Author name cluster

Jiajun Liang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

EAAI Journal 2026 Journal Article

An explainable artificial intelligence-Based approach for intelligent prediction and decision mechanism analysis of tunnel boring machine excavation performance

Jiajun Liang
Kangping Gao
Jingjing Feng
Fan Yang

Accurately predicting tunnel boring machine (TBM) excavation performance while ensuring model interpretability remains challenging under hard rock tunneling conditions with noisy, redundant multi-source sensor data. To address this, the paper first collects 83, 868 sets of tunneling data from actual engineering projects and, through grey relational analysis, determines 10 highly correlated feature parameters from the cleaned dataset. Then, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), combined with the wavelet threshold method, is employed for joint denoising. A hybrid model of graph attention network (GAT) and bidirectional long short-term memory network (BiLSTM) is constructed to achieve synchronous prediction of multiple performance parameters (such as specific energy, field penetration index, and torque penetration index). The Bayesian optimization algorithm is introduced to adaptively tune the hyperparameters, and Shapley additive explanations (SHAP) are combined to analyze the decision-making mechanism of the model from both global and local perspectives. Verification using the actual tunnel dataset shows that the model achieves an average coefficient of determination of 0. 9303 across the three performance parameters, and the mean absolute percentage error (MAPE) is 2. 42%. Compared with the baseline model BiLSTM, the average coefficient of determination improves by 6. 4%, and the MAPE decreases by 37. 3%. Furthermore, the proposed method outperforms mainstream state-of-the-art prediction models. The core innovation is the integration of CEEMDAN-wavelet denoising, GAT-BiLSTM spatiotemporal prediction, and SHAP interpretability, enabling both high-precision and transparent TBM excavation performance prediction.

Details DOI

ICML Conference 2025 Conference Paper

Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and Divergence

Zhaowei Chen
Borui Zhao
Yuchen Ge
Yuhao Chen
Renjie Song
Jiajun Liang

Online Knowledge Distillation (OKD) methods represent a streamlined, one-stage distillation training process that obviates the necessity of transferring knowledge from a pretrained teacher network to a more compact student network. In contrast to existing logits-based OKD methods, this paper presents an innovative approach to leverage intermediate spatial representations. Our analysis of the intermediate features from both teacher and student models reveals two pivotal insights: (1) the similar features between students and teachers are predominantly focused on the foreground objects. (2) teacher models emphasize foreground objects more than students. Building on these findings, we propose Asymmetric Decision-Making (ADM) to enhance feature consensus learning for student models while continuously promoting feature diversity in teacher models. Specifically, Consensus Learning for student models prioritizes spatial features with high consensus relative to teacher models. Conversely, Divergence Learning for teacher models highlights spatial features with lower similarity compared to student models, indicating superior performance by teacher models in these regions. Consequently, ADM facilitates the student models to catch up with the feature learning process of the teacher models. Extensive experiments demonstrate that ADM consistently surpasses existing OKD methods across various online knowledge distillation settings and also achieves superior results when transferred to offline knowledge distillation, semantic segmentation and diffusion distillation tasks.

Details

NeurIPS Conference 2025 Conference Paper

Flow-GRPO: Training Flow Matching Models via Online RL

Jie Liu
Gongye Liu
Jiajun Liang
Yangguang Li
Jiaheng Liu
Xintao Wang
Pengfei Wan
Di Zhang

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation (ODE) into an equivalent Stochastic Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps, enabling statistical sampling for RL exploration; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original number of inference steps, significantly improving sampling efficiency without sacrificing performance. Empirically, Flow-GRPO is effective across multiple text-to-image tasks. For compositional generation, RL-tuned SD3. 5-M generates nearly perfect object counts, spatial relations, and fine-grained attributes, increasing GenEval accuracy from $63\%$ to $95\%$. In visual text rendering, accuracy improves from $59\%$ to $92\%$, greatly enhancing text generation. Flow-GRPO also achieves substantial gains in human preference alignment. Notably, very little reward hacking occurred, meaning rewards did not increase at the cost of appreciable image quality or diversity degradation.

PDF Details

NeurIPS Conference 2025 Conference Paper

Improving Video Generation with Human Feedback

Jie Liu
Gongye Liu
Jiajun Liang
Ziyang Yuan
Xiaokun Liu
Mingwu Zheng
Xiele Wu
Qiulin Wang

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human feedback to mitigate these problems and refine the video generation model. Specifically, we begin by constructing a large-scale human preference dataset focused on modern video generation models, incorporating pairwise annotations across multi-dimensions. We then introduce VideoReward, a multi-dimensional video reward model, and examine how annotations and various design choices impact its rewarding efficacy. From a unified reinforcement learning perspective aimed at maximizing reward with KL regularization, we introduce three alignment algorithms for flow-based models. These include two training-time strategies: direct preference optimization for flow (Flow-DPO) and reward weighted regression for flow (Flow-RWR), and an inference-time technique, Flow-NRG, which applies reward guidance directly to noisy videos. Experimental results indicate that VideoReward significantly outperforms existing reward models, and Flow-DPO demonstrates superior performance compared to both Flow-RWR and supervised fine-tuning methods. Additionally, Flow-NRG lets users assign custom weights to multiple objectives during inference, meeting personalized video quality needs.

PDF Details

NeurIPS Conference 2025 Conference Paper

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang
Siyuan Liang
Yaning Tan
Zhaowei Chen
Linze Li
Ge Wu
Yuhao Chen
Shuheng Li

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings (PE), such as RoPE, need extrapolating to unseen positions which degrades performance when the inference resolution differs from training. In this paper, We propose a Length-Extrapolatable Diffusion Transformer (LEDiT) to overcome this limitation. LEDiT needs no explicit PEs, thereby avoiding PE extrapolation. The key innovation of LEDiT lies in the use of causal attention. We demonstrate that causal attention can implicitly encode global positional information and show that such information facilitates extrapolation. We further introduce a locality enhancement module, which captures fine-grained local information to complement the global coarse-grained position information encoded by causal attention. Experimental results on both conditional and text-to-image generation tasks demonstrate that LEDiT supports up to 4× resolution scaling (e. g. , from 256$\times$256 to 512$\times$512), achieving better image quality compared to the state-of-the-art length extrapolation methods. We believe that LEDiT marks a departure from the standard RoPE-based methods and offers a promising insight into length extrapolation. Project page: https: //shenzhang2145. github. io/ledit/

PDF Details

AAAI Conference 2025 Conference Paper

MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

Shurong Yang
Huadong Li
Juhao Wu
Minhao Jing
Linze Li
Renhe Ji
Jiajun Liang
Haoqiang Fan

Diffusion models have demonstrated superior performance in portrait animation. However, current approaches relied on either visual or audio modality to control character movements, failing to exploit the potential of mixed-modal control. This challenge arises from the difficulty in balancing the weak control strength of audio modality and the strong control strength of visual modality. To address this issue, we introduce MegActor-Sigma: a mixed-modal conditional diffusion transformer (DiT), which can flexibly inject audio and visual modality control signals into portrait animation. Specifically, we make substantial advancements over its predecessor, MegActor, by leveraging the promising model structure of DiT and integrating audio and visual conditions through advanced modules within the DiT framework. To further achieve flexible combinations of mixed-modal control signals, we propose a ``Modality Decoupling Control" training strategy to balance the control strength between visual and audio modalities, along with the ``Amplitude Adjustment" inference strategy to freely regulate the motion amplitude of each modality. Finally, to facilitate extensive studies in this field, we design several dataset evaluation metrics to filter out public datasets and solely use this filtered dataset for training. Extensive experiments demonstrate the superiority of our approach in generating vivid portrait animations.

PDF Details DOI

AAAI Conference 2022 Conference Paper

DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior

Shuangping Jin
Bingbing Yu
Minhao Jing
Yi Zhou
Jiajun Liang
Renhe Ji

RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images, which fails existing algorithms. To handle this, we propose a new RGB-NIR fusion algorithm called Dark Vision Net (DVN) with two technical novelties: Deep Structure and Deep Inconsistency Prior (DIP). The Deep Structure extracts clear structure details in deep multiscale feature space rather than raw input space, which is more robust to noisy inputs. Based on the deep structures from both RGB and NIR domains, we introduce the DIP to leverage the structure inconsistency to guide the fusion of RGB-NIR. Benefiting from this, the proposed DVN obtains high-quality lowlight images without the visual artifacts. We also propose a new dataset called Dark Vision Dataset (DVD), consisting of aligned RGB-NIR image pairs, as the first public RGB- NIR fusion benchmark. Quantitative and qualitative results on the proposed benchmark show that DVN significantly outperforms other comparison algorithms in PSNR and SSIM, especially in extremely low light conditions.

PDF Details

NeurIPS Conference 2021 Conference Paper

Sharp Impossibility Results for Hyper-graph Testing

Jiashun Jin
Zheng Tracy Ke
Jiajun Liang

In a broad Degree-Corrected Mixed-Membership (DCMM) setting, we test whether a non-uniform hypergraph has only one community or has multiple communities. Since both the null and alternative hypotheses have many unknown parameters, the challenge is, given an alternative, how to identify the null that is hardest to separate from the alternative. We approach this by proposing a degree matching strategy where the main idea is leveraging the theory for tensor scaling to create a least favorable pair of hypotheses. We present a result on standard minimax lower bound theory and a result on Region of Impossibility (which is more informative than the minimax lower bound). We show that our lower bounds are tight by introducing a new test that attains the lower bound up to a logarithmic factor. We also discuss the case where the hypergraphs may have mixed-memberships.

PDF Details

AAAI Conference 2019 Conference Paper

Scene Text Recognition from Two-Dimensional Perspective

Minghui Liao
Jian Zhang
Zhaoyi Wan
Fengming Xie
Jiajun Liang
Pengyuan Lyu
Cong Yao
Xiang Bai

Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in images are actually distributed in two-dimensional space. It is a nature quite different from that of speech, which is essentially a one-dimensional signal. In principle, directly compressing features of text into a one-dimensional form may lose useful information and introduce extra noise. In this paper, we approach scene text recognition from a two-dimensional perspective. A simple yet effective model, called Character Attention Fully Convolutional Network (CA-FCN), is devised for recognizing the text of arbitrary shapes. Scene text recognition is realized with a semantic segmentation network, where an attention mechanism for characters is adopted. Combined with a word formation module, CA-FCN can simultaneously recognize the script and predict the position of each character. Experiments demonstrate that the proposed algorithm outperforms previous methods on both regular and irregular text datasets. Moreover, it is proven to be more robust to imprecise localizations in the text detection phase, which are very common in practice.

PDF Details