arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 613 records · Page 34Linked to original sources

arXiv2025

Graph Augmentation for Cross Graph Domain Generalization

Cross-graph node classification, utilizing the abundant labeled nodes from one graph to help classify unlabeled nodes in another graph, can be viewed as a domain generalization problem of graph neural networks (GNNs) due to the structure shift commonly appearing among various graphs. Nevertheless, current endeavors for cross-graph node classification mainly focus on model training. Data augmentation approaches, a simple and easy-to-implement domain generalization technique, remain under-explored. In this paper, we develop a new graph structure augmentation for the crossgraph domain generalization problem. Specifically, low-weight edgedropping is applied to remove potential noise edges that may hinder the generalization ability of GNNs, stimulating the GNNs to capture the essential invariant information underlying different structures. Meanwhile, clustering-based edge-adding is proposed to generate invariant structures based on the node features from the same distribution. Consequently, with these augmentation techniques, the GNNs can maintain the domain invariant structure information that can improve the generalization ability. The experiments on out-ofdistribution citation network datasets verify our method achieves state-of-the-art performance among conventional augmentations.

cs.LG↗

arXiv2025

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators.

cs.CV↗

arXiv2025

Blockchain innovation in promoting employment

Blockchain technology, though conceptualized in the early 1990s, only gained practical relevance with Bitcoin's launch in 2009. Recent advancements have demonstrated its transformative potential, particularly in the digital art and global payment sectors. Non-fungible tokens (NFTs) have redefined digital ownership, while financial institutions use blockchain to enhance cross-border transactions, reducing costs and settlement times. Using the Diamond-Mortensen-Pissarides (DMP) model, this paper examines blockchain's impact on labor markets by improving job-matching efficiency, thereby reducing unemployment. However, high research costs and competition with incumbent technologies hinder early-stage blockchain adoption. We extend the DMP model to analyze the role of government intervention through tax and wage policies in mitigating these barriers. Our findings suggest that lowering firm tax rates can accelerate blockchain innovation, enhance labor market efficiency, and promote employment growth, highlighting the critical balance between technological progress and economic policy in fostering blockchain-driven economic transformation.

econ.GN↗

arXiv2025

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios

We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.

cs.CL↗

arXiv2025

Unveiling the Power of Complex-Valued Transformers in Wireless Communications

Utilizing complex-valued neural networks (CVNNs) in wireless communication tasks has received growing attention for their ability to provide natural and effective representation of complex-valued signals and data. However, existing studies typically employ complex-valued versions of simple neural network architectures. Not only they merely scratch the surface of the extensive range of modern deep learning techniques, theoretical understanding of the superior performance of CVNNs is missing. To this end, this paper aims to fill both the theoretical and practice gap of employing CVNNs in wireless communications. In particular, we provide a comprehensive description on the various operations in CVNNs and theoretically prove that the CVNN requires fewer layers than the real-valued counterpart to achieve a given approximation error of a continuous function. Furthermore, to advance CVNNs in the field of wireless communications, this paper focuses on the transformer model, which represents a more sophisticated deep learning architecture and has been shown to have excellent performance in wireless communications but only in its real-valued form. In this aspect, we propose a fundamental paradigm of complex-valued transformers for wireless communications. Leveraging this structure, we develop customized complex-valued transformers for three representative applications in wireless communications: channel estimation, user activity detection, and precoding design. These applications utilize transformers with varying levels of sophistication and span a variety of tasks, ranging from regression to classification, supervised to unsupervised learning, and specific module design to end-to-end design. Experimental results demonstrate the superior performance of the complex-valued transformers for the above three applications compared to other traditional real-valued neural network-based methods.

eess.SP↗

arXiv2025

EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and real-time scenarios compared to conventional video capture methods. Event data augmentation serve as an essential method for overcoming the limitation of scale and diversity in event datasets. Our comparative experiments demonstrate that the two factors, spatial integrity and temporal continuity, can significantly affect the capacity of event data augmentation, which are guarantee for maintaining the sparsity and high dynamic range characteristics unique to event data. However, existing augmentation methods often neglect the preservation of spatial integrity and temporal continuity. To address this, we developed a novel event data augmentation strategy EventZoom, which employs a temporal progressive strategy, embedding transformed samples into the original samples through progressive scaling and shifting. The scaling process avoids the spatial information loss associated with cropping, while the progressive strategy prevents interruptions or abrupt changes in temporal information. We validated EventZoom across various supervised learning frameworks. The experimental results show that EventZoom consistently outperforms existing event data augmentation methods with SOTA performance. For the first time, we have concurrently employed Semi-supervised and Unsupervised learning to verify feasibility on event augmentation algorithms, demonstrating the applicability and effectiveness of EventZoom as a powerful event-based data augmentation tool in handling real-world scenes with high dynamics and variability environments.

cs.CV↗

arXiv2025

DeepThink: Aligning Language Models with Domain-Specific User Intents

Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes a novel framework called DeepThink to generate high-quality instructions. DeepThink first generates a few seed questions to mimic actual user questions, simulates conversations to uncover the hidden user needs, and refines the answer by conversational contexts and the retrieved documents for more comprehensive answers. Experiments demonstrate that DeepThink achieves an average performance improvement of 7.92% compared to a GPT-4-turbo+RAG-based assistant on the real user test set in the advertising domain across dimensions such as relevance, completeness, clarity, accuracy, and actionability.

cs.CL↗

arXiv2025

Blockchain-based Ecommerce It's an Evolution NOT a Revolution-Experimental Evidence from Users' Perspective

Proponents of blockchains believe that this technology will revolutionize e-commerce. To evaluate this belief, we invite several groups of students to transact on a decentralized peer-to-peer marketplace built on the platform provided by Origin Protocol Inc., and then we conduct a survey about their experience of usage. Based on our survey results, we find that 33% of respondents play tricks on others, which implies that this undesirable result may hinder the widespread adoption of blockchain technologies. We also attempt to propose a conceptual mechanism to mitigate fraudulent behaviors. In the event of disputation, a trusted authority is entitled to the right to downgrade the fraudulent side's credit record, which is stored by a permissioned blockchain accessed only by the authority. Such a punishment can effectively decrease agents' incentives to sell counterfeits and leave fake ratings. In sum, we must distinguish what we proposed blockchains will do and what blockchains can do before enabling this technology in e-commerce.

econ.GN↗

arXiv2025

Bijections in weakly increasing trees via binary trees

As a unification of increasing trees and plane trees, the weakly increasing trees labeled by a multiset was introduced by Lin-Ma-Ma-Zhou in 2021. Motived by some symmetries in plane trees proved recently by Dong, Du, Ji and Zhang, we construct four bijections on weakly increasing trees in the same flavor via switching the role of left child and right child of some specified nodes in their corresponding binary trees. Consequently, bijective proofs of the aforementioned symmetries found by Dong et al. and a non-recursive construction of a bijection on plane trees of Deutsch are provided. Applications of some symmetries in weakly increasing trees to permutation patterns and statistics will also be discussed.

math.CO↗

arXiv2025

pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning

Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, \texttt{pFedGPA}. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, \texttt{pFedGPA} can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches.

cs.LG↗

arXiv2025

A CT Geometry With Multiple Centers Of Rotation For Solving Sparse View Problem

With the emergence of CNT (Carbon nanotube), static and instant CT scanning becomes possible. By transforming the traditionally rotated thermal source into a static ring array source composed of multiple CNTs, the imaging system can achieve high temporal resolution in scanning. However, due to the non-negligible packaging size of CNTs, the static CT based on CNTs faces sparse view problem, which affects the image quality by introducing streak artifacts. In this study, we based on the local correlation equation (LCE) to address the sparse view problem of static CT. The LCE is a series of partial differential equations (PDEs) to describe the local correlation of Radon transform in a neighborhood projection domain. Based on LCE, we analyze the characteristic of sparse view projection and propose a scanning geometry with multiple rotation centers, which is different from existing CT devices that acquires the projection around one rotation center. Specifically, in the proposed scanning geometry, the circular ring array X-ray sources is divided into several arcs while the sources of each arc share one rotation center. All rotation centers of the arcs are uniformly distributed on a small circle. The optimal distribution of the rotation centers can be optimized by the radius of the circle. Moreover, to elevate the image quality under the sparse view reconstruction, we employed the LCE to interpolate unmeasured projections. Compared to the single rotation center scheme used in existing CT geometries, the multiple rotation centers scan contributes to a more even projection distribution with same view number. The simulated results demonstrated the efficiency and potential applications of the proposed method in static CT reconstructions.

physics.med-ph↗

arXiv2025

Robust and Flexible Omnidirectional Depth Estimation with Multiple 360-degree Cameras

Omnidirectional depth estimation has received much attention from researchers in recent years. However, challenges arise due to camera soiling and variations in camera layouts, affecting the robustness and flexibility of the algorithm. In this paper, we use the geometric constraints and redundant information of multiple 360-degree cameras to achieve robust and flexible multi-view omnidirectional depth estimation. We implement two algorithms, in which the two-stage algorithm obtains initial depth maps by pairwise stereo matching of multiple cameras and fuses the multiple depth maps to achieve the final depth estimation; the one-stage algorithm adopts spherical sweeping based on hypothetical depths to construct a uniform spherical matching cost of the multi-camera images and obtain the depth. Additionally, a generalized epipolar equirectangular projection is introduced to simplify the spherical epipolar constraints. To overcome panorama distortion, a spherical feature extractor is implemented. Furthermore, a synthetic 360-degree dataset consisting of 12K road scene panoramas and 3K ground truth depth maps is presented to train and evaluate 360-degree depth estimation algorithms. Our dataset takes soiled camera lenses and glare into consideration, which is more consistent with the real-world environment. Experiments show that our two algorithms achieve state-of-the-art performance, accurately predicting depth maps even when provided with soiled panorama inputs. The flexibility of the algorithms is experimentally validated in terms of camera layouts and numbers.

cs.CV↗

arXiv2025

Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization

Diffusion models have recently advanced Combinatorial Optimization (CO) as a powerful backbone for neural solvers. However, their iterative sampling process requiring denoising across multiple noise levels incurs substantial overhead. We propose to learn direct mappings from different noise levels to the optimal solution for a given instance, facilitating high-quality generation with minimal shots. This is achieved through an optimization consistency training protocol, which, for a given instance, minimizes the difference among samples originating from varying generative trajectories and time steps relative to the optimal solution. The proposed model enables fast single-step solution generation while retaining the option of multi-step sampling to trade for sampling quality, which offers a more effective and efficient alternative backbone for neural solvers. In addition, within the training-to-testing (T2T) framework, to bridge the gap between training on historical instances and solving new instances, we introduce a novel consistency-based gradient search scheme during the test stage, enabling more effective exploration of the solution space learned during training. It is achieved by updating the latent solution probabilities under objective gradient guidance during the alternation of noise injection and denoising steps. We refer to this model as Fast T2T. Extensive experiments on two popular tasks, the Traveling Salesman Problem (TSP) and Maximal Independent Set (MIS), demonstrate the superiority of Fast T2T regarding both solution quality and efficiency, even outperforming LKH given limited time budgets. Notably, Fast T2T with merely one-step generation and one-step gradient search can mostly outperform the SOTA diffusion-based counterparts that require hundreds of steps, while achieving tens of times speedup.

cs.LG↗

arXiv2025

Bottom-Up Reputation Promotes Cooperation with Multi-Agent Reinforcement Learning

Reputation serves as a powerful mechanism for promoting cooperation in multi-agent systems, as agents are more inclined to cooperate with those of good social standing. While existing multi-agent reinforcement learning methods typically rely on predefined social norms to assign reputations, the question of how a population reaches a consensus on judgement when agents hold private, independent views remains unresolved. In this paper, we propose a novel bottom-up reputation learning method, Learning with Reputation Reward (LR2), designed to promote cooperative behaviour through rewards shaping based on assigned reputation. Our agent architecture includes a dilemma policy that determines cooperation by considering the impact on neighbours, and an evaluation policy that assigns reputations to affect the actions of neighbours while optimizing self-objectives. It operates using local observations and interaction-based rewards, without relying on centralized modules or predefined norms. Our findings demonstrate the effectiveness and adaptability of LR2 across various spatial social dilemma scenarios. Interestingly, we find that LR2 stabilizes and enhances cooperation not only with reward reshaping from bottom-up reputation but also by fostering strategy clustering in structured populations, thereby creating environments conducive to sustained cooperation.

cs.MA↗

arXiv2025

Transfer Risk Map: Mitigating Pixel-level Negative Transfer in Medical Segmentation

How to mitigate negative transfer in transfer learning is a long-standing and challenging issue, especially in the application of medical image segmentation. Existing methods for reducing negative transfer focus on classification or regression tasks, ignoring the non-uniform negative transfer risk in different image regions. In this work, we propose a simple yet effective weighted fine-tuning method that directs the model's attention towards regions with significant transfer risk for medical semantic segmentation. Specifically, we compute a transferability-guided transfer risk map to quantify the transfer hardness for each pixel and the potential risks of negative transfer. During the fine-tuning phase, we introduce a map-weighted loss function, normalized with image foreground size to counter class imbalance. Extensive experiments on brain segmentation datasets show our method significantly improves the target task performance, with gains of 4.37% on FeTS2021 and 1.81% on iSeg2019, avoiding negative transfer across modalities and tasks. Meanwhile, a 2.9% gain under a few-shot scenario validates the robustness of our approach.

cs.CV↗

arXiv2025

LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing

The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, selecting the optimal LLM for user queries often involves a challenging trade-off between accuracy and cost, a problem exacerbated by the diverse demands of individual queries. In this work, we present a novel framework that formulates the LLM selection process as a multi-armed bandit problem, enabling dynamic and intelligent routing of queries to the most appropriate model. Our approach incorporates a preference-conditioned dynamic routing mechanism, allowing users to specify their preferences at inference time, thereby offering a customizable balance between performance and cost. Additionally, our selection policy is designed to generalize to unseen LLMs, ensuring adaptability to new models as they emerge. Experimental results demonstrate that our method achieves significant improvements in both accuracy and cost-effectiveness across various LLM platforms, showcasing the potential of our framework to adaptively optimize LLM selection in real-world scenarios.

cs.LG↗

arXiv2025

Policy Guided Tree Search for Enhanced LLM Reasoning

Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are limited by their reliance on predefined heuristics and computationally expensive exploration strategies. We propose Policy-Guided Tree Search (PGTS), a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branching, backtracking, or terminating exploration, eliminating the need for manual heuristics or exhaustive search. Experiments across mathematical reasoning, logical deduction, and planning benchmarks demonstrate that PGTS achieves superior reasoning performance while significantly reducing computational costs compared to existing methods. These results establish PGTS as a scalable and effective solution for tackling complex reasoning tasks with LLMs.

cs.LG↗

arXiv2025

Adapting Foundation Models for Few-Shot Medical Image Segmentation: Actively and Sequentially

Recent advances in foundation models have brought promising results in computer vision, including medical image segmentation. Fine-tuning foundation models on specific low-resource medical tasks has become a standard practice. However, ensuring reliable and robust model adaptation when the target task has a large domain gap and few annotated samples remains a challenge. Previous few-shot domain adaptation (FSDA) methods seek to bridge the distribution gap between source and target domains by utilizing auxiliary data. The selection and scheduling of auxiliaries are often based on heuristics, which can easily cause negative transfer. In this work, we propose an Active and Sequential domain AdaPtation (ASAP) framework for dynamic auxiliary dataset selection in FSDA. We formulate FSDA as a multi-armed bandit problem and derive an efficient reward function to prioritize training on auxiliary datasets that align closely with the target task, through a single-round fine-tuning. Empirical validation on diverse medical segmentation datasets demonstrates that our method achieves favorable segmentation performance, significantly outperforming the state-of-the-art FSDA methods, achieving an average gain of 27.75% on MRI and 7.52% on CT datasets in Dice score. Code is available at the git repository: https://github.com/techicoco/ASAP.

cs.CV↗