arXiv subjects

Yangming Li

Publications and source records attributed to Yangming Li.

At least 19 recordsLinked to original sources

arXiv2025

GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting

A few recent works explored incorporating geometric priors to regularize the optimization of Gaussian splatting, further improving its performance. However, those early studies mainly focused on the use of low-order geometric priors (e.g., normal vector), and they might also be unreliably estimated by noise-sensitive methods, like local principal component analysis. To address their limitations, we first present GeoSplat, a general geometry-constrained optimization framework that exploits both first-order and second-order geometric quantities to improve the entire training pipeline of Gaussian splatting, including Gaussian initialization, gradient update, and densification. As an example, we initialize the scales of 3D Gaussian primitives in terms of principal curvatures, leading to a better coverage of the object surface than random initialization. Secondly, based on certain geometric structures (e.g., local manifold), we introduce efficient and noise-robust estimation methods that provide dynamic geometric priors for our framework. We conduct extensive experiments on multiple datasets for novel view synthesis, showing that our framework, GeoSplat, significantly improves the performance of Gaussian splatting and outperforms previous baselines.

cs.CV↗

arXiv2025

Adaptive Correction for Ensuring Conservation Laws in Neural Operators

Physical laws, such as the conversation of mass and momentum, are fundamental principles in many physical systems. Neural operators have achieved promising performance in learning the solutions to those systems, but often fail to ensure conservation. Existing methods typically enforce strict conservation via hand-crafted post-processing or architectural constraints, leading to limited model flexibility and adaptability. In this work, we propose a novel plug-and-play adaptive correction approach to ensure the conservation of fundamental linear and quadratic quantities for neural operator outputs. Our method introduces a lightweight learnable operator to adaptively enforce the target conservation law during training. This method allows the model to flexibly and adaptively correct its output to guarantee strict conservation. We provide a theoretical result showing that our correction method does not hamper the expression ability of neural operators and can potentially achieve lower reconstruction loss than their conservation-constrained counterparts. Our method is evaluated across multiple neural operator architectures and representative PDEs. Extensive experiments show that incorporating our correction method into baseline models significantly improves both accuracy and stability. In addition, the experimental results demonstrate that our approach consistently achieves superior performance over widely used conservation-enforcement techniques on various PDE benchmarks.

cs.LG↗

arXiv2025

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Text watermarking aims to subtly embed statistical signals into text by controlling the Large Language Model (LLM)'s sampling process, enabling watermark detectors to verify that the output was generated by the specified model. The robustness of these watermarking algorithms has become a key factor in evaluating their effectiveness. Current text watermarking algorithms embed watermarks in high-entropy tokens to ensure text quality. In this paper, we reveal that this seemingly benign design can be exploited by attackers, posing a significant risk to the robustness of the watermark. We introduce a generic efficient paraphrasing attack, the Self-Information Rewrite Attack (SIRA), which leverages the vulnerability by calculating the self-information of each token to identify potential pattern tokens and perform targeted attack. Our work exposes a widely prevalent vulnerability in current watermarking algorithms. The experimental results show SIRA achieves nearly 100% attack success rates on seven recent watermarking methods with only 0.88 USD per million tokens cost. Our approach does not require any access to the watermark algorithms or the watermarked LLM and can seamlessly transfer to any LLM as the attack model, even mobile-level models. Our findings highlight the urgent need for more robust watermarking.

cs.LG↗

arXiv2025

Enhancing Fourier Neural Operators with Local Spatial Features

Partial Differential Equation (PDE) problems often exhibit strong local spatial structures, and effectively capturing these structures is critical for approximating their solutions. Recently, the Fourier Neural Operator (FNO) has emerged as an efficient approach for solving these PDE problems. By using parametrization in the frequency domain, FNOs can efficiently capture global patterns. However, this approach inherently overlooks the critical role of local spatial features, as frequency-domain parameterized convolutions primarily emphasize global interactions without encoding comprehensive localized spatial dependencies. Although several studies have attempted to address this limitation, their extracted Local Spatial Features (LSFs) remain insufficient, and computational efficiency is often compromised. To address this limitation, we introduce a convolutional neural network (CNN)-based feature pre-extractor to capture LSFs directly from input data, resulting in a hybrid architecture termed \textit{Conv-FNO}. Furthermore, we introduce two novel resizing schemes to make our Conv-FNO resolution invariant. In this work, we focus on demonstrating the effectiveness of incorporating LSFs into FNOs by conducting both a theoretical analysis and extensive numerical experiments. Our findings show that this simple yet impactful modification enhances the representational capacity of FNOs and significantly improves performance on challenging PDE benchmarks.

cs.LG↗

arXiv2025

Generative Unordered Flow for Set-Structured Data Generation

Flow-based generative models have demonstrated promising performance across a broad spectrum of data modalities (e.g., image and text). However, there are few works exploring their extension to unordered data (e.g., spatial point set), which is not trivial because previous models are mostly designed for vector data that are naturally ordered. In this paper, we present unordered flow, a type of flow-based generative model for set-structured data generation. Specifically, we convert unordered data into an appropriate function representation, and learn the probability measure of such representations through function-valued flow matching. For the inverse map from a function representation to unordered data, we propose a method similar to particle filtering, with Langevin dynamics to first warm-up the initial particles and gradient-based search to update them until convergence. We have conducted extensive experiments on multiple real-world datasets, showing that our unordered flow model is very effective in generating set-structured data and significantly outperforms previous baselines.

cs.LG↗

arXiv2024

Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space

Deep Generative Models (DGMs), including Energy-Based Models (EBMs) and Score-based Generative Models (SGMs), have advanced high-fidelity data generation and complex continuous distribution approximation. However, their application in Markov Decision Processes (MDPs), particularly in distributional Reinforcement Learning (RL), remains underexplored, with conventional histogram-based methods dominating the field. This paper rigorously highlights that this application gap is caused by the nonlinearity of modern DGMs, which conflicts with the linearity required by the Bellman equation in MDPs. For instance, EBMs involve nonlinear operations such as exponentiating energy functions and normalizing constants. To address this, we introduce Bellman Diffusion, a novel DGM framework that maintains linearity in MDPs through gradient and scalar field modeling. With divergence-based training techniques to optimize neural network proxies and a new type of stochastic differential equation (SDE) for sampling, Bellman Diffusion is guaranteed to converge to the target distribution. Our empirical results show that Bellman Diffusion achieves accurate field estimations and is a capable image generator, converging 1.5x faster than the traditional histogram-based baseline in distributional RL tasks. This work enables the effective integration of DGMs into MDP applications, unlocking new avenues for advanced decision-making frameworks.

cs.LG↗

arXiv2024

A Study of Posterior Stability for Time-Series Latent Diffusion

Latent diffusion has demonstrated promising results in image generation and permits efficient sampling. However, this framework might suffer from the problem of posterior collapse when applied to time series. In this paper, we first show that posterior collapse will reduce latent diffusion to a variational autoencoder (VAE), making it less expressive. This highlights the importance of addressing this issue. We then introduce a principled method: dependency measure, that quantifies the sensitivity of a recurrent decoder to input variables. Using this tool, we confirm that posterior collapse significantly affects time-series latent diffusion on real datasets, and a phenomenon termed dependency illusion is also discovered in the case of shuffled time series. Finally, building on our theoretical and empirical studies, we introduce a new framework that extends latent diffusion and has a stable posterior. Extensive experiments on multiple real time-series datasets show that our new framework is free from posterior collapse and significantly outperforms previous baselines in time series synthesis.

cs.LG↗

arXiv2024

Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples

Diffusion models are mainly studied on image data. However, non-image data (e.g., tabular data) are also prevalent in real applications and tend to be noisy due to some inevitable factors in the stage of data collection, degrading the generation quality of diffusion models. In this paper, we consider a novel problem setting where every collected sample is paired with a vector indicating the data quality: risk vector. This setting applies to many scenarios involving noisy data and we propose risk-sensitive SDE, a type of stochastic differential equation (SDE) parameterized by the risk vector, to address it. With some proper coefficients, risk-sensitive SDE can minimize the negative effect of noisy samples on the optimization of diffusion models. We conduct systematic studies for both Gaussian and non-Gaussian noise distributions, providing analytical forms of risk-sensitive SDE. To verify the effectiveness of our method, we have conducted extensive experiments on multiple tabular and time-series datasets, showing that risk-sensitive SDE permits a robust optimization of diffusion models with noisy samples and significantly outperforms previous baselines.

cs.LG↗

arXiv2023

TS-Diffusion: Generating Highly Complex Time Series with Diffusion Models

While current generative models have achieved promising performances in time-series synthesis, they either make strong assumptions on the data format (e.g., regularities) or rely on pre-processing approaches (e.g., interpolations) to simplify the raw data. In this work, we consider a class of time series with three common bad properties, including sampling irregularities, missingness, and large feature-temporal dimensions, and introduce a general model, TS-Diffusion, to process such complex time series. Our model consists of three parts under the framework of point process. The first part is an encoder of the neural ordinary differential equation (ODE) that converts time series into dense representations, with the jump technique to capture sampling irregularities and self-attention mechanism to handle missing values; The second component of TS-Diffusion is a diffusion model that learns from the representation of time series. These time-series representations can have a complex distribution because of their high dimensions; The third part is a decoder of another ODE that generates time series with irregularities and missing values given their representations. We have conducted extensive experiments on multiple time-series datasets, demonstrating that TS-Diffusion achieves excellent results on both conventional and complex time series and significantly outperforms previous baselines.

cs.LG↗

arXiv2023

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models

Because diffusion models have shown impressive performances in a number of tasks, such as image synthesis, there is a trend in recent works to prove (with certain assumptions) that these models have strong approximation capabilities. In this paper, we show that current diffusion models actually have an expressive bottleneck in backward denoising and some assumption made by existing theoretical guarantees is too strong. Based on this finding, we prove that diffusion models have unbounded errors in both local and global denoising. In light of our theoretical studies, we introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising. SMD not only permits diffusion models to well approximate any Gaussian mixture distributions in theory, but also is simple and efficient for implementation. Our experiments on multiple image datasets show that SMD significantly improves different types of diffusion models (e.g., DDPM), espeically in the situation of few backward iterations.

cs.LG↗

arXiv2023

On Error Propagation of Diffusion Models

Although diffusion models (DMs) have shown promising performances in a number of tasks (e.g., speech synthesis and image generation), they might suffer from error propagation because of their sequential structure. However, this is not certain because some sequential models, such as Conditional Random Field (CRF), are free from this problem. To address this issue, we develop a theoretical framework to mathematically formulate error propagation in the architecture of DMs, The framework contains three elements, including modular error, cumulative error, and propagation equation. The modular and cumulative errors are related by the equation, which interprets that DMs are indeed affected by error propagation. Our theoretical study also suggests that the cumulative error is closely related to the generation quality of DMs. Based on this finding, we apply the cumulative error as a regularization term to reduce error propagation. Because the term is computationally intractable, we derive its upper bound and design a bootstrap algorithm to efficiently estimate the bound for optimization. We have conducted extensive experiments on multiple image datasets, showing that our proposed regularization reduces error propagation, significantly improves vanilla DMs, and outperforms previous baselines.

cs.LG↗

arXiv2023

3 Dimensional Dense Reconstruction: A Review of Algorithms and Dataset

3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This work systematically introduces classical methods of 3D dense reconstruction based on geometric and optical models, as well as methods based on deep learning. It also introduces datasets for deep learning and the performance and advantages and disadvantages demonstrated by deep learning methods on these datasets.

cs.CV↗

arXiv2022

Deep Causal Learning for Robotic Intelligence

This invited review discusses causal learning in the context of robotic intelligence. The paper introduced the psychological findings on causal learning in human cognition, then it introduced the traditional statistical solutions on causal discovery and causal inference. The paper reviewed recent deep causal learning algorithms with a focus on their architectures and the benefits of using deep nets and discussed the gap between deep causal learning and the needs of robotic intelligence.

cs.RO↗

arXiv2022

Efficient Sub-structured Knowledge Distillation

Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output space. In this work, we propose an approach that is much simpler in its formulation and far more efficient for training than existing approaches. Specifically, we transfer the knowledge from a teacher model to its student model by locally matching their predictions on all sub-structures, instead of the whole output space. In this manner, we avoid adopting some time-consuming techniques like dynamic programming (DP) for decoding output structures, which permits parallel computation and makes the training process even faster in practice. Besides, it encourages the student model to better mimic the internal behavior of the teacher model. Experiments on two structured prediction tasks demonstrate that our approach outperforms previous methods and halves the time cost for one training epoch.

cs.LG↗

arXiv2021

Real-time Informative Surgical Skill Assessment with Gaussian Process Learning

Endoscopic Sinus and Skull Base Surgeries (ESSBSs) is a challenging and potentially dangerous surgical procedure, and objective skill assessment is the key components to improve the effectiveness of surgical training, to re-validate surgeons' skills, and to decrease surgical trauma and the complication rate in operating rooms. Because of the complexity of surgical procedures, the variation of operation styles, and the fast development of new surgical skills, the surgical skill assessment remains a challenging problem. This work presents a novel Gaussian Process Learning-based heuristic automatic objective surgical skill assessment method for ESSBSs. Different with classical surgical skill assessment algorithms, the proposed method 1) utilizes the kinematic features in surgical instrument relative movements, instead of using specific surgical tasks or the statistics to assess skills in real-time; 2) provide informative feedback, instead of a summative scores; 3) has the ability to incrementally learn from new data, instead of depending on a fixed dataset. The proposed method projects the instrument movements into the endoscope coordinate to reduce the data dimensionality. It then extracts the kinematic features of the projected data and learns the relationship between surgical skill levels and the features with the Gaussian Process learning technique. The proposed method was verified in full endoscopic skull base and sinus surgeries on cadavers. These surgeries have different pathology, requires different treatment and has different complexities. The experimental results show that the proposed method reaches 100\% prediction precision for complete surgical procedures and 90\% precision for real-time prediction assessment.

cs.LG↗

arXiv2021

Real-time Virtual Intraoperative CT for Image Guided Surgery

Abstract. Purpose: This paper presents a scheme for generating virtual intraoperative CT scans in order to improve surgical completeness in Endoscopic Sinus Surgeries (ESS). Approach: The work presents three methods, the tip motion-based, the tip trajectory-based, and the instrument based, along with non-parametric smoothing and Gaussian Process Regression, for virtual intraoperative CT generation. Results: The proposed methods studied and compared on ESS performed on cadavers. Surgical results show all three methods improve the Dice Similarity Coefficients > 86%, with F-score > 92% and precision > 89.91%. The tip trajectory-based method was found to have best performance and reached 96.87% precision in surgical completeness evaluation. Conclusions: This work demonstrated that virtual intraoperative CT scans improves the consistency between the actual surgical scene and the reference model, and improves surgical completeness in ESS. Comparing with actual intraoperative CT scans, the proposed scheme has no impact on existing surgical protocols, does not require extra hardware other than the one is already available in most ESS overcome the high costs, the repeated radiation, and the elongated anesthesia caused by actual intraoperative CTs, and is practical in ESS.

eess.IV↗

arXiv2021

Rethinking Negative Sampling for Handling Missing Entity Annotations

Negative sampling is highly effective in handling missing annotations for named entity recognition (NER). One of our contributions is an analysis on how it makes sense through introducing two insightful concepts: missampling and uncertainty. Empirical studies show low missampling rate and high uncertainty are both essential for achieving promising performances with negative sampling. Based on the sparsity of named entities, we also theoretically derive a lower bound for the probability of zero missampling rate, which is only relevant to sentence length. The other contribution is an adaptive and weighted sampling distribution that further improves negative sampling via our former analysis. Experiments on synthetic datasets and well-annotated datasets (e.g., CoNLL-2003) show that our proposed approach benefits negative sampling in terms of F1 score and loss convergence. Besides, models with improved negative sampling have achieved new state-of-the-art results on real-world datasets (e.g., EC).

cs.CL↗

arXiv2021

Neural Sequence Segmentation as Determining the Leftmost Segments

Prior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we propose a novel framework that incrementally segments natural language sentences at segment level. For every step in segmentation, it recognizes the leftmost segment of the remaining sequence. Implementations involve LSTM-minus technique to construct the phrase representations and recurrent neural networks (RNN) to model the iterations of determining the leftmost segments. We have conducted extensive experiments on syntactic chunking and Chinese part-of-speech (POS) tagging across 3 datasets, demonstrating that our methods have significantly outperformed previous all baselines and achieved new state-of-the-art results. Moreover, qualitative analysis and the study on segmenting long-length sentences verify its effectiveness in modeling long-term dependencies.

cs.CL↗