arXiv subjects

Wei Lin

Publications and source records attributed to Wei Lin.

At least 127 records · Page 7Linked to original sources

arXiv2025

Deciphering interventional dynamical causality from non-intervention complex systems

Detecting and quantifying causality is a focal topic in the fields of science, engineering, and interdisciplinary studies. However, causal studies on non-intervention systems attract much attention but remain extremely challenging. Delay-embedding technique provides a promising approach. In this study, we propose a framework named Interventional Dynamical Causality (IntDC) in contrast to the traditional Constructive Dynamical Causality (ConDC). ConDC, including Granger causality, transfer entropy and convergence of cross-mapping, measures the causality by constructing a dynamical model without considering interventions. A computational criterion, Interventional Embedding Entropy (IEE), is proposed to measure causal strengths in an interventional manner. IEE is an intervened causal information flow but in the delay-embedding space. Further, the IEE theoretically and numerically enables the deciphering of IntDC solely from observational (non-interventional) time-series data, without requiring any knowledge of dynamical models or real interventions in the considered system. In particular, IEE can be applied to rank causal effects according to their importance and construct causal networks from data. We conducted numerical experiments to demonstrate that IEE can find causal edges accurately, eliminate effects of confounding, and quantify causal strength robustly over traditional indices. We also applied IEE to real-world tasks. IEE performed as an accurate and robust tool for causal analyses solely from the observational data. The IntDC framework and IEE algorithm provide an efficient approach to the study of causality from time series in diverse non-intervention complex systems.

cs.LG↗

arXiv2025

Neural Event-Triggered Control with Optimal Scheduling

Learning-enabled controllers with stability certificate functions have demonstrated impressive empirical performance in addressing control problems in recent years. Nevertheless, directly deploying the neural controllers onto actual digital platforms requires impractically excessive communication resources due to a continuously updating demand from the closed-loop feedback controller. We introduce a framework aimed at learning the event-triggered controller (ETC) with optimal scheduling, i.e., minimal triggering times, to address this challenge in resource-constrained scenarios. Our proposed framework, denoted by Neural ETC, includes two practical algorithms: the path integral algorithm based on directly simulating the event-triggered dynamics, and the Monte Carlo algorithm derived from new theoretical results regarding lower bound of inter-event time. Furthermore, we propose a projection operation with an analytical expression that ensures theoretical stability and schedule optimality for Neural ETC. Compared to the conventional neural controllers, our empirical results show that the Neural ETC significantly reduces the required communication resources while enhancing the control performance in constrained communication resources scenarios.

math.OC↗

arXiv2025

Efficient Long Context Fine-tuning with Chunk Flow

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail distribution and employ training strategies designed specifically for long sequences. Moreover, these approaches also fail to address the challenges posed by variable sequence lengths during distributed training, such as load imbalance in data parallelism and severe pipeline bubbles in pipeline parallelism. These issues lead to suboptimal training performance and poor GPU resource utilization. To tackle these problems, we propose a chunk-centric training method named ChunkFlow. ChunkFlow reorganizes input sequences into uniformly sized chunks by consolidating short sequences and splitting longer ones. This approach achieves optimal computational efficiency and balance among training inputs. Additionally, ChunkFlow incorporates a state-aware chunk scheduling mechanism to ensure that the peak memory usage during training is primarily determined by the chunk size rather than the maximum sequence length in the dataset. Integrating this scheduling mechanism with existing pipeline scheduling algorithms further enhances the performance of distributed training. Experimental results demonstrate that, compared with Megatron-LM, ChunkFlow can be up to 4.53x faster in the long context fine-tuning of LLMs. Furthermore, we believe that ChunkFlow serves as an effective solution for a broader range of scenarios, such as long context continual pre-training, where datasets contain variable-length sequences.

cs.DC↗

arXiv2025

Featureless Wireless Communications using Enhanced Autoencoder

Artificial intelligence (AI) techniques, particularly autoencoders (AEs), have gained significant attention in wireless communication systems. This paper investigates using an AE to generate featureless signals with a low probability of detection and interception (LPD/LPI). Firstly, we introduce a novel loss function that adds a KL divergence term to the categorical cross entropy, enhancing the noise like characteristics of AE-generated signals while preserving block error rate (BLER). Secondly, to support long source message blocks for the AE's inputs, we replace one-hot inputs of source blocks with binary inputs pre-encoded by conventional error correction coding schemes. The AE's outputs are then decoded back to the source blocks using the same scheme. This design enables the AE to learn the coding structure, yielding superior BLER performance on coded blocks and the BLER of the source blocks is further decreased by the error correction decoder. Moreover, we also validate the AE based communication system in the over-the-air communication. Experimental results demonstrate that our proposed methods improve the featureless properties of AE signals and significantly reduce the BLER of message blocks, underscoring the promise of our AE-based approach for secure and reliable wireless communication systems.

eess.SP↗

arXiv2025

Revisiting Multi-Wave Resonance in Classical Lattices: Quasi-Resonances, Not Exact Resonance, Govern Energy Redistribution

The multi-wave exact resonance condition is a fundamental principle for understanding energy transfer in condensed matter systems, yet the dynamical evolution of waves satisfying this condition remains unexplored. Here, we reveal that the multi-wave resonant kinetic equations possess distinctive symmetry properties that preferentially induce energy equalization between counter-propagating waves of identical frequency. This initial equalization disrupts the exact resonance condition, rendering it dynamically invalid. We further demonstrate that nonlinearity-mediated multi-wave quasi-resonances--not exact resonances--overn energy transfer and drive the system toward thermalization. Crucially, the strength of exact resonances decays with increasing system size, while quasi-resonance strength grows. Moreover, exact resonance strength remains independent of nonlinearity, whereas quasi-resonance strength diminishes with reduced nonlinearity. These observations provide additional evidence supporting the aforementioned conclusion while elucidating the size-dependent thermalization characteristics in lattice systems.

cond-mat.stat-mech↗

arXiv2025

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through comprehensive analysis of token distributions, learning dynamics, and integration mechanisms from entropy-based perspectives, we reveal key differences between these paradigms: SFT induces coarse-grained global changes to LLM policy distributions, while RL performs fine-grained selective optimizations, with entropy serving as a critical indicator of training effectiveness. Building on these observations, we propose Supervised Reinforcement Fine-Tuning (SRFT), a single-stage method that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms. Our approach simultaneously applies SFT and RL to directly optimize the LLM using demonstrations and self-exploration rollouts rather than through two-stage sequential methods. Extensive experiments show that SRFT achieves 59.1% average accuracy, outperforming zero-RL methods by 9.0% on five mathematical reasoning benchmarks and 10.9% on three out-of-distribution benchmarks.

cs.CL↗

arXiv2025

Towards Robust Learning to Optimize with Theoretical Guarantees

Learning to optimize (L2O) is an emerging technique to solve mathematical optimization problems with learning-based methods. Although with great success in many real-world scenarios such as wireless communications, computer networks, and electronic design, existing L2O works lack theoretical demonstration of their performance and robustness in out-of-distribution (OOD) scenarios. We address this gap by providing comprehensive proofs. First, we prove a sufficient condition for a robust L2O model with homogeneous convergence rates over all In-Distribution (InD) instances. We assume an L2O model achieves robustness for an InD scenario. Based on our proposed methodology of aligning OOD problems to InD problems, we also demonstrate that the L2O model's convergence rate in OOD scenarios will deteriorate by an equation of the L2O model's input features. Moreover, we propose an L2O model with a concise gradient-only feature construction and a novel gradient-based history modeling method. Numerical simulation demonstrates that our proposed model outperforms the state-of-the-art baseline in both InD and OOD scenarios and achieves up to 10 $\times$ convergence speedup. The code of our method can be found from https://github.com/NetX-lab/GoMathL2O-Official.

cs.LG↗

arXiv2025

pLSTM: parallelizable Linear Source Transition Mark networks

Modern recurrent architectures, such as xLSTM and Mamba, have recently challenged the Transformer in language modeling. However, their structure constrains their applicability to sequences only or requires processing multi-dimensional data structures, such as images or molecular graphs, in a pre-defined sequential order. In contrast, Multi-Dimensional RNNs (MDRNNs) are well suited for data with a higher level structure, like 2D grids, trees, and directed acyclic graphs (DAGs). In this work, we extend the notion of multi-dimensionality to linear RNNs. We introduce parallelizable Linear Source Transition Mark networks (pLSTMs) using Source, Transition, and Mark gates that act on the line graph of a general DAG. This enables parallelization in analogy to parallel associative scans and the chunkwise-recurrent form of sequential linear RNNs, but for DAGs. For regular grids (1D and 2D), like images, this scheme can be efficiently implemented using einsum operations, concatenations, and padding in logarithmic time. pLSTMs tackle the vanishing/exploding activation/gradient problem for long distances in DAGs via two distinct modes: a directed propagation mode (P-mode) and a diffusive distribution mode (D-mode). To showcase the long-range capabilities of pLSTM, we introduce arrow-pointing extrapolation as a synthetic computer vision task that contains long-distance directional information. We demonstrate that pLSTMs generalize well to larger image sizes, whereas Transformers struggle to extrapolate. On established molecular graph and computer vision benchmarks, pLSTMs also show strong performance. Code and Datasets are available at: https://github.com/ml-jku/plstm_experiments.

cs.LG↗

arXiv2025

Responses of a Coronal Hole to a Fast Flare-Driven Coronal Wave

Coronal waves, significant solar phenomena, act as diagnostic tools for scientists studying solar atmosphere properties. Here, we present a novel observation detailing how a coronal wave event, associated with an X5.0 class flare, influenced the properties of an adjacent coronal hole through interaction. The coronal wave was observed in both extreme ultraviolet observations from the Atmospheric Imaging Assembly aboard the Solar Dynamics Observatory and Lyman-alpha observations from the Solar Disk Imager aboard the Advanced Space-based Solar Observatory. Utilizing the method of differential emission measure, we found that as the coronal wave passed through, the adjacent coronal hole experienced an increase in temperature from 1.31 to 1.43 MK and a rise in density from $\sim$1.62$\times10^{8}$ to 1.76$\times10^{8}$ cm$^{-3}$ within the rising period of $\sim$7 minutes. Subsequently, after the wave passed, the entire coronal hole transitioned to a new state with a slight temperature increase and a 14$\%$ decrease in density, with more pronounced changes observed at the coronal hole's boundary. Taking into account the impacts of radiative loss and heat conduction, the coronal wave was estimated to provide an average energy of 2.2$\times10^{8}$ erg cm$^{-2}$ to the coronal hole during the short rising period. This study highlights the identification of the coronal wave in both extreme ultraviolet and Lyman-alpha observations, shedding light on the significant energy input, particularly within the coronal hole. These findings provide new insights into better understanding kinematics of fast coronal waves, energy transfer processes open versus closed magnetic topologies, and the possible acceleration of solar winds.

astro-ph.SR↗

arXiv2025

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using ground-truth annotations, provides an intuitive user interface for efficient human verification, and generates multiple-choice questions for model evaluation. Applied to the NuScenes dataset, we present STSnu, the first benchmark that evaluates the spatio-temporal reasoning capabilities of VLMs based on comprehensive 3D perception. Existing benchmarks typically target off-the-shelf or fine-tuned VLMs for images or videos from a single viewpoint and focus on semantic tasks such as object recognition, dense captioning, risk assessment, or scene understanding. In contrast, STSnu evaluates driving expert VLMs for end-to-end driving, operating on videos from multi-view cameras or LiDAR. It specifically assesses their ability to reason about both ego-vehicle actions and complex interactions among traffic participants, a crucial capability for autonomous vehicles. The benchmark features 43 diverse scenarios spanning multiple views and frames, resulting in 971 human-verified multiple-choice questions. A thorough evaluation uncovers critical shortcomings in existing models' ability to reason about fundamental traffic dynamics in complex environments. These findings highlight the urgent need for architectural advances that explicitly model spatio-temporal reasoning. By addressing a core gap in spatio-temporal evaluation, STSBench enables the development of more robust and explainable VLMs for autonomous driving.

cs.CV↗

arXiv2025

Hidden Representation Clustering with Multi-Task Representation Learning towards Robust Online Budget Allocation

Marketing optimization, commonly formulated as an online budget allocation problem, has emerged as a pivotal factor in driving user growth. Most existing research addresses this problem by following the principle of 'first predict then optimize' for each individual, which presents challenges related to large-scale counterfactual prediction and solving complexity trade-offs. Note that the practical data quality is uncontrollable, and the solving scale tends to be tens of millions. Therefore, the existing approaches make the robust budget allocation non-trivial, especially in industrial scenarios with considerable data noise. To this end, this paper proposes a novel approach that solves the problem from the cluster perspective. Specifically, we propose a multi-task representation network to learn the inherent attributes of individuals and project the original features into high-dimension hidden representations through the first two layers of the trained network. Then, we divide these hidden representations into $K$ groups through partitioning-based clustering, thus reformulating the problem as an integer stochastic programming problem under different total budgets. Finally, we distill the representation module and clustering model into a multi-category model to facilitate online deployment. Offline experiments validate the effectiveness and superiority of our approach compared to six state-of-the-art marketing optimization algorithms. Online A/B tests on the Meituan platform indicate that the approach outperforms the online algorithm by 0.53% and 0.65%, considering order volume (OV) and gross merchandise volume (GMV), respectively.

cs.LG↗

arXiv2025

RLAE: Reinforcement Learning-Assisted Ensemble for LLMs

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting strategies that fail to adapt to the dynamic, context-dependent characteristics of LLM capabilities. In this work, we propose Reinforcement Learning-Assisted Ensemble for LLMs (RLAE), a novel framework that reformulates LLM ensemble through the lens of a Markov Decision Process (MDP). Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states, with the agent being trained using rewards that directly correspond to the quality of final outputs. We implement RLAE using both single-agent and multi-agent reinforcement learning algorithms ($\text{RLAE}_\text{PPO}$ and $\text{RLAE}_\text{MAPPO}$ ), demonstrating substantial improvements over conventional ensemble methods. Extensive evaluations on a diverse set of tasks show that RLAE outperforms existing approaches by up to $3.3\%$ accuracy points, offering a more effective framework for LLM ensembling. Furthermore, our method exhibits superior generalization capabilities across different tasks without the need for retraining, while simultaneously achieving lower time latency.

cs.LG↗

arXiv2025

Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting

Point detection has been developed to locate pedestrians in crowded scenes by training a counter through a point-to-point (P2P) supervision scheme. Despite its excellent localization and counting performance, training a point-based counter still faces challenges concerning annotation labor: hundreds to thousands of points are required to annotate a single sample capturing a dense crowd. In this paper, we integrate point-based methods into a semi-supervised counting framework based on pseudo-labeling, enabling the training of a counter with only a few annotated samples supplemented by a large volume of pseudo-labeled data. However, during implementation, the training encounters issues as the confidence for pseudo-labels fails to be propagated to background pixels via the P2P. To tackle this challenge, we devise a point-specific activation map (PSAM) to visually interpret the phenomena occurring during the ill-posed training. Observations from the PSAM suggest that the feature map is excessively activated by the loss for unlabeled data, causing the decoder to misinterpret these over-activations as pedestrians. To mitigate this issue, we propose a point-to-region (P2R) scheme to substitute P2P, which segments out local regions rather than detects a point corresponding to a pedestrian for supervision. Consequently, pixels in the local region can share the same confidence with the corresponding pseudo points. Experimental results in both semi-supervised counting and unsupervised domain adaptation highlight the advantages of our method, illustrating P2R can resolve issues identified in PSAM. The code is available at https://github.com/Elin24/P2RLoss.

cs.CV↗

arXiv2025

Amalgamations along surfaces with boundary in a handlebody

Let M be a connected orientable 3-manifold, and F a compact connected orientable surface properly embedded in M. If F cuts M into two connected 3-manifolds X and Y, that is, M=X \cup_F Y, we say that M is an amalgamation of X and Y along F; and if F cuts M into a connected 3-manifold X, we say that M is a self-amalgamation of X along F. A characterization of an amalgamation of two handlebodies along a surface, incompressible in both, to be a handlebody was obtained by Lei, Liu, Li, and Vesnin. The case of amalgamation of two handelbodies along a compressional surface was studdied by Xu, Fang, and Lei. In the present paper, a characterization of an amalgamation and self-amalgamation of a handlebody to be a handlebody is given.

math.GT↗

arXiv2025

SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation

Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video generation remains computationally intensive, especially for high-resolution, long-duration videos. Prior work accelerates its inference by skipping computation, usually at the cost of severe quality degradation. In this paper, we propose SRDiffusion, a novel framework that leverages collaboration between large and small models to reduce inference cost. The large model handles high-noise steps to ensure semantic and motion fidelity (Sketching), while the smaller model refines visual details in low-noise steps (Rendering). Experimental results demonstrate that our method outperforms existing approaches, over 3$\times$ speedup for Wan with nearly no quality loss for VBench, and 2$\times$ speedup for CogVideoX. Our method is introduced as a new direction orthogonal to existing acceleration strategies, offering a practical solution for scalable video generation.

cs.GR↗

arXiv2025

Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion

Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs, converting them to strong LMMs. While many VisIT datasets are available, most are constructed using ad-hoc techniques developed independently by different groups. They are often poorly documented, lack reproducible code, and rely on paid, closed-source model APIs such as GPT-4, Gemini, or Claude to convert image metadata (labels) into VisIT instructions. This leads to high costs and makes it challenging to scale, enhance quality, or generate VisIT data for new datasets. In this work, we address these challenges and propose an open and unified recipe and approach,~\textbf{\method}, for converting available metadata to VisIT instructions using open LLMs. Our multi-stage \method features an efficient framework for metadata grouping, quality control, data and prompt organization, and conversation sampling. We show that our approach can reproduce or enhance the data quality of available VisIT datasets when applied to the same image data and metadata sources, improving GPT-4 generated VisIT instructions by ~3\% on average and up to 12\% on individual benchmarks using open models, such as Gemma 2 27B and LLaMa 3.1 70B. Additionally, our approach enables effective performance scaling - both in quantity and quality - by enhancing the resulting LMM performance across a wide range of benchmarks. We also analyze the impact of various factors, including conversation format, base model selection, and resampling strategies. Our code, which supports the reproduction of equal or higher-quality VisIT datasets and facilities future metadata-to-VisIT data conversion for niche domains, is released at https://github.com/jacob-hansen/Instructify.

cs.CV↗

arXiv2025

A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods

Tuning step sizes is crucial for the stability and efficiency of optimization algorithms. While adaptive coordinate-wise step sizes have been shown to outperform scalar step size in first-order methods, their use in second-order methods is still under-explored and more challenging. Current approaches, including hypergradient descent and cutting plane methods, offer limited improvements or encounter difficulties in second-order contexts. To address these limitations, we first conduct a theoretical analysis within the Broyden-Fletcher-Goldfarb-Shanno (BFGS) framework, a prominent quasi-Newton method, and derive sufficient conditions for coordinate-wise step sizes that ensure convergence and stability. Building on this theoretical foundation, we introduce a novel learn-to-optimize (L2O) method that employs LSTM-based networks to learn optimal step sizes by leveraging insights from past optimization trajectories, while inherently respecting the derived theoretical guarantees. Extensive experiments demonstrate that our approach achieves substantial improvements over scalar step size methods and hypergradient descent-based method, offering up to 4$\times$ faster convergence across diverse optimization tasks.

cs.LG↗

arXiv2025

Wan: Open and Advanced Large-Scale Video Generative Models

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

cs.CV↗