arXiv subjects

Yifei Wang

Publications and source records attributed to Yifei Wang.

At least 109 records · Page 6Linked to original sources

arXiv2025

Generating Sizing Fields for Mesh Generation via GCN-based Simplification of Adaptive Background Grids

The sizing field defined on a triangular background grid is pivotal for controlling the quality and efficiency of unstructured mesh generation. However, creating an optimal background grid that is geometrically conforming, computationally lightweight, and free from artifacts like banding is a significant challenge. This paper introduces a novel, adaptive background grid simplification (ABGS) framework based on a Graph Convolutional Network (GCN). We reformulate the grid simplification task as an edge score regression problem and train a GCN model to efficiently predict optimal edge collapse candidates. The model is guided by a custom loss function that holistically considers both geometric fidelity and sizing field accuracy. This data-driven approach replaces a costly procedural evaluation, accelerating the simplification process. Experimental results demonstrate the effectiveness of our framework across diverse and complex engineering models. Compared to the initial dense grids, our simplified background grids achieve an element reduction of 74%-94%, leading to a 35%-88% decrease in sizing field query times.

cs.GR↗

arXiv2025

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabulary where low-level tokens with detailed semantics are surjectively mapped to high-level tokens with coarse-grained meanings. In the forward process, each token is independently perturbed to its higher-level ancestor with more abstract semantics according to the scheduler, while in the reverse process the model progressively predicts the next, more detailed semantics. Taken together, HDLM provides a general time-varying next semantic scale prediction process for language modeling. We derive closed-form expressions for the diffusion Evidence Lower Bound (ELBO), and show that HDLM can be implemented in a flexible manner while including the existing MDLM as a special case. We also propose practical training techniques based on the insights. Extensive text generation experiments validate the effectiveness of HDLM, which demonstrates consistently lower validation and generative perplexity than baselines.

cs.CL↗

arXiv2025

Fine-Grained AI Model Caching and Downloading With Coordinated Multipoint Broadcasting in Multi-Cell Edge Networks

6G networks are envisioned to support on-demand AI model downloading to accommodate diverse inference requirements of end users. By proactively caching models at edge nodes, users can retrieve the requested models with low latency for on-device AI inference. However, the substantial size of contemporary AI models poses significant challenges for edge caching under limited storage capacity, as well as for the concurrent delivery of heterogeneous models over wireless channels. To address these challenges, we propose a fine-grained AI model caching and downloading system that exploits parameter reusability, stemming from the common practice of fine-tuning task-specific models from a shared pre-trained model with frozen parameters. This system selectively caches model parameter blocks (PBs) at edge nodes, eliminating redundant storage of reusable parameters across different cached models. Additionally, it incorporates coordinated multipoint (CoMP) broadcasting to simultaneously deliver reusable PBs to multiple users, thereby enhancing downlink spectrum utilization. Under this arrangement, we formulate a model downloading delay minimization problem to jointly optimize PB caching, migration (among edge nodes), and broadcasting beamforming. To tackle this intractable problem, we develop a distributed multi-agent learning framework that enables edge nodes to explicitly learn mutual influence among their actions, thereby facilitating cooperation. Furthermore, a data augmentation approach is proposed to adaptively generate synthetic training samples through a predictive model, boosting sample efficiency and accelerating policy learning. Both theoretical analysis and simulation experiments validate the superior convergence performance of the proposed learning framework.

cs.NI↗

arXiv2025

HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection or decoding, aiming to obtain higher-quality data. However, they typically allocate a uniform sampling budget across all problems, overlooking the varying utility of problems at different difficulty levels. In this work, we conduct an empirical study and find that problems near the boundary of the LLM's reasoning capability offer significantly greater learning utility than both easy and overly difficult ones. To identify and exploit such problems, we propose HS-STaR, a Hierarchical Sampling framework for Self-Taught Reasoners. Given a fixed sampling budget, HS-STaR first performs lightweight pre-sampling with a reward-guided difficulty estimation strategy to efficiently identify boundary-level problems. Subsequently, it dynamically reallocates the remaining budget toward these high-utility problems during a re-sampling phase, maximizing the generation of valuable training data. Extensive experiments across multiple reasoning benchmarks and backbone LLMs demonstrate that HS-STaR significantly outperforms other baselines without requiring additional sampling budget.

cs.AI↗

arXiv2025

Robust Computer-Vision based Construction Site Detection for Assistive-Technology Applications

Purpose: Navigating urban environments poses significant challenges for individuals who are blind or have low vision, especially in areas affected by construction. Construction zones introduce hazards such as uneven surfaces, barriers, hazardous materials, excessive noise, and altered routes that obstruct familiar paths and compromise safety. Although navigation tools assist in trip planning, they often overlook these temporary obstacles. Existing hazard detection systems also struggle with the visual variability of construction sites. Methods: We developed a computer vision--based assistive system integrating three modules: an open-vocabulary object detector to identify diverse construction-related elements, a YOLO-based model specialized in detecting scaffolding and poles, and an optical character recognition module to interpret construction signage. Results: In static testing at seven construction sites using images from multiple stationary viewpoints, the system achieved 88.56% overall accuracy. It consistently identified relevant objects within 2--10 meters and at approach angles up to 75$^{\circ}$. At 2--4 meters, detection was perfect (100%) across all angles. Even at 10 meters, six of seven sites remained detectable within a 15$^{\circ}$ approach. In dynamic testing along a 0.5-mile urban route containing eight construction sites, the system analyzed every frame of a first-person walking video. It achieved 87.26% accuracy in distinguishing construction from non-construction areas, rising to 92.0% with a 50-frame majority vote filter. Conclusion: The system can reliably detect construction sites in real time and at sufficient distances to provide advance warnings, enabling individuals with visual impairments to make safer mobility decisions such as proceeding with caution or rerouting.

cs.CV↗

arXiv2025

Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation

Positional bias (PB), manifesting as non-uniform sensitivity across different contextual locations, significantly impairs long-context comprehension and processing capabilities. Previous studies have addressed PB either by modifying the underlying architectures or by employing extensive contextual awareness training. However, the former approach fails to effectively eliminate the substantial performance disparities, while the latter imposes significant data and computational overhead. To address PB effectively, we introduce \textbf{Pos2Distill}, a position to position knowledge distillation framework. Pos2Distill transfers the superior capabilities from advantageous positions to less favorable ones, thereby reducing the huge performance gaps. The conceptual principle is to leverage the inherent, position-induced disparity to counteract the PB itself. We identify distinct manifestations of PB under \textbf{\textsc{r}}etrieval and \textbf{\textsc{r}}easoning paradigms, thereby designing two specialized instantiations: \emph{Pos2Distill-R\textsuperscript{1}} and \emph{Pos2Distill-R\textsuperscript{2}} respectively, both grounded in this core principle. By employing the Pos2Distill approach, we achieve enhanced uniformity and significant performance gains across all contextual positions in long-context retrieval and reasoning tasks. Crucially, both specialized systems exhibit strong cross-task generalization mutually, while achieving superior performance on their respective tasks.

cs.CL↗

arXiv2025

DyKen-Hyena: Dynamic Kernel Generation via Cross-Modal Attention for Multimodal Intent Recognition

Though Multimodal Intent Recognition (MIR) proves effective by utilizing rich information from multiple sources (e.g., language, video, and audio), the potential for intent-irrelevant and conflicting information across modalities may hinder performance from being further improved. Most current models attempt to fuse modalities by applying mechanisms like multi-head attention to unimodal feature sequences and then adding the result back to the original representation. This process risks corrupting the primary linguistic features with noisy or irrelevant non-verbal signals, as it often fails to capture the fine-grained, token-level influence where non-verbal cues should modulate, not just augment, textual meaning. To address this, we introduce DyKen-Hyena, which reframes the problem from feature fusion to processing modulation. Our model translates audio-visual cues into dynamic, per-token convolutional kernels that directly modulate textual feature extraction. This fine-grained approach achieves state-of-the-art results on the MIntRec and MIntRec2.0 benchmarks. Notably, it yields a +10.46% F1-score improvement in out-of-scope detection, validating that our method creates a fundamentally more robust intent representation.

cs.LG↗

arXiv2025

A Time Splitting Based Optimization Method for Nonlinear MHE

Moving Horizon Estimation~(MHE) is essentially an optimization-based approach designed to estimate the states of dynamic systems within a moving time horizon. Traditional MHE solutions become computationally prohibitive due to the \textit{curse of dimensionality} arising from increasing problem complexity and growing length of time horizon. To address this issue, we propose novel computationally efficient algorithms for solving nonlinear MHE problems. Specifically, we first introduce a distributed reformulation utilizing a time-splitting technique. Leveraging this reformulation, we develop the Efficient Gauss-Newton Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) to achieve computational efficiency. Additionally, to accommodate limited computational capabilities inherent in some sub-problem solvers, we propose the Efficient Sensitivity Assisted ALADIN, which enables sub-problems to be solved inexactly without hindering computational efficiency. Furthermore, recognizing scenarios where sub-problem solvers possess no computational power, we propose a Distributed Sequential Quadratic Programming (SQP) that relies solely on first- and second-order information of local objective functions. We demonstrate the performance and advantages of our proposed methods through numerical experiments on differential drive robots case, a practical nonlinear MHE problem. Our results demonstrate that the three proposed algorithms achieve computational efficiency while preserving high accuracy, thereby satisfying the real-time requirements of MHE.

eess.SY↗

arXiv2025

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning

Although Large Language Models (LLMs) have demonstrated remarkable progress, their proficiency in graph-related tasks remains notably limited, hindering the development of truly general-purpose models. Previous attempts, including pretraining graph foundation models or employing supervised fine-tuning, often face challenges such as the scarcity of large-scale, universally represented graph data. We introduce G1, a simple yet effective approach demonstrating that Reinforcement Learning (RL) on synthetic graph-theoretic tasks can significantly scale LLMs' graph reasoning abilities. To enable RL training, we curate Erdõs, the largest graph reasoning dataset to date comprising 50 diverse graph-theoretic tasks of varying difficulty levels, 100k training data and 5k test data, all drived from real-world graphs. With RL on Erdõs, G1 obtains substantial improvements in graph reasoning, where our finetuned 3B model even outperforms Qwen2.5-72B-Instruct (24x size). RL-trained models also show strong zero-shot generalization to unseen tasks, domains, and graph encoding schemes, including other graph-theoretic benchmarks as well as real-world node classification and link prediction tasks, without compromising general reasoning abilities. Our findings offer an efficient, scalable path for building strong graph reasoners by finetuning LLMs with RL on graph-theoretic tasks, which combines the strengths of pretrained LLM capabilities with abundant, automatically generated synthetic data, suggesting that LLMs possess graph understanding abilities that RL can elicit successfully. Our implementation is open-sourced at https://github.com/PKU-ML/G1, with models and datasets hosted on Hugging Face collections https://huggingface.co/collections/PKU-ML/g1-683d659e992794fc99618cf2 for broader accessibility.

cs.LG↗

arXiv2025

On the Emergence of Position Bias in Transformers

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and positional encodings shape these biases remains elusive. This paper presents a graph-theoretic framework for analyzing position bias in multi-layer attention. Modeling attention masks as directed graphs, we quantify how tokens interact with contextual information based on their sequential positions. We uncover two key insights: First, causal masking inherently biases attention toward earlier positions, as tokens in deeper layers attend to increasingly more contextualized representations of earlier tokens. Second, we characterize the competing effects of the causal mask and relative positional encodings, such as the decay mask and rotary positional encoding (RoPE): while both mechanisms introduce distance-based decay within individual attention maps, their aggregate effect across multiple attention layers$\unicode{x2013}$coupled with the causal mask$\unicode{x2013}$leads to a trade-off between the long-term decay effects and the cumulative importance of early sequence positions. Through controlled numerical experiments, we not only validate our theoretical findings but also reproduce position biases observed in real-world LLMs. Our framework offers a principled foundation for understanding positional biases in transformers, shedding light on the complex interplay of attention mechanism components and guiding more informed architectural design.

cs.LG↗

arXiv2025

ALADIN-$β$: A Distributed Optimization Algorithm for Solving MPCC Problems

Mathematical Programs with Complementarity Constraints (MPCC) are critical in various real-world applications but notoriously challenging due to non-smoothness and degeneracy from complementarity constraints. The $\ell_1$-Exact Penalty-Barrier enhanced \texttt{IPOPT} improves performance and robustness by introducing additional inequality constraints and decision variables. However, this comes at the cost of increased computational complexity due to the higher dimensionality and additional constraints introduced in the centralized formulation. To mitigate this, we propose a distributed structure-splitting reformulation that decomposes these inequality constraints and auxiliary variables into independent sub-problems. Furthermore, we introduce Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN)-$β$, a novel approach that integrates the $\ell_1$-Exact Penalty-Barrier method with ALADIN to efficiently solve the distributed reformulation. Numerical experiments demonstrate that even without a globalization strategy, the proposed distributed approach achieves fast convergence while maintaining high precision.

eess.SY↗

arXiv2025

Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation

Vision Language Navigation (VLN) typically requires agents to navigate to specified objects or remote regions in unknown scenes by obeying linguistic commands. Such tasks require organizing historical visual observations for linguistic grounding, which is critical for long-sequence navigational decisions. However, current agents suffer from overly detailed scene representation and ambiguous vision-language alignment, which weaken their comprehension of navigation-friendly high-level scene priors and easily lead to behaviors that violate linguistic commands. To tackle these issues, we propose a navigation policy by recursively summarizing along-the-way visual perceptions, which are adaptively aligned with commands to enhance linguistic grounding. In particular, by structurally modeling historical trajectories as compact neural grids, several Recursive Visual Imagination (RVI) techniques are proposed to motivate agents to focus on the regularity of visual transitions and semantic scene layouts, instead of dealing with misleading geometric details. Then, an Adaptive Linguistic Grounding (ALG) technique is proposed to align the learned situational memories with different linguistic components purposefully. Such fine-grained semantic matching facilitates the accurate anticipation of navigation actions and progress. Our navigation policy outperforms the state-of-the-art methods on the challenging VLN-CE and ObjectNav tasks, showing the superiority of our RVI and ALG techniques for VLN.

cs.CV↗

arXiv2025

What is Wrong with Perplexity for Long-context Language Modeling?

Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averaging across all tokens and thereby obscuring the true performance of models in long-context scenarios. To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them. Our experiments demonstrate that LongPPL strongly correlates with performance on various long-context benchmarks (e.g., Pearson correlation of -0.96), significantly outperforming traditional PPL in predictive accuracy. Additionally, we introduce \textbf{LongCE} (Long-context Cross-Entropy) loss, a re-weighting strategy for fine-tuning that prioritizes key tokens, leading to consistent improvements across diverse benchmarks. In summary, these contributions offer deeper insights into the limitations of PPL and present effective solutions for accurately evaluating and enhancing the long-context capabilities of LLMs. Code is available at https://github.com/PKU-ML/LongPPL.

cs.CL↗

arXiv2025

Nitrogen-Vacancy Magnetometry of Edge Magnetism in WS2 Flakes

Two-dimensional (2D) magnets are of significant interest both as a platform for exploring novel fundamental physics and for their potential in spintronic and optoelectronic devices. Recent bulk magnetometry studies have indicated a weak ferromagnetic response in WS2, and theoretical predictions suggest edge-localized magnetization in flakes with partial hydrogenation. Here, we use room-temperature wide-field quantum diamond magnetometry to image pristine and Fe-implanted WS2 flakes of varying thicknesses (45-160 nm), exfoliated from bulk crystals and transferred to NV-doped diamond substrates. We observe direct evidence of edge-localized stray magnetic fields, which scale linearly with applied external magnetic field (4.4-220 mT), reaching up to 4.7 uT. The edge signal shows a limited dependence on the flake thickness, consistent with dipolar field decay and sensing geometry. Magnetic simulations using five alternative models favor the presence of edge magnetization aligned along an axis slightly tilted from the normal to the WS2 flake plane, consistent with spin canting in antiferromagnetically coupled edge states. Our findings establish WS2 as a promising platform for edge-controlled 2D spintronics.

cond-mat.mes-hall↗

arXiv2025

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding

Reasoning distillation has emerged as an effective approach to enhance the reasoning capabilities of smaller language models. However, the impact of large-scale reasoning distillation on other critical abilities, particularly in-context retrieval and reasoning, remains unexplored. This gap in understanding is particularly significant given the increasing importance of Retrieval-Augmented Generation (RAG) systems, where efficient acquisition and utilization of contextual information are paramount for generating reliable responses. Motivated by the need to understand how the extended long-CoT process influences long-context comprehension, we conduct a comprehensive investigation using a series of open-source models distilled from Deepseek-R1, renowned for its exceptional reasoning capabilities. Our study focuses on evaluating these models' performance in extracting and integrating relevant information from extended contexts through multi-document question and answering tasks. Through rigorous experimentation, we demonstrate that distilled reasoning patterns significantly improve long-context understanding. Our analysis reveals that distillation fosters greater long-context awareness by promoting more detailed and explicit reasoning processes during context analysis and information parsing. This advancement effectively mitigates the persistent "lost in the middle" issue that has hindered long-context models.

cs.CL↗

arXiv2025

STF: Spatial Temporal Fusion for Trajectory Prediction

Trajectory prediction is a challenging task that aims to predict the future trajectory of vehicles or pedestrians over a short time horizon based on their historical positions. The main reason is that the trajectory is a kind of complex data, including spatial and temporal information, which is crucial for accurate prediction. Intuitively, the more information the model can capture, the more precise the future trajectory can be predicted. However, previous works based on deep learning methods processed spatial and temporal information separately, leading to inadequate spatial information capture, which means they failed to capture the complete spatial information. Therefore, it is of significance to capture information more fully and effectively on vehicle interactions. In this study, we introduced an integrated 3D graph that incorporates both spatial and temporal edges. Based on this, we proposed the integrated 3D graph, which considers the cross-time interaction information. In specific, we design a Spatial-Temporal Fusion (STF) model including Multi-layer perceptions (MLP) and Graph Attention (GAT) to capture the spatial and temporal information historical trajectories simultaneously on the 3D graph. Our experiment on the ApolloScape Trajectory Datasets shows that the proposed STF outperforms several baseline methods, especially on the long-time-horizon trajectory prediction.

cs.CV↗

arXiv2025

Long-Short Alignment for Effective Long-Context Modeling in LLMs

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of the transformer architecture, posing challenges for long-context modeling. Among these challenges, length generalization -- the ability to generalize to sequences longer than those seen during training -- is a classical and fundamental problem. In this work, we propose a fresh perspective on length generalization, shifting the focus from the conventional emphasis on input features such as positional encodings or data structures to the output distribution of the model. Specifically, through case studies on synthetic tasks, we highlight the critical role of \textbf{long-short alignment} -- the consistency of output distributions across sequences of varying lengths. Extending this insight to natural language tasks, we propose a metric called Long-Short Misalignment to quantify this phenomenon, uncovering a strong correlation between the metric and length generalization performance. Building on these findings, we develop a regularization term that promotes long-short alignment during training. Extensive experiments validate the effectiveness of our approach, offering new insights for achieving more effective long-context modeling in LLMs. Code is available at https://github.com/PKU-ML/LongShortAlignment.

cs.CL↗

arXiv2025

A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs

Deep graph neural networks (GNNs) often suffer from oversmoothing, where node representations become overly homogeneous with increasing depth. While techniques like normalization, residual connections, and edge dropout have been proposed to mitigate oversmoothing, they are typically developed independently, with limited theoretical understanding of their underlying mechanisms. In this work, we present a unified theoretical perspective based on the framework of signed graphs, showing that many existing strategies implicitly introduce negative edges that alter message-passing to resist oversmoothing. However, we show that merely adding negative edges in an unstructured manner is insufficient-the asymptotic behavior of signed propagation depends critically on the strength and organization of positive and negative edges. To address this limitation, we leverage the theory of structural balance, which promotes stable, cluster-preserving dynamics by connecting similar nodes with positive edges and dissimilar ones with negative edges. We propose Structural Balanced Propagation (SBP), a plug-and-play method that assigns signed edges based on either labels or feature similarity to explicitly enhance structural balance in the constructed signed graphs. Experiments on nine benchmarks across both homophilic and heterophilic settings demonstrate that SBP consistently improves classification accuracy and mitigates oversmoothing, even at depths of up to 300 layers. Our results provide a principled explanation for prior oversmoothing remedies and introduce a new direction for signed message-passing design in deep GNNs.

cs.LG↗