Yukun Zhang

Yukun Zhang, Xiaoxue Gong, Weigang Hou et al.

With the explosion of data traffic triggered by 5G/6G and Generative artificial intelligence, coherent optical communication is moving towards higher baud rates and more complex modulation formats. This leads to a significant increase in the computational complexity and power consumption of digital signal processing (DSP) at the transmitter and receiver ends, especially in the chromatic dispersion(CD) Compensation and low roll-off shaping filter modules. We propose a joint shaping filtering and CD compensation (JFS-CD) algorithm. This algorithm moves the CD compensation to the transmitter side and utilizes the characteristics of discrete fourier transform and the spectral features of shaping filtering for integrated processing. Aiming at the high peak-to-average power ratio (PAPR) problem caused by chromatic dispersion pre-compensation, we propose a low-complexity square boundary clipping algorithm(SBC). Simulation results show that, under the premise of maintaining unchanged performance, JFS-CD can reduce the real multiplication complexity by about 46%. Meanwhile, benefiting from the suppression of the effects of system nonlinearity and receiver IQ imbalance, the joint JFS-CD and SBC scheme improves the Q-factor by about 0.3 dB in experiments compared to the traditional post-chromatic dispersion compensation scheme. This research provides a highly potential transmitter DSP solution for next-generation low-power and high-performance data center interconnects (DCI).

Xinyi Ni, Qiuyang Wang, Yukun Zhang et al.

LLM-based tool agents offer natural language interfaces, enabling users to seamlessly interact with computing services. While REST APIs are valuable resources for building such agents, they must first be transformed into AI-compatible tools. Automatically generating AI-compatible tools from REST API documents can greatly streamline tool agent development and minimize user learning curves. However, API documentation often suffers from a lack of standardization, inconsistent schemas, and incomplete information. To address these issues, we developed \textbf{ToolFactory}, an open-source pipeline for automating tool generation from unstructured API documents. To enhance the reliability of the developed tools, we implemented an evaluation method to diagnose errors. Furthermore, we built a knowledge base of verified tools, which we leveraged to infer missing information from poorly documented APIs. We developed the API Extraction Benchmark, comprising 167 API documents and 744 endpoints in various formats, and designed a JSON schema to annotate them. This annotated dataset was utilized to train and validate ToolFactory. The experimental results highlight the effectiveness of ToolFactory. We also demonstrated ToolFactory by creating a domain-specific AI agent for glycomaterials research. ToolFactory exhibits significant potential for facilitating the seamless integration of scientific REST APIs into AI workflows.

Yukun Zhang, Guanzhong Chen, Zenglin Xu et al.

Cardiovascular diseases (CVDs) are currently the leading cause of death worldwide, highlighting the critical need for early diagnosis and treatment. Machine learning (ML) methods can help diagnose CVDs early, but their performance relies on access to substantial data with high quality. However, the sensitive nature of healthcare data often restricts individual clinical institutions from sharing data to train sufficiently generalized and unbiased ML models. Federated Learning (FL) is an emerging approach, which offers a promising solution by enabling collaborative model training across multiple participants without compromising the privacy of the individual data owners. However, to the best of our knowledge, there has been limited prior research applying FL to the cardiovascular disease domain. Moreover, existing FL benchmarks and datasets are typically simulated and may fall short of replicating the complexity of natural heterogeneity found in realistic datasets that challenges current FL algorithms. To address these gaps, this paper presents the first real-world FL benchmark for cardiovascular disease detection, named FedCVD. This benchmark comprises two major tasks: electrocardiogram (ECG) classification and echocardiogram (ECHO) segmentation, based on naturally scattered datasets constructed from the CVD data of seven institutions. Our extensive experiments on these datasets reveal that FL faces new challenges with real-world non-IID and long-tail data. The code and datasets of FedCVD are available https://github.com/SMILELab-FL/FedCVD.

Tao Xia, Jiawei Liu, Yukun Zhang et al.

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise manipulation in diffusion-based methods to token-level operations, VAR-based approaches achieve better background preservation and significantly faster inference. However, existing VAR-based editing methods still face two key challenges: accurately localizing editable tokens and maintaining structural consistency in the edited results. In this work, we propose a novel text-guided image editing framework rooted in an analysis of intermediate feature distributions within VAR models. First, we introduce a coarse-to-fine token localization strategy that can refine editable regions, balancing editing fidelity and background preservation. Second, we analyze the intermediate representations of VAR models and identify structure-related features, by which we design a simple yet effective feature injection mechanism to enhance structural consistency between the edited and source images. Third, we develop a reinforcement learning-based adaptive feature injection scheme that automatically learns scale- and layer-specific injection ratios to jointly optimize editing fidelity and structure preservation. Extensive experiments demonstrate that our method achieves superior structural consistency and editing quality compared with state-of-the-art approaches, across both local and global editing scenarios.

Yukun Zhang, Stefan Elbl Droguett, Samyak Jain

This research project addresses the errors of financial numerical reasoning Question Answering (QA) tasks due to the lack of domain knowledge in finance. Despite recent advances in Large Language Models (LLMs), financial numerical questions remain challenging because they require specific domain knowledge in finance and complex multi-step numeric reasoning. We implement a multi-retriever Retrieval Augmented Generators (RAG) system to retrieve both external domain knowledge and internal question contexts, and utilize the latest LLM to tackle these tasks. Through comprehensive ablation experiments and error analysis, we find that domain-specific training with the SecBERT encoder significantly contributes to our best neural symbolic model surpassing the FinQA paper's top model, which serves as our baseline. This suggests the potential superior performance of domain-specific training. Furthermore, our best prompt-based LLM generator achieves the state-of-the-art (SOTA) performance with significant improvement (>7%), yet it is still below the human expert performance. This study highlights the trade-off between hallucinations loss and external knowledge gains in smaller models and few-shot examples. For larger models, the gains from external facts typically outweigh the hallucination loss. Finally, our findings confirm the enhanced numerical reasoning capabilities of the latest LLM, optimized for few-shot learning.

Lei Sun, Andrea Alfarano, Peiqi Duan et al.

This paper presents an overview of NTIRE 2025 the First Challenge on Event-Based Image Deblurring, detailing the proposed methodologies and corresponding results. The primary goal of the challenge is to design an event-based method that achieves high-quality image deblurring, with performance quantitatively assessed using Peak Signal-to-Noise Ratio (PSNR). Notably, there are no restrictions on computational complexity or model size. The task focuses on leveraging both events and images as inputs for single-image deblurring. A total of 199 participants registered, among whom 15 teams successfully submitted valid results, offering valuable insights into the current state of event-based image deblurring. We anticipate that this challenge will drive further advancements in event-based vision research.

Hongxuan Wu, Yukun Zhang, Xueqing Zhou

When a multimodal Transformer answers a visual question, is the prediction driven by visual evidence, linguistic reasoning, or genuinely fused cross-modal computation -- and how does this structure evolve across layers? We address this question with a layer-wise framework based on Partial Information Decomposition (PID) that decomposes the predictive information at each Transformer layer into redundant, vision-unique, language-unique, and synergistic components. To make PID tractable for high-dimensional neural representations, we introduce \emph{PID Flow}, a pipeline combining dimensionality reduction, normalizing-flow Gaussianization, and closed-form Gaussian PID estimation. Applying this framework to LLaVA-1.5-7B and LLaVA-1.6-7B across six GQA reasoning tasks, we uncover a consistent \emph{modal transduction} pattern: visual-unique information peaks early and decays with depth, language-unique information surges in late layers to account for roughly 82\% of the final prediction, and cross-modal synergy remains below 2\%. This trajectory is highly stable across model variants (layer-wise correlations $>$0.96) yet strongly task-dependent, with semantic redundancy governing the detailed information fingerprint. To establish causality, we perform targeted Image$\rightarrow$Question attention knockouts and show that disrupting the primary transduction pathway induces predictable increases in trapped visual-unique information, compensatory synergy, and total information cost -- effects that are strongest in vision-dependent tasks and weakest in high-redundancy tasks. Together, these results provide an information-theoretic, causal account of how vision becomes language in multimodal Transformers, and offer quantitative guidance for identifying architectural bottlenecks where modality-specific information is lost.

Yukun Zhang, Xueqing Zhou

The Transformer architecture has revolutionized artificial intelligence, yet a principled theoretical understanding of its internal mechanisms remains elusive. This paper introduces a novel analytical framework that reconceptualizes the Transformer's discrete, layered structure as a continuous spatiotemporal dynamical system governed by a master Partial Differential Equation (PDE). Within this paradigm, we map core architectural components to distinct mathematical operators: self-attention as a non-local interaction, the feed-forward network as a local reaction, and, critically, residual connections and layer normalization as indispensable stabilization mechanisms. We do not propose a new model, but rather employ the PDE system as a theoretical probe to analyze the mathematical necessity of these components. By comparing a standard Transformer with a PDE simulator that lacks explicit stabilizers, our experiments provide compelling empirical evidence for our central thesis. We demonstrate that without residual connections, the system suffers from catastrophic representational drift, while the absence of layer normalization leads to unstable, explosive training dynamics. Our findings reveal that these seemingly heuristic "tricks" are, in fact, fundamental mathematical stabilizers required to tame an otherwise powerful but inherently unstable continuous system. This work offers a first-principles explanation for the Transformer's design and establishes a new paradigm for analyzing deep neural networks through the lens of continuous dynamics.

Yukun Zhang

This paper explores the application of Stochastic Differential Equations (SDE) to interpret the text generation process of Large Language Models (LLMs) such as GPT-4. Text generation in LLMs is modeled as a stochastic process where each step depends on previously generated content and model parameters, sampling the next word from a vocabulary distribution. We represent this generation process using SDE to capture both deterministic trends and stochastic perturbations. The drift term describes the deterministic trends in the generation process, while the diffusion term captures the stochastic variations. We fit these functions using neural networks and validate the model on real-world text corpora. Through numerical simulations and comprehensive analyses, including drift and diffusion analysis, stochastic process property evaluation, and phase space exploration, we provide deep insights into the dynamics of text generation. This approach not only enhances the understanding of the inner workings of LLMs but also offers a novel mathematical perspective on language generation, which is crucial for diagnosing, optimizing, and controlling the quality of generated text.

Yukun Zhang

The language evaluation information of the interactive group decision method at present is based on the one-dimension language variable. At the same time, multi-attribute group decision making method based on two-dimension linguistic information only use single-stage and static evaluation method. In this paper, we propose a dynamic group decision making method based on two-dimension linguistic information, combining dynamic interactive group decision making methods with two-dimensional language evaluation information The method first use Two-Dimensional Uncertain Linguistic Generalized Weighted Aggregation (DULGWA) Operators to aggregate the preference information of each decision maker, then adopting dynamic information entropy method to obtain weights of attributes at each stage. Finally we propose the group consistency index to quantify the termination conditions of group interaction. One example is given to verify the developed approach and to demonstrate its effectiveness

Yukun Zhang, Xueqing Zhou

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely on a static attention matrix, we allow attention weights to evolve over a pseudo_time dimension via diffusion, wave, or reaction_diffusion dynamics. This mechanism systematically smooths local noise, enhances long_range dependencies, and stabilizes gradient flow. Theoretically, our analysis shows that PDE_based attention leads to better optimization landscapes and polynomial rather than exponential decay of distant interactions. Empirically, we benchmark our method on diverse experiments_demonstrating consistent gains over both standard and specialized long sequence Transformer variants. Our findings highlight the potential of PDE_based formulations to enrich attention mechanisms with continuous_time dynamics and global coherence.

Yukun Zhang, Qi Dong

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach overlooks the functional specialization within the Transformer architecture, where different layers are known to handle distinct tasks from syntax to abstract reasoning. In this paper, we challenge this one-size-fits-all paradigm by introducing Hierarchical Alignment, a novel method that applies targeted DPO to distinct functional blocks of a model's layers: local (syntax), intermediate (logic), and global (factuality). Through a series of controlled experiments on state-of-the-art models like Llama-3.1-8B and Qwen1.5-7B using LoRA for surgical fine-tuning, our results, evaluated by a powerful LLM-as-Judge, demonstrate significant and predictable improvements. Specifically, aligning the local layers (Local-Align) enhances grammatical fluency. More importantly, aligning the global layers (Global-Align) not only improves factual consistency as hypothesized but also proves to be the most effective strategy for enhancing logical coherence, outperforming all baselines. Critically, all hierarchical strategies successfully avoid the "alignment tax" observed in standard DPO, where gains in fluency come at the cost of degraded logical reasoning. These findings establish a more resource-efficient, controllable, and interpretable path for model alignment, highlighting the immense potential of shifting from monolithic optimization to structure-aware surgical fine-tuning to build more advanced and reliable LLMs.

Yukun Zhang, Xueqing Zhou

We propose PDE-Transformer, a novel sequence modeling paradigm that casts the forward pass of a Transformer as the numerical discretization of a continuous reaction-diffusion system derived from a variational energy functional. In our framework, token embeddings evolve under a partial differential equation whose nonlocal integral term models self-attention, local reaction term models feed-forward layers, diffusion term encodes positional smoothing, and a stability control term corresponds to layer normalization. From this unifying perspective, we design an Adaptive PDE Diffusion Layer-an efficient, learnable finite-difference stencil that enforces local smoothness in feature space with linear time complexity and complements self-attention's global routing. Through a systematic theoretical analysis based on four pillars:stability, diffusion geometry, multi-scale dynamics, and component coupling, we derive principled guidelines for integrating the PDE layer at seven candidate points in the Transformer. Empirically, on the Long Range Arena benchmark, placing the layer immediately after embedding yields a 4.1 pp average accuracy gain over a strong baseline, and an adaptive multi-scale variant delivers further improvements. Our work thus offers a principled, lightweight mechanism to bolster long-range dependency modeling by harmonizing continuous PDE smoothing with discrete self-attention.

Yukun Zhang, Qi Dong

This paper introduces the Dynamical Manifold Evolution Theory (DMET), a conceptual framework that models large language model (LLM) generation as a continuous trajectory evolving on a low-dimensional semantic manifold. The theory characterizes latent dynamics through three interpretable metrics-state continuity ($C$), attractor compactness ($Q$), and topological persistence ($P$)-which jointly capture the smoothness, stability, and structure of representation evolution. Empirical analyses across multiple Transformer architectures reveal consistent links between these latent dynamics and text quality: smoother trajectories correspond to greater fluency, and richer topological organization correlates with enhanced coherence. Different models exhibit distinct dynamical regimes, reflecting diverse strategies of semantic organization in latent space. Moreover, decoding parameters such as temperature and top-$p$ shape these trajectories in predictable ways, defining a balanced region that harmonizes fluency and creativity. As a phenomenological rather than first-principles framework, DMET provides a unified and testable perspective for interpreting, monitoring, and guiding LLM behavior, offering new insights into the interplay between internal representation dynamics and external text generation quality.

Yukun Zhang, Qi Dong

We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cross-scale mappings that preserve geometry and information. Across GPT-2, BERT, RoBERTa, and T5, we observe consistent hierarchical patterns and find that MSMA improves alignment metrics under multiple estimators (e.g., relative KL reduction and MI gains with statistical significance across seeds). Controlled interventions at different scales yield distinct and architecture-dependent effects on lexical diversity, sentence structure, and discourse coherence. While our theoretical analysis relies on idealized assumptions, the empirical results suggest that multi-objective alignment offers a practical lens for analyzing cross-scale information flow and guiding representation-level control.

Baoping Cheng, Yukun Zhang, Liming Wang et al.

With the continuous increase in the number and resolution of video surveillance cameras, the burden of transmitting and storing surveillance video is growing. Traditional communication methods based on Shannon's theory are facing optimization bottlenecks. Semantic communication, as an emerging communication method, is expected to break through this bottleneck and reduce the storage and transmission consumption of video. Existing semantic decoding methods often require many samples to train the neural network for each scene, which is time-consuming and labor-intensive. In this study, a semantic encoding and decoding method for surveillance video is proposed. First, the sketch was extracted as semantic information, and a sketch compression method was proposed to reduce the bit rate of semantic information. Then, an image translation network was proposed to translate the sketch into a video frame with a reference frame. Finally, a few-shot sketch decoding network was proposed to reconstruct video from sketch. Experimental results showed that the proposed method achieved significantly better video reconstruction performance than baseline methods. The sketch compression method could effectively reduce the storage and transmission consumption of semantic information with little compromise on video quality. The proposed method provides a novel semantic encoding and decoding method that only needs a few training samples for each surveillance scene, thus improving the practicality of the semantic communication system.

Yukun Zhang, Qi Dong

This paper proposes a framework combining Neural Ordinary Differential Equations (Neural ODEs) and robust control theory to enhance the interpretability and control of large language models (LLMs). By utilizing Neural ODEs to model the dynamic evolution of input-output relationships and introducing control mechanisms to optimize output quality, we demonstrate the effectiveness of this approach across multiple question-answer datasets. Experimental results show that the integration of Neural ODEs and control theory significantly improves output consistency and model interpretability, advancing the development of explainable AI technologies.

Yongri Piao, Xinxin Ji, Miao Zhang et al.

Light field data has been demonstrated to facilitate the depth estimation task. Most learning-based methods estimate the depth infor-mation from EPI or sub-aperture images, while less methods pay attention to the focal stack. Existing learning-based depth estimation methods from the focal stack lead to suboptimal performance because of the defocus blur. In this paper, we propose a multi-modal learning method for robust light field depth estimation. We first excavate the internal spatial correlation by designing a context reasoning unit which separately extracts comprehensive contextual information from the focal stack and RGB images. Then we integrate the contextual information by exploiting a attention-guide cross-modal fusion module. Extensive experiments demonstrate that our method achieves superior performance than existing representative methods on two light field datasets. Moreover, visual results on a mobile phone dataset show that our method can be widely used in daily life.

Yongri Piao, Yukun Zhang, Miao Zhang et al.

Focus based methods have shown promising results for the task of depth estimation. However, most existing focus based depth estimation approaches depend on maximal sharpness of the focal stack. Out of focus information in the focal stack poses challenges for this task. In this paper, we propose a dynamically multi modal learning strategy which incorporates RGB data and the focal stack in our framework. Our goal is to deeply excavate the spatial correlation in the focal stack by designing the spatial correlation perception module and dynamically fuse multi modal information between RGB data and the focal stack in a adaptive way by designing the multi modal dynamic fusion module. The success of our method is demonstrated by achieving the state of the art performance on two datasets. Furthermore, we test our network on a set of different focused images generated by a smart phone camera to prove that the proposed method not only broke the limitation of only using light field data, but also open a path toward practical applications of depth estimation on common consumer level cameras data.

Yukun Zhang, Longsheng Zhou

Artificial Intelligence (AI) is an important driving force for the development and transformation of the financial industry. However, with the fast-evolving AI technology and application, unintentional bias, insufficient model validation, immature contingency plan and other underestimated threats may expose the company to operational and reputational risks. In this paper, we focus on fairness evaluation, one of the key components of AI Governance, through a quantitative lens. Statistical methods are reviewed for imbalanced data treatment and bias mitigation. These methods and fairness evaluation metrics are then applied to a credit card default payment example.