Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jian Sun has a total of 149 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration

    by Wei Dai, Haoyu Wang, Honghao Chang, Lijun He, Fan Li, Jian Sun, Haixia Bi

  • Top Cited Papers

    Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration

    by Xiaole Tang, Xiaoyi He, Jiayi Xu, Xiang Gu, Jian Sun

    Despite substantial advances in all-in-one image restoration for addressing diverse degradations within a unified model, existing methods remain vulnerable to out-of-distribution degradations, thereby limiting their generalization in real-world scenarios. To tackle the challenge, this work is motivated by the intuition that multisource degraded feature distributions are induced by different degradation-specific shifts from an underlying degradation-agnostic distribution, and recovering such a shared distribution is thus crucial for achieving generalization across degradations. With this insight, we propose BaryIR, a representation learning framework that aligns multisource degraded features in the Wasserstein barycenter (WB) space, which models a degradation-agnostic distribution by minimizing the average of Wasserstein distances to multisource degraded distributions. We further introduce residual subspaces, whose embeddings are mutually contrasted while remaining orthogonal to the WB embeddings. Consequently, BaryIR explicitly decouples two orthogonal spaces: a WB space that encodes the degradation-agnostic invariant contents shared across degradations, and residual subspaces that adaptively preserve the degradation-specific knowledge. This disentanglement mitigates overfitting to in-distribution degradations and enables adaptive restoration grounded on the degradation-agnostic shared invariance. Extensive experiments demonstrate that BaryIR performs competitively against state-of-the-art all-in-one methods. Notably, BaryIR generalizes well to unseen degradations (e.g., types and levels) and shows remarkable robustness in learning generalized features, even when trained on limited degradation types and evaluated on real-world data with mixed degradations.


  • Open Access

    Generative flow model on distance geometry for predicting transition states of chemical reactions

    by Yufei Luo, Xiang Gu, Jian Sun

    This paper addresses the challenge of predicting transition states, which are essential for understanding reaction mechanisms but difficult to obtain through experiments or conventional computations. We formulate transition state prediction as conditional probability flow learning in molecular distance geometry space rather than Cartesian coordinates. By operating on interatomic distances, the generative flow model on distance geometry employs a chemically constrained representation that captures bond reorganization. An optimal transport inspired evolution path directs the generative process toward chemically consistent intermediates through a dual branch network architecture. On the benchmark datasets, the proposed model improves pre-optimization structural fidelity over Cartesian baselines, accelerates transition state refinement, and generalizes to unseen reactions. This work shows that aligning generative modeling with chemically constrained geometric representations enables practical and accelerated transition state modeling pipelines.


  • Generative Diffusion-Based Bayesian Modeling for Universal Channel Estimation

    by Runhua Li, Jian Sun, Jiang Xue

    The growth of frequency bandwidths in the new generation of wireless networks gives rise to the multitude of wireless communication scenarios and highlights the challenges of generalized capability of the wireless communication system in different scenarios, especially the channel estimation module. In this paper, we propose a large model dubbed Conditional Latent Diffusion Channel Generation Model (C-LCGM) to learn the distributions of channel state information (CSI) in different wireless communication scenarios to form Bayesian Modeling based Channel Estimation Scheme (BMCE) for universal channel estimation. BMCE conducts universal channel estimation by generating reference CSIs from C-LCGM and mapping the reference CSIs to the optimal channel estimation neural network for each scenario. Specifically in C-LCGM, we propose to compress the CSIs into latent codes and design a conditional diffusion model to model the distribution of the latent codes given the large-scale parameters (LSP) of CSIs as the condition. Further in BMCE, we propose to deploy C-LCGM on the server center and design a hyper-network dubbed Parameters Generating Module (PGM) to map the generated CSIs of C-LCGM to the channel estimation networks for the base stations (BS) according to the reported LSPs. The design rationale and training loss of C-LCGM and BMCE are derived theoretically in this paper. We also conduct extensive simulations to verify the performance of C-LCGM and BMCE. The simulation results show that BMCE can achieve optimal channel estimation performance in different and novel scenarios with C-LCGM generating high-quality CSIs approximating the real CSIs in each scenario. Complexity analysis shows BMCE can fit the delay requirement of wireless communication systems.

  • Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstruction

    by Hao Zhang, Qi Wang, Jian Sun, Zhijie Wen, Jun Shi, Shihui Ying

    Magnetic Resonance Imaging (MRI) is widely used in clinical practice, but suffers from prolonged acquisition time. Although deep learning methods have been proposed to accelerate acquisition and demonstrate promising performance, they rely on high-quality fully-sampled datasets for training in a supervised manner. However, such datasets are time-consuming and expensive-to-collect, which constrains their broader applications. On the other hand, self-supervised methods offer an alternative by enabling learning from under-sampled data alone, but most existing methods rely on further partitioned under-sampled k-space data as model's input for training, which causes an input distribution shift between the the training stage and the inference stage. Additionally, their models have not effectively incorporated comprehensive image priors, leading to degraded reconstruction performance. In this paper, we propose a novel re-visible dual-domain self-supervised deep unfolding network to address these issues when only under-sampled datasets are available. Specifically, by incorporating re-visible dual-domain loss, all under-sampled k-space data are utilized during training to mitigate the input distribution shift caused by further partitioning. This design enables the model to implicitly adapt to all under-sampled k-space data as input. Additionally, we design a Deep Unfolding Network based on Chambolle and Pock Proximal Point Algorithm (DUN-CP-PPA) to achieve end-to-end reconstruction. By employing a Spatial-Frequency Feature Extraction (SFFE) block to capture both global and local representations, the model effectively integrates imaging physics with comprehensive image priors to enhance reconstruction performance. Experiments on both single-coil and multi-coil datasets demonstrate that our method outperforms state-of-the-art approaches in terms of reconstruction performance and generalization capability.


  • Open Access

    Generating transition states of chemical reactions via distance-geometry-based flow matching

    by Yufei Luo, Xiang Gu, Jian Sun

    Transition states (TSs) are crucial for understanding reaction mechanisms, yet their exploration is limited by the complexity of experimental and computational approaches. Here we propose TS-DFM, a flow matching framework that predicts TSs from reactants and products. By operating in molecular distance geometry space, TS-DFM explicitly captures the dynamic changes of interatomic distances in chemical reactions. A network structure named TSDVNet is designed to learn the velocity field for generating TS geometries accurately. On the benchmark dataset Transition1X, TS-DFM outperforms the previous state-of-the-art method React-OT by 30\% in structural accuracy. These predicted TSs provide high-quality initial structures, accelerating the convergence of CI-NEB optimization. Additionally, TS-DFM can identify alternative reaction paths. In our experiments, even a more favorable TS with lower energy barrier is discovered. Further tests on RGD1 dataset confirm its strong generalization ability on unseen molecules and reaction types, highlighting its potential for facilitating reaction exploration.

  • In-Context Learning Implicit Representation for Time Series Forecasting

    by Liwei Yang, Xiang Gu, Jian Sun

    Time series forecasting task aims at predicting future time series signal given historical time series observations. This letter investigates time series signal modeling and forecasting from a novel perspective named In-Context Learning Implicit Representation (ICL-IR). ICL-IR formulates the time series data as an Implicit Representation (IR), which is a mapping from timestamps to time series data. By incorporating the decoder-only transformer architecture, ICL-IR automatically identifies the mapping from timestamps to data based on the constructed in-context examples and predicts future time series data in an autoregressive fashion. To improve the autoregressive prediction performance, we design a One-Step-ahead Training (OST) strategy and demonstrate its effectiveness through both theoretical analysis and empirical evaluation. Experiments demonstrate the superiority of ICL-IR for the time series forecasting task.