-based methods and model explainability, along with public datasets, evaluation methods, current challenges, and future directions in this field. We have also conducted a quantitative comparison between different methods in the same experimental setting. This is the most up-to-date survey that focuses on multi-modality inputs and data fusion for radiology report generation. The aim is to provide comprehensive and rich information for researchers interested in automatic clinical report generation and medical image analysis, especially when using multimodal inputs, and to assist them in developing new algorithms to advance the field.

Peng Xu, Shengwu Xiong, Jiajun Zhang et al.

This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to follow the state-of-the-art in this very dynamic area. Meanwhile, a growing number of testbeds have boosted the evolution of general-purpose large language models. Thus, this year's MARS2 focuses on real-world and specialized scenarios to broaden the multimodal reasoning applications of MLLMs. Our organizing team released two tailored datasets Lens and AdsQA as test sets, which support general reasoning in 12 daily scenarios and domain-specific reasoning in advertisement videos, respectively. We evaluated 40+ baselines that include both generalist MLLMs and task-specific models, and opened up three competition tracks, i.e., Visual Grounding in Real-world Scenarios (VG-RS), Visual Question Answering with Spatial Awareness (VQA-SA), and Visual Reasoning in Creative Advertisement Videos (VR-Ads). Finally, 76 teams from the renowned academic and industrial institutions have registered and 40+ valid submissions (out of 1200+) have been included in our ranking lists. Our datasets, code sets (40+ baselines and 15+ participants' methods), and rankings are publicly available on the MARS2 workshop website and our GitHub organization page https://github.com/mars2workshop/, where our updates and announcements of upcoming events will be continuously provided.

Yang Han, Pengyu Wang, Kai Yu et al.

Mass spectrometry (MS) plays a critical role in molecular identification, significantly advancing scientific discovery. However, structure elucidation from MS data remains challenging due to the scarcity of annotated spectra. While large-scale pretraining has proven effective in addressing data scarcity in other domains, applying this paradigm to mass spectrometry is hindered by the complexity and heterogeneity of raw spectral signals. To address this, we propose MS-BART, a unified modeling framework that maps mass spectra and molecular structures into a shared token vocabulary, enabling cross-modal learning through large-scale pretraining on reliably computed fingerprint-molecule datasets. Multi-task pretraining objectives further enhance MS-BART's generalization by jointly optimizing denoising and translation task. The pretrained model is subsequently transferred to experimental spectra through finetuning on fingerprint predictions generated with MIST, a pre-trained spectral inference model, thereby enhancing robustness to real-world spectral variability. While finetuning alleviates the distributional difference, MS-BART still suffers molecular hallucination and requires further alignment. We therefore introduce a chemical feedback mechanism that guides the model toward generating molecules closer to the reference structure. Extensive evaluations demonstrate that MS-BART achieves SOTA performance across 5/12 key metrics on MassSpecGym and NPLIB1 and is faster by one order of magnitude than competing diffusion-based methods, while comprehensive ablation studies systematically validate the model's effectiveness and robustness.

Xin Chen, Gillian Dobbie, Xinyu Wang et al.

Conditional diffusion models have the generative controllability by incorporating external conditions. However, their performance significantly degrades with noisy conditions, such as corrupted labels in the image generation or unreliable observations or states in the control policy generation. This paper introduces a robust learning framework to address extremely noisy conditions in conditional diffusion models. We empirically demonstrate that existing noise-robust methods fail when the noise level is high. To overcome this, we propose learning pseudo conditions as surrogates for clean conditions and refining pseudo ones progressively via the technique of temporal ensembling. Additionally, we develop a Reverse-time Diffusion Condition (RDC) technique, which diffuses pseudo conditions to reinforce the memorization effect and further facilitate the refinement of the pseudo conditions. Experimentally, our approach achieves state-of-the-art performance across a range of noise levels on both class-conditional image generation and visuomotor policy generation tasks.The code can be accessible via the project page https://robustdiffusionpolicy.github.io

Varun Mannam, Fang Wang, Chaochun Liu et al.

In talent management systems, critical information often resides in complex tabular formats, presenting significant retrieval challenges for conventional language models. These challenges are pronounced when processing Talent documentation that requires precise interpretation of tabular relationships for accurate information retrieval and downstream decision-making. Current table extraction methods struggle with semantic understanding, resulting in poor performance when integrated into retrieval-augmented chat applications. This paper identifies a key bottleneck - while structural table information can be extracted, the semantic relationships between tabular elements are lost, causing downstream query failures. To address this, we introduce TalentMine, a novel LLM-enhanced framework that transforms extracted tables into semantically enriched representations. Unlike conventional approaches relying on CSV or text linearization, our method employs specialized multimodal reasoning to preserve both structural and semantic dimensions of tabular data. Experimental evaluation across employee benefits document collections demonstrates TalentMine's superior performance, achieving 100% accuracy in query answering tasks compared to 0% for standard AWS Textract extraction and 40% for AWS Textract Visual Q&A capabilities. Our comparative analysis also reveals that the Claude v3 Haiku model achieves optimal performance for talent management applications. The key contributions of this work include (1) a systematic analysis of semantic information loss in current table extraction pipelines, (2) a novel LLM-based method for semantically enriched table representation, (3) an efficient integration framework for retrieval-augmented systems as end-to-end systems, and (4) comprehensive benchmarks on talent analytics tasks showing substantial improvements across multiple categories.

Xin Chen, Jason M. Klusowski

This paper introduces an iterative algorithm for training nonparametric additive models that enjoys favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient descent, applied to the coefficients of a truncated basis expansion of the component functions. We show that the resulting estimator satisfies an oracle inequality that allows for model mis-specification. In the well-specified setting, by choosing the learning rate carefully across three distinct stages of training, we demonstrate that its risk is minimax optimal in terms of the dependence on the dimensionality of the data and the size of the training sample. We also provide polynomial convergence rates even when the covariates do not have full support on their domain.

Yubao Zhang, Xin Chen, Sumei Gong et al.

Wind power is becoming an increasingly important source of renewable energy worldwide. However, wind farm power control faces significant challenges due to the high system complexity inherent in these farms. A novel communication-based multi-agent deep reinforcement learning large-scale wind farm multivariate control is proposed to handle this challenge and maximize power output. A wind farm multivariate power model is proposed to study the influence of wind turbines (WTs) wake on power. The multivariate model includes axial induction factor, yaw angle, and tilt angle controllable variables. The hierarchical communication multi-agent proximal policy optimization (HCMAPPO) algorithm is proposed to coordinate the multivariate large-scale wind farm continuous controls. The large-scale wind farm is divided into multiple wind turbine aggregators (WTAs), and neighboring WTAs can exchange information through hierarchical communication to maximize the wind farm power output. Simulation results demonstrate that the proposed multivariate HCMAPPO can significantly increase wind farm power output compared to the traditional PID control, coordinated model-based predictive control, and multi-agent deep deterministic policy gradient algorithm. Particularly, the HCMAPPO algorithm can be trained with the environment based on the thirteen-turbine wind farm and effectively applied to larger wind farms. At the same time, there is no significant increase in the fatigue damage of the wind turbine blade from the wake control as the wind farm scale increases. The multivariate HCMAPPO control can realize the collective large-scale wind farm maximum power output.

Yanmin Wu, Yunzhou Zhang, Delong Zhu et al.

Object SLAM is considered increasingly significant for robot high-level perception and decision-making. Existing studies fall short in terms of data association, object representation, and semantic mapping and frequently rely on additional assumptions, limiting their performance. In this paper, we present a comprehensive object SLAM framework that focuses on object-based perception and object-oriented robot tasks. First, we propose an ensemble data association approach for associating objects in complicated conditions by incorporating parametric and nonparametric statistic testing. In addition, we suggest an outlier-robust centroid and scale estimation algorithm for modeling objects based on the iForest and line alignment. Then a lightweight and object-oriented map is represented by estimated general object models. Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching. Finally, we suggest an object-driven active exploration strategy to achieve autonomous mapping in the grasping scenario. A range of public datasets and real-world results in mapping, augmented reality, scene matching, relocalization, and robotic manipulation have been used to evaluate the proposed object SLAM framework for its efficient performance.

Peiyuan Sun, Long Huo, Siyuan Liang et al.

Transient stability prediction is critically essential to the fast online assessment and maintaining the stable operation in power systems. The wide deployment of phasor measurement units (PMUs) promotes the development of data-driven approaches for transient stability assessment. This paper proposes the temporal and topological embedding deep neural network (TTEDNN) model to forecast transient stability with the early transient dynamics. The TTEDNN model can accurately and efficiently predict the transient stability by extracting the temporal and topological features from the time-series data of the early transient dynamics. The grid-informed adjacency matrix is used to incorporate the power grid structural and electrical parameter information. The transient dynamics simulation environments under the single-node and multiple-node perturbations are used to test the performance of the TTEDNN model for the IEEE 39-bus and IEEE 118-bus power systems. The results show that the TTEDNN model has the best and most robust prediction performance. Furthermore, the TTEDNN model also demonstrates the transfer capability to predict the transient stability in the more complicated transient dynamics simulation environments.

Xin Chen, Lingxi Xie, Jun Wu et al.

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from which exponentially many sub-networks can be sampled and efficiently evaluated. These methods enjoy great advantages in terms of computational costs, but the sampled sub-networks are not guaranteed to be estimated precisely unless an individual training process is taken. This paper owes such inaccuracy to the inevitable mismatch between assembled network layers, so that there is a random error term added to each estimation. We alleviate this issue by training a graph convolutional network to fit the performance of sampled sub-networks so that the impact of random errors becomes minimal. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates, which consequently leads to better performance of the final architecture. In addition, our approach also enjoys the flexibility of being used under different hardware constraints, since the graph convolutional network has provided an efficient lookup table of the performance of architectures in the entire search space.

Xin Chen, Anqi Pang, Yang Wei et al.

In this paper, we present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single 3D human scan, which enables numerous applications such as virtual try-on, biometrics and body evaluation. To break the severe variations of the human poses and garments, we propose to model the clothing tightness - the displacements from the garments to the human shape implicitly in the global UV texturing domain. To this end, we utilize an enhanced statistical human template and an effective multi-stage alignment scheme to map the 3D scan into a hybrid 2D geometry image. Based on this 2D representation, we propose a novel framework to predicted clothing tightness via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer human shape and garments under various clothing categories and human postures. We further propose a new clothing tightness dataset (CTD) of human scans with a large variety of clothing styles, poses and corresponding ground-truth human shapes to stimulate further research. Extensive experiments demonstrate the effectiveness of our TightCap to achieve high-quality human shape and dressed garments reconstruction, as well as the further applications for clothing segmentation, retargeting and animation.

He Jiang, Xin Chen, Shuwei Zhang et al.

Wearable devices are a new form of mobile computer system that provides exclusive and user-personalized services. Wearable devices bring new issues and challenges to computer science and technology. This paper summarizes the development process and the categories of wearable devices. In addition, we present new key issues arising in aspects of wearable devices, including operating systems, database management system, network communication protocol, application development platform, privacy and security, energy consumption, human-computer interaction, software engineering, and big data.