Searcharxiv⌕ Search

arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 235 records · Page 13Linked to original sources
arXiv2024

Marginal Structural Modeling of Representative Treatment Trajectories

Marginal structural models (MSMs) are widely used in observational studies to estimate the causal effect of time-varying treatments. Despite its popularity, limited attention has been paid to summarizing the treatment history in the outcome model, which proves particularly challenging when individuals' treatment trajectories exhibit complex patterns over time. Commonly used metrics such as the average treatment level fail to adequately capture the treatment history, hindering causal interpretation. For scenarios where treatment histories exhibit distinct temporal patterns, we develop a new approach to parameterize the outcome model. We apply latent growth curve analysis to identify representative treatment trajectories from the observed data and use the posterior probability of latent class membership to summarize the different treatment trajectories. We demonstrate its use in parameterizing the MSMs, which facilitates the interpretations of the results. We apply the method to analyze data from an existing cohort of lung transplant recipients to estimate the effect of Tacrolimus concentrations on the risk of incident chronic kidney disease.

stat.ME↗
arXiv2024

Observation of electrical high-harmonic generation

High-harmonic generation (HHG), an extreme nonlinear effect, introduces an unprecedented paradigm to detect emergent quantum phases and electron dynamics inconceivable in the framework of linear and low-order nonlinear processes. As an important manifestation, the optical HHG (o-HHG) enables extraordinary opportunities to underpin attosecond physics. In addition to nonlinear optics, emerging nonlinear electric transport has been demonstrated recently and opens new paradigms to probe quantum phase transition, symmetry breaking, band geometrical and topological properties. Thus far, only electrical second-/third-harmonic generation in perturbative regime has been elucidated, while the electrical HHG (e-HHG) that can advance to extreme non-perturbative physics remains elusive. Here we report the observation of e-HHG up to 300th-order. Remarkably, the e-HHG shows a clear non-perturbative character and exhibits periodic oscillations with the reciprocal of driving current. Further, theoretical simulations corroborate the experiments, suggesting the contribution of singular distribution of Berry curvature near band edges. Our results demonstrate e-HHG in extreme nonlinear regime and may shed light on a plethora of exotic physics and applications, such as extreme non-equilibrium quantum phenomena, ultra-fast and coherent electrical signal generations and detections.

cond-mat.mes-hall↗
arXiv2024

MIMONet: Multi-Input Multi-Output On-Device Deep Learning

Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that multi-input single-output (MISO) deep neural networks (DNN) outperform traditional single-input single-output (SISO) models, representing a significant step towards this goal. In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage. Leveraging existing SISO model compression techniques, MIMONet develops a new deep-compression method that is specifically tailored to MIMO models. This new method explores unique yet non-trivial properties of the MIMO model, resulting in boosted accuracy and on-device efficiency. Extensive experiments on three embedded platforms commonly used in robotic systems, as well as a case study using the TurtleBot3 robot, demonstrate that MIMONet achieves higher accuracy and superior on-device efficiency compared to state-of-the-art SISO and MISO models, as well as a baseline MIMO model we constructed. Our evaluation highlights the real-world applicability of MIMONet and its potential to significantly enhance the performance of intelligent robotic systems.

cs.RO↗
arXiv2024

Diffusion Model-based Contrastive Learning for Human Activity Recognition

WiFi Channel State Information (CSI)-based activity recognition has sparked numerous studies due to its widespread availability and privacy protection. However, when applied in practical applications, general CSI-based recognition models may face challenges related to the limited generalization capability, since individuals with different behavior habits will cause various fluctuations in CSI data and it is difficult to gather enough training data to cover all kinds of motion habits. To tackle this problem, we design a diffusion model-based Contrastive Learning framework for human Activity Recognition (CLAR) using WiFi CSI. On the basis of the contrastive learning framework, we primarily introduce two components for CLAR to enhance CSI-based activity recognition. To generate diverse augmented data and complement limited training data, we propose a diffusion model-based time series-specific augmentation model. In contrast to typical diffusion models that directly apply conditions to the generative process, potentially resulting in distorted CSI data, our tailored model dissects these condition into the high-frequency and low-frequency components, and then applies these conditions to the generative process with varying weights. This can alleviate data distortion and yield high-quality augmented data. To efficiently capture the difference of the sample importance, we present an adaptive weight algorithm. Different from typical contrastive learning methods which equally consider all the training samples, this algorithm adaptively adjusts the weights of positive sample pairs for learning better data representations. The experiments suggest that CLAR achieves significant gains compared to state-of-the-art methods.

cs.NI↗
arXiv2024

Charmed hypernuclei within density-dependent relativistic mean-field theory

The charmed $ Λ_{c}^{+} $ hypernuclei are investigated within the framework of the density-dependent relativistic mean-field (DDRMF) theory. Starting from the empirical hyperon potential in symmetric nuclear matter, obtained through microscopic first-principle calculations, two sets of $Λ_c N$ effective interactions were derived by fitting the potentials with minimal uncertainty (Fermi momentum $k_{F,n} = 1.05~\rm{fm}^{-1}$) and near saturation density ($k_{F,n} = 1.35~\rm{fm}^{-1}$). These DDRMF models were then used to explore the $Λ_{c} N$ effective interaction uncertainties on the description of hypernuclear bulk and single-particle properties. A systematic investigation was conducted on the existence of bound $Λ_{c}^{+}$ hypernuclei. The dominant factors affecting the existence and stability of hypernuclei were analyzed from the perspective of the $Λ_{c}^{+}$ potential. It is found that the hyperon potential is not only influenced by the Coulomb repulsion, but by an extra contribution from the rearrangement terms due to the density dependence of the meson-baryon coupling strengths. Therefore, the rearrangement term significantly impacts the stability description for light hypernuclei, while for heavier hypernuclei, the contribution from Coulomb repulsion becomes increasingly significant and eventually dominant. The discussion then delves into the bulk and single-particle properties of charmed hypernuclei using these models. It is found that even when different models yield similar hyperon potentials for nuclear matter, different treatments of nuclear medium effects could lead to disparities in the theoretical description of hypernuclear structures. This study indicates that constraints on the $ Λ_{c} N $ interaction at finite densities are crucial for the study of $ Λ_{c}^{+} $ hypernuclear structures.

nucl-th↗
arXiv2024

Autogenic Language Embedding for Coherent Point Tracking

Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences. Recent advancements have primarily focused on temporal modeling techniques to improve local feature similarity, often overlooking the valuable semantic consistency inherent in tracked points. In this paper, we introduce a novel approach leveraging language embeddings to enhance the coherence of frame-wise visual features related to the same object. Our proposed method, termed autogenic language embedding for visual feature enhancement, strengthens point correspondence in long-term sequences. Unlike existing visual-language schemes, our approach learns text embeddings from visual features through a dedicated mapping network, enabling seamless adaptation to various tracking tasks without explicit text annotations. Additionally, we introduce a consistency decoder that efficiently integrates text tokens into visual features with minimal computational overhead. Through enhanced visual consistency, our approach significantly improves tracking trajectories in lengthy videos with substantial appearance variations. Extensive experiments on widely-used tracking benchmarks demonstrate the superior performance of our method, showcasing notable enhancements compared to trackers relying solely on visual cues.

cs.CV↗
arXiv2024

Privacy Amplification via Shuffling: Unified, Simplified, and Tightened

The shuffle model of differential privacy provides promising privacy-utility balances in decentralized, privacy-preserving data analysis. However, the current analyses of privacy amplification via shuffling lack both tightness and generality. To address this issue, we propose the \emph{variation-ratio reduction} as a comprehensive framework for privacy amplification in both single-message and multi-message shuffle protocols. It leverages two new parameterizations: the total variation bounds of local messages and the probability ratio bounds of blanket messages, to determine indistinguishability levels. Our theoretical results demonstrate that our framework provides tighter bounds, especially for local randomizers with extremal probability design, where our bounds are exactly tight. Additionally, variation-ratio reduction complements parallel composition in the shuffle model, yielding enhanced privacy accounting for popular sampling-based randomizers employed in statistical queries (e.g., range queries, marginal queries, and frequent itemset mining). Empirical findings demonstrate that our numerical amplification bounds surpass existing ones, conserving up to $30\%$ of the budget for single-message protocols, $75\%$ for multi-message ones, and a striking $75\%$-$95\%$ for parallel composition. Our bounds also result in a remarkably efficient $\tilde{O}(n)$ algorithm that numerically amplifies privacy in less than $10$ seconds for $n=10^8$ users.

cs.CR↗
arXiv2024

Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software

By treating data and models as the source code, Foundation Models (FMs) become a new type of software. Mirroring the concept of software crisis, the increasing complexity of FMs making FM crisis a tangible concern in the coming decade, appealing for new theories and methodologies from the field of software engineering. In this paper, we outline our vision of introducing Foundation Model (FM) engineering, a strategic response to the anticipated FM crisis with principled engineering methodologies. FM engineering aims to mitigate potential issues in FM development and application through the introduction of declarative, automated, and unified programming interfaces for both data and model management, reducing the complexities involved in working with FMs by providing a more structured and intuitive process for developers. Through the establishment of FM engineering, we aim to provide a robust, automated, and extensible framework that addresses the imminent challenges, and discovering new research opportunities for the software engineering field.

cs.SE↗
arXiv2024

Boosting Medical Image Synthesis via Registration-guided Consistency and Disentanglement Learning

Medical image synthesis remains challenging due to misalignment noise during training. Existing methods have attempted to address this challenge by incorporating a registration-guided module. However, these methods tend to overlook the task-specific constraints on the synthetic and registration modules, which may cause the synthetic module to still generate spatially aligned images with misaligned target images during training, regardless of the registration module's function. Therefore, this paper proposes registration-guided consistency and incorporates disentanglement learning for medical image synthesis. The proposed registration-guided consistency architecture fosters task-specificity within the synthetic and registration modules by applying identical deformation fields before and after synthesis, while enforcing output consistency through an alignment loss. Moreover, the synthetic module is designed to possess the capability of disentangling anatomical structures and specific styles across various modalities. An anatomy consistency loss is introduced to further compel the synthetic module to preserve geometrical integrity within latent spaces. Experiments conducted on both an in-house abdominal CECT-CT dataset and a publicly available pelvic MR-CT dataset have demonstrated the superiority of the proposed method.

cs.CV↗
arXiv2024

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. To address this, we propose a soft deduplication method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. Central to our approach is the concept of "data commonness", a metric we introduce to quantify the degree of duplication by measuring the occurrence probabilities of samples using an n-gram model. Empirical analysis shows that this method significantly improves training efficiency, achieving comparable perplexity scores with at least a 26% reduction in required training steps. Additionally, it enhances average few-shot downstream accuracy by 1.77% when trained for an equivalent duration. Importantly, this approach consistently improves performance, even on rigorously deduplicated datasets, indicating its potential to complement existing methods and become a standard pre-training process for LLMs.

cs.CL↗
arXiv2024

WindowMixer: Intra-Window and Inter-Window Modeling for Time Series Forecasting

Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making accurate forecasting challenging. Traditional methods model point-to-point relationships, which limits their ability to capture complex temporal patterns and increases their susceptibility to noise.To address these issues, we introduce the WindowMixer model, built on an all-MLP framework. WindowMixer leverages the continuous nature of time series by examining temporal variations from a window-based perspective. It decomposes time series into trend and seasonal components, handling them individually. For trends, a fully connected (FC) layer makes predictions. For seasonal components, time windows are projected to produce window tokens, processed by Intra-Window-Mixer and Inter-Window-Mixer modules. The Intra-Window-Mixer models relationships within each window, while the Inter-Window-Mixer models relationships between windows. This approach captures intricate patterns and long-range dependencies in the data.Experiments show WindowMixer consistently outperforms existing methods in both long-term and short-term forecasting tasks.

cs.LG↗
arXiv2024

Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models

Recent research showcases the considerable potential of conditional diffusion models for generating consistent stories. However, current methods, which predominantly generate stories in an autoregressive and excessively caption-dependent manner, often underrate the contextual consistency and relevance of frames during sequential generation. To address this, we propose a novel Rich-contextual Conditional Diffusion Models (RCDMs), a two-stage approach designed to enhance story generation's semantic consistency and temporal consistency. Specifically, in the first stage, the frame-prior transformer diffusion model is presented to predict the frame semantic embedding of the unknown clip by aligning the semantic correlations between the captions and frames of the known clip. The second stage establishes a robust model with rich contextual conditions, including reference images of the known clip, the predicted frame semantic embedding of the unknown clip, and text embeddings of all captions. By jointly injecting these rich contextual conditions at the image and feature levels, RCDMs can generate semantic and temporal consistency stories. Moreover, RCDMs can generate consistent stories with a single forward inference compared to autoregressive models. Our qualitative and quantitative results demonstrate that our proposed RCDMs outperform in challenging scenarios. The code and model will be available at https://github.com/muzishen/RCDMs.

cs.CV↗
arXiv2024

An eight-neuron network for quadruped locomotion with hip-knee joint control

The gait generator, which is capable of producing rhythmic signals for coordinating multiple joints, is an essential component in the quadruped robot locomotion control framework. The biological counterpart of the gait generator is the Central Pattern Generator (abbreviated as CPG), a small neural network consisting of interacting neurons. Inspired by this architecture, researchers have designed artificial neural networks composed of simulated neurons or oscillator equations. Despite the widespread application of these designed CPGs in various robot locomotion controls, some issues remain unaddressed, including: (1) Simplistic network designs often overlook the symmetry between signal and network structure, resulting in fewer gait patterns than those found in nature. (2) Due to minimal architectural consideration, quadruped control CPGs typically consist of only four neurons, which restricts the network's direct control to leg phases rather than joint coordination. (3) Gait changes are achieved by varying the neuron couplings or the assignment between neurons and legs, rather than through external stimulation. We apply symmetry theory to design an eight-neuron network, composed of Stein neuronal models, capable of achieving five gaits and coordinated control of the hip-knee joints. We validate the signal stability of this network as a gait generator through numerical simulations, which reveal various results and patterns encountered during gait transitions using neuronal stimulation. Based on these findings, we have developed several successful gait transition strategies through neuronal stimulations. Using a commercial quadruped robot model, we demonstrate the usability and feasibility of this network by implementing motion control and gait transitions.

cs.RO↗
arXiv2024

Tokenize features, enhancing tables: the FT-TABPFN model for tabular classification

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has changed this paradigm. TabPFN uses a 12-layer transformer trained on large synthetic datasets to learn universal tabular representations. This method enables fast and accurate predictions on new tasks with a single forward pass and no need for additional training. Although TabPFN has been successful on small datasets, it generally shows weaker performance when dealing with categorical features. To overcome this limitation, we propose FT-TabPFN, which is an enhanced version of TabPFN that includes a novel Feature Tokenization layer to better handle classification features. By fine-tuning it for downstream tasks, FT-TabPFN not only expands the functionality of the original model but also significantly improves its applicability and accuracy in tabular classification. Our full source code is available for community use and development.

cs.LG↗
arXiv2024

CompVPD: Iteratively Identifying Vulnerability Patches Based on Human Validation Results with a Precise Context

Applying security patches in open source software timely is critical for ensuring the security of downstream applications. However, it is challenging to apply these patches promptly because notifications of patches are often incomplete and delayed. To address this issue, existing approaches employ deep-learning (DL) models to identify additional vulnerability patches by determining whether a code commit addresses a vulnerability. Nonetheless, these approaches suffer from low accuracy due to the imprecise context provided for the patches. To provide precise context for patches, we propose a multi-granularity slicing algorithm and an adaptive-expanding algorithm to accurately identify code related to the patches. Additionally, the precise context enables to design an iterative identification framework, CompVPD, which utilizes the human validation results, and substantially improve the effectiveness. We empirically compare CompVPD with four state-of-the-art/practice (SOTA) approaches in identifying vulnerability patches. The results demonstrate that CompVPD improves the F1 score by 20% compared to the best scores of the SOTA approaches. Additionally, CompVPD contributes to security practice by helping identify 20 vulnerability patches and 18 fixes for high-risk bugs from 2,500 recent code commits in five highly popular open-source projects.

cs.CR↗
arXiv2024

V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation

In the field of portrait video generation, the use of single images to generate portrait videos has become increasingly prevalent. A common approach involves leveraging generative models to enhance adapters for controlled generation. However, control signals (e.g., text, audio, reference image, pose, depth map, etc.) can vary in strength. Among these, weaker conditions often struggle to be effective due to interference from stronger conditions, posing a challenge in balancing these conditions. In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as facial pose and reference image. However, direct training with weak signals often leads to difficulties in convergence. To address this, we propose V-Express, a simple method that balances different control signals through the progressive training and the conditional dropout operation. Our method gradually enables effective control by weak conditions, thereby achieving generation capabilities that simultaneously take into account the facial pose, reference image, and audio. The experimental results demonstrate that our method can effectively generate portrait videos controlled by audio. Furthermore, a potential solution is provided for the simultaneous and effective use of conditions of varying strengths.

cs.CV↗
arXiv2024

TIGER: Text-Instructed 3D Gaussian Retrieval and Coherent Editing

Editing objects within a scene is a critical functionality required across a broad spectrum of applications in computer vision and graphics. As 3D Gaussian Splatting (3DGS) emerges as a frontier in scene representation, the effective modification of 3D Gaussian scenes has become increasingly vital. This process entails accurately retrieve the target objects and subsequently performing modifications based on instructions. Though available in pieces, existing techniques mainly embed sparse semantics into Gaussians for retrieval, and rely on an iterative dataset update paradigm for editing, leading to over-smoothing or inconsistency issues. To this end, this paper proposes a systematic approach, namely TIGER, for coherent text-instructed 3D Gaussian retrieval and editing. In contrast to the top-down language grounding approach for 3D Gaussians, we adopt a bottom-up language aggregation strategy to generate a denser language embedded 3D Gaussians that supports open-vocabulary retrieval. To overcome the over-smoothing and inconsistency issues in editing, we propose a Coherent Score Distillation (CSD) that aggregates a 2D image editing diffusion model and a multi-view diffusion model for score distillation, producing multi-view consistent editing with much finer details. In various experiments, we demonstrate that our TIGER is able to accomplish more consistent and realistic edits than prior work.

cs.CV↗
arXiv2024

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is often hampered by the limitations of existing digital tools, which demand extensive expertise and efforts. To narrow this disparity, we introduce CLAY, a 3D geometry and material generator designed to effortlessly transform human imagination into intricate 3D digital structures. CLAY supports classic text or image inputs as well as 3D-aware controls from diverse primitives (multi-view images, voxels, bounding boxes, point clouds, implicit representations, etc). At its core is a large-scale generative model composed of a multi-resolution Variational Autoencoder (VAE) and a minimalistic latent Diffusion Transformer (DiT), to extract rich 3D priors directly from a diverse range of 3D geometries. Specifically, it adopts neural fields to represent continuous and complete surfaces and uses a geometry generative module with pure transformer blocks in latent space. We present a progressive training scheme to train CLAY on an ultra large 3D model dataset obtained through a carefully designed processing pipeline, resulting in a 3D native geometry generator with 1.5 billion parameters. For appearance generation, CLAY sets out to produce physically-based rendering (PBR) textures by employing a multi-view material diffusion model that can generate 2K resolution textures with diffuse, roughness, and metallic modalities. We demonstrate using CLAY for a range of controllable 3D asset creations, from sketchy conceptual designs to production ready assets with intricate details. Even first time users can easily use CLAY to bring their vivid 3D imaginations to life, unleashing unlimited creativity.

cs.CV↗