Search

The goal of product copywriting is to capture the interest of potential buyers by emphasizing the features of products through text descriptions. As e-commerce platforms offer a wide range of services, it's becoming essential to dynamically adjust the styles of these auto-generated descriptions. Typical approaches to copywriting generation often rely solely on specified product attributes, which may result in dull and repetitive content. To tackle this issue, we propose to generate copywriting based on customer reviews, as they provide firsthand practical experiences with products, offering a richer source of information than just product attributes. We have developed a sequence-to-sequence framework, enhanced with reinforcement learning, to produce copywriting that is attractive, authentic, and rich in information. Our framework outperforms all existing baseline and zero-shot large language models, including LLaMA-2-chat-7B and GPT-3.5, in terms of both attractiveness and faithfulness. Furthermore, this work features the use of LLMs for aspect-based summaries collection and argument allure assessment. Experiments demonstrate the effectiveness of using LLMs for marketing domain corpus construction. The code and the dataset is publicly available at: https://github.com/YuXiangLin1234/Copywriting-Generation., Comment: NAACL 2024 main conference paper

We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into 3,807 multiple-choice questions, paired with single or multiple images and visual prompting. While humans get 95.70% accuracy on average, Blink is surprisingly challenging for existing multimodal LLMs: even the best-performing GPT-4V and Gemini achieve accuracies of 51.26% and 45.72%, only 13.17% and 7.63% higher than random guessing, indicating that such perception abilities have not "emerged" yet in recent multimodal LLMs. Our analysis also highlights that specialist CV models could solve these problems much better, suggesting potential pathways for future improvements. We believe Blink will stimulate the community to help multimodal LLMs catch up with human-level visual perception., Comment: Multimodal Benchmark, Project Url: https://zeyofu.github.io/blink/, ECCV 2024

Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D poses and resulting in false positives. We conduct thorough studies on key factors of ill-conformational problems when applying autoregressive methods and diffusion to SBDD, including mode collapse and hybrid continuous-discrete space. In this paper, we introduce MolCRAFT, the first SBDD model that operates in the continuous parameter space, together with a novel noise reduced sampling strategy. Empirical results show that our model consistently achieves superior performance in binding affinity with more stable 3D structure, demonstrating our ability to accurately model interatomic interactions. To our best knowledge, MolCRAFT is the first to achieve reference-level Vina Scores (-6.59 kcal/mol) with comparable molecular size, outperforming other strong baselines by a wide margin (-0.84 kcal/mol). Code is available at https://github.com/AlgoMole/MolCRAFT., Comment: Accepted to ICML 2024

Creating high-quality and interactive virtual environments, such as games and simulators, often involves complex and costly manual modeling processes. In this paper, we present Video2Game, a novel approach that automatically converts videos of real-world scenes into realistic and interactive game environments. At the heart of our system are three core components:(i) a neural radiance fields (NeRF) module that effectively captures the geometry and visual appearance of the scene; (ii) a mesh module that distills the knowledge from NeRF for faster rendering; and (iii) a physics module that models the interactions and physical dynamics among the objects. By following the carefully designed pipeline, one can construct an interactable and actionable digital replica of the real world. We benchmark our system on both indoor and large-scale outdoor scenes. We show that we can not only produce highly-realistic renderings in real-time, but also build interactive games on top., Comment: CVPR 2024. Project page (with code): https://video2game.github.io/

Source code vulnerability detection aims to identify inherent vulnerabilities to safeguard software systems from potential attacks. Many prior studies overlook diverse vulnerability characteristics, simplifying the problem into a binary (0-1) classification task for example determining whether it is vulnerable or not. This poses a challenge for a single deep learning-based model to effectively learn the wide array of vulnerability characteristics. Furthermore, due to the challenges associated with collecting large-scale vulnerability data, these detectors often overfit limited training datasets, resulting in lower model generalization performance. To address the aforementioned challenges, in this work, we introduce a fine-grained vulnerability detector namely FGVulDet. Unlike previous approaches, FGVulDet employs multiple classifiers to discern characteristics of various vulnerability types and combines their outputs to identify the specific type of vulnerability. Each classifier is designed to learn type-specific vulnerability semantics. Additionally, to address the scarcity of data for some vulnerability types and enhance data diversity for learning better vulnerability semantics, we propose a novel vulnerability-preserving data augmentation technique to augment the number of vulnerabilities. Taking inspiration from recent advancements in graph neural networks for learning program semantics, we incorporate a Gated Graph Neural Network (GGNN) and extend it to an edge-aware GGNN to capture edge-type information. FGVulDet is trained on a large-scale dataset from GitHub, encompassing five different types of vulnerabilities. Extensive experiments compared with static-analysis-based approaches and learning-based approaches have demonstrated the effectiveness of FGVulDet.

Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist that LLM cannot properly predict. Such faults will harm the usability of LLMs in general and could introduce safety issues in reliability-critical systems such as autonomous driving systems. How to quickly reveal these faults in real-world datasets that LLM could face is important, but challenging. The major reason is that the ground truth is necessary but the data labeling process is heavy considering the time and human effort. To handle this problem, in the conventional deep learning testing field, test selection methods have been proposed for efficiently evaluating deep learning models by prioritizing faults. However, despite their importance, the usefulness of these methods on LLMs is unclear, and lack of exploration. In this paper, we conduct the first empirical study to investigate the effectiveness of existing fault detection methods for LLMs. Experimental results on four different tasks~(including both code tasks and natural language processing tasks) and four LLMs~(e.g., LLaMA3 and GPT4) demonstrated that simple methods such as Margin perform well on LLMs but there is still a big room for improvement. Based on the study, we further propose \textbf{MuCS}, a prompt \textbf{Mu}tation-based prediction \textbf{C}onfidence \textbf{S}moothing framework to boost the fault detection capability of existing methods. Concretely, multiple prompt mutation techniques have been proposed to help collect more diverse outputs for confidence smoothing. The results show that our proposed framework significantly enhances existing methods with the improvement of test relative coverage by up to 70.53\%.

Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. Like traditional SE tools, open-source collaboration is key in realising the excellent products. However, with AI models, the essential need is in data. The collaboration of these AI-based SE models hinges on maximising the sources of high-quality data. However, data especially of high quality, often holds commercial or sensitive value, making it less accessible for open-source AI-based SE projects. This reality presents a significant barrier to the development and enhancement of AI-based SE tools within the software engineering community. Therefore, researchers need to find solutions for enabling open-source AI-based SE models to tap into resources by different organisations. Addressing this challenge, our position paper investigates one solution to facilitate access to diverse organizational resources for open-source AI models, ensuring privacy and commercial sensitivities are respected. We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security. Additionally, we present guidelines for developers on AI-based SE tool collaboration, covering data requirements, model architecture, updating strategies, and version control. Given the significant influence of data characteristics on FL, our research examines the effect of code data heterogeneity on FL performance.

Recently, Automated Vulnerability Localization (AVL) has attracted much attention, aiming to facilitate diagnosis by pinpointing the lines of code responsible for discovered vulnerabilities. Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in vulnerability localization remains underexplored. In this work, we perform the first comprehensive study of LLMs for AVL. Our investigation encompasses 10+ leading LLMs suitable for code analysis, including ChatGPT and various open-source models, across three architectural types: encoder-only, encoder-decoder, and decoder-only, with model sizes ranging from 60M to 16B parameters. We explore the efficacy of these LLMs using 4 distinct paradigms: zero-shot learning, one-shot learning, discriminative fine-tuning, and generative fine-tuning. Our evaluation framework is applied to the BigVul-based dataset for C/C++, and an additional dataset comprising smart contract vulnerabilities. The results demonstrate that discriminative fine-tuning of LLMs can significantly outperform existing learning-based methods for AVL, while other paradigms prove less effective or unexpectedly ineffective for the task. We also identify challenges related to input length and unidirectional context in fine-tuning processes for encoders and decoders. We then introduce two remedial strategies: the sliding window and the right-forward embedding, both of which substantially enhance performance. Furthermore, our findings highlight certain generalization capabilities of LLMs across Common Weakness Enumerations (CWEs) and different projects, indicating a promising pathway toward their practical application in vulnerability localization.

Rug pulls pose a grave threat to the cryptocurrency ecosystem, leading to substantial financial loss and undermining trust in decentralized finance (DeFi) projects. With the emergence of new rug pull patterns, research on rug pull is out of state. To fill this gap, we first conducted an extensive analysis of the literature review, encompassing both scholarly and industry sources. By examining existing academic articles and industrial discussions on rug pull projects, we present a taxonomy inclusive of 34 root causes, introducing six new categories inspired by industry sources: burn, hidden owner, ownership transfer, unverified contract, external call, and fake LP lock. Based on the developed taxonomy, we evaluated current rug pull datasets and explored the effectiveness and limitations of existing detection mechanisms. Our evaluation indicates that the existing datasets, which document 2,448 instances, address only 7 of the 34 root causes, amounting to a mere 20% coverage. It indicates that existing open-source datasets need to be improved to study rug pulls. In response, we have constructed a more comprehensive dataset containing 2,360 instances, expanding the coverage to 54% with the best effort. In addition, the examination of 14 detection tools showed that they can identify 25 of the 34 root causes, achieving a coverage of 73.5%. There are nine root causes (Fake LP Lock, Hidden Fee, and Destroy Token, Fake Money Transfer, Ownership Transfer, Liquidity Pool Block, Freeze Account, Wash-Trading, Hedge) that the existing tools cannot cover. Our work indicates that there is a significant gap between current research and detection tools, and the actual situation of rug pulls.

Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential in auditing smart contracts, but the state-of-the-art indicates that even GPT-4 can achieve only 30% precision (when both decision and justification are correct). This is likely because off-the-shelf LLMs were primarily pre-trained on a general text/code corpus and not fine-tuned on the specific domain of Solidity smart contract auditing. In this paper, we propose iAudit, a general framework that combines fine-tuning and LLM-based agents for intuitive smart contract auditing with justifications. Specifically, iAudit is inspired by the observation that expert human auditors first perceive what could be wrong and then perform a detailed analysis of the code to identify the cause. As such, iAudit employs a two-stage fine-tuning approach: it first tunes a Detector model to make decisions and then tunes a Reasoner model to generate causes of vulnerabilities. However, fine-tuning alone faces challenges in accurately identifying the optimal cause of a vulnerability. Therefore, we introduce two LLM-based agents, the Ranker and Critic, to iteratively select and debate the most suitable cause of vulnerability based on the output of the fine-tuned Reasoner model. To evaluate iAudit, we collected a balanced dataset with 1,734 positive and 1,810 negative samples to fine-tune iAudit. We then compared it with traditional fine-tuned models (CodeBERT, GraphCodeBERT, CodeT5, and UnixCoder) as well as prompt learning-based LLMs (GPT4, GPT-3.5, and CodeLlama-13b/34b). On a dataset of 263 real smart contract vulnerabilities, iAudit achieves an F1 score of 91.21% and an accuracy of 91.11%. The causes generated by iAudit achieved a consistency of about 38% compared to the ground truth causes., Comment: Accepted for the 47th International Conference on Software Engineering (ICSE 2025)

This paper develops a systematic framework for the evidence neuroscientists use to establish whether a neural response represents a feature. Researchers try to establish that the neural response is (1) sensitive and (2) specific to the feature, (3) invariant to other features, and (4) functional, which means that it is used downstream in the brain. We formalize these desiderata in information-theoretic terms. This formalism allows us to precisely state the desiderata while unifying the different analysis methods used in neuroscience under one framework. We discuss how common methods such as correlational analyses, decoding and encoding models, representational similarity analysis, and tests of statistical dependence are used to evaluate the desiderata. In doing so, we provide a common terminology to researchers that helps to clarify disagreements, to compare and integrate results across studies and research groups, and to identify when evidence might be missing and when evidence for some representational conclusion is strong. We illustrate the framework with several canonical examples, including the representation of orientation, numerosity, faces, and spatial location. We end by discussing how the framework can be extended to cover models of the neural code, multi-stage models, and other domains., Comment: 50 pages, 11 figures

Advanced generative model (e.g., diffusion model) derived from simplified continuity assumptions of data distribution, though showing promising progress, has been difficult to apply directly to geometry generation applications due to the multi-modality and noise-sensitive nature of molecule geometry. This work introduces Geometric Bayesian Flow Networks (GeoBFN), which naturally fits molecule geometry by modeling diverse modalities in the differentiable parameter space of distributions. GeoBFN maintains the SE-(3) invariant density modeling property by incorporating equivariant inter-dependency modeling on parameters of distributions and unifying the probabilistic modeling of different modalities. Through optimized training and sampling techniques, we demonstrate that GeoBFN achieves state-of-the-art performance on multiple 3D molecule generation benchmarks in terms of generation quality (90.87% molecule stability in QM9 and 85.6% atom stability in GEOM-DRUG. GeoBFN can also conduct sampling with any number of steps to reach an optimal trade-off between efficiency and quality (e.g., 20-times speedup without sacrificing performance)., Comment: ICLR 2024

Isolated interacting quantum systems generally thermalize, yet there are several counterexamples for the breakdown of ergodicity, such as many-body localization and quantum scars. Recently, ergodicity breaking has been observed in systems subjected to linear potentials, termed Stark many-body localization. This phenomenon is closely associated with Hilbert-space fragmentation, characterized by a strong dependence of dynamics on initial conditions. Here, we experimentally explore initial-state dependent dynamics using a ladder-type superconducting processor with up to 24 qubits, which enables precise control of the qubit frequency and initial state preparation. In systems with linear potentials, we observe distinct non-equilibrium dynamics for initial states with the same quantum numbers and energy, but with varying domain wall numbers. This distinction becomes increasingly pronounced as the system size grows, in contrast with disordered interacting systems. Our results provide convincing experimental evidence of the fragmentation in Stark systems, enriching our understanding of the weak breakdown of ergodicity., Comment: main text: 7 pages, 4 figures; supplementary: 13 pages, 14 figures

Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-switch protein sequences and utilizing a multi-scale position encoding to capture relationships among residues and atoms. Experimental results indicate that ESM-AA surpasses previous methods in protein-molecule tasks, demonstrating the full utilization of protein language models. Further investigations reveal that through unified molecular modeling, ESM-AA not only gains molecular knowledge but also retains its understanding of proteins. The source codes of ESM-AA are publicly released at https://github.com/zhengkangjie/ESM-AA., Comment: ICML2024 camera-ready, update some experimental results, add github url, fix some typos

In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.

In recent years, self-supervised learning has emerged as a powerful tool to harness abundant unlabelled data for representation learning and has been broadly adopted in diverse areas. However, when applied to molecular representation learning (MRL), prevailing techniques such as masked sub-unit reconstruction often fall short, due to the high degree of freedom in the possible combinations of atoms within molecules, which brings insurmountable complexity to the masking-reconstruction paradigm. To tackle this challenge, we introduce REMO, a self-supervised learning framework that takes advantage of well-defined atom-combination rules in common chemistry. Specifically, REMO pre-trains graph/Transformer encoders on 1.7 million known chemical reactions in the literature. We propose two pre-training objectives: Masked Reaction Centre Reconstruction (MRCR) and Reaction Centre Identification (RCI). REMO offers a novel solution to MRL by exploiting the underlying shared patterns in chemical reactions as \textit{context} for pre-training, which effectively infers meaningful representations of common chemistry knowledge. Such contextual representations can then be utilized to support diverse downstream molecular tasks with minimum finetuning, such as affinity prediction and drug-drug interaction prediction. Extensive experimental results on MoleculeACE, ACNet, drug-drug interaction (DDI), and reaction type classification show that across all tested downstream tasks, REMO outperforms the standard baseline of single-molecule masked modeling used in current MRL. Remarkably, REMO is the pioneering deep learning model surpassing fingerprint-based methods in activity cliff benchmarks., Comment: Preprint. Under Review

Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Planning (OUIP), which generates personalized urban itineraries from user requests in natural language. We then present ITINERA, an OUIP system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs. This involves decomposing user requests, selecting candidate points of interest (POIs), ordering the POIs based on cluster-aware spatial optimization, and generating the itinerary. Experiments on real-world datasets and the performance of the deployed system demonstrate our system's capacity to deliver personalized and spatially coherent itineraries compared to current solutions. Source codes of ITINERA are available at https://github.com/YihongT/ITINERA.

Large language models (LLMs) have demonstrated significant potential in various tasks, including those requiring human-level intelligence, such as vulnerability detection. However, recent efforts to use LLMs for vulnerability detection remain preliminary, as they lack a deep understanding of whether a subject LLM's vulnerability reasoning capability stems from the model itself or from external aids such as knowledge retrieval and tooling support. In this paper, we aim to decouple LLMs' vulnerability reasoning from other capabilities, such as vulnerability knowledge adoption, context information retrieval, and advanced prompt schemes. We introduce LLM4Vuln, a unified evaluation framework that separates and assesses LLMs' vulnerability reasoning capabilities and examines improvements when combined with other enhancements. We conduct controlled experiments using 147 ground-truth vulnerabilities and 147 non-vulnerable cases in Solidity, Java and C/C++, testing them in a total of 3,528 scenarios across four LLMs (GPT-3.5, GPT-4, Phi-3, and Llama 3). Our findings reveal the varying impacts of knowledge enhancement, context supplementation, and prompt schemes. We also identify 14 zero-day vulnerabilities in four pilot bug bounty programs, resulting in $3,576 in bounties., Comment: This is a technical report by Nanyang Technological University. Updated to support Solidity, Java and C/C++

Our world is full of identical objects (\emphe.g., cans of coke, cars of same model). These duplicates, when seen together, provide additional and strong cues for us to effectively reason about 3D. Inspired by this observation, we introduce Structure from Duplicates (SfD), a novel inverse graphics framework that reconstructs geometry, material, and illumination from a single image containing multiple identical objects. SfD begins by identifying multiple instances of an object within an image, and then jointly estimates the 6DoF pose for all instances.An inverse graphics pipeline is subsequently employed to jointly reason about the shape, material of the object, and the environment light, while adhering to the shared geometry and material constraint across instances. Our primary contributions involve utilizing object duplicates as a robust prior for single-image inverse graphics and proposing an in-plane rotation-robust Structure from Motion (SfM) formulation for joint 6-DoF object pose estimation. By leveraging multi-view cues from a single image, SfD generates more realistic and detailed 3D reconstructions, significantly outperforming existing single image reconstruction models and multi-view reconstruction approaches with a similar or greater number of observations., Comment: Code: https://github.com/Tianhang-Cheng/SfD

Thouless pumping, a dynamical version of the integer quantum Hall effect, represents the quantized charge pumped during an adiabatic cyclic evolution. Here we report experimental observations of nontrivial topological pumping that is induced by disorder even during a topologically trivial pumping trajectory. With a 41-qubit superconducting quantum processor, we develop a Floquet engineering technique to realize cycles of adiabatic pumping by simultaneously varying the on-site potentials and the hopping couplings. We demonstrate Thouless pumping in the presence of disorder and show its breakdown as the strength of disorder increases. Moreover, we observe two types of topological pumping that are induced by on-site potential disorder and hopping disorder, respectively. Especially, an intrinsic topological pump that is induced by quasi-periodic hopping disorder has never been experimentally realized before. Our highly controllable system provides a valuable quantum simulating platform for studying various aspects of topological physics in the presence of disorder.

The generation of 3D molecules requires simultaneously deciding the categorical features~(atom types) and continuous features~(atom coordinates). Deep generative models, especially Diffusion Models (DMs), have demonstrated effectiveness in generating feature-rich geometries. However, existing DMs typically suffer from unstable probability dynamics with inefficient sampling speed. In this paper, we introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics. More specifically, we propose a hybrid probability path where the coordinates probability path is regularized by an equivariant optimal transport, and the information between different modalities is aligned. Experimentally, the proposed method could consistently achieve better performance on multiple molecule generation benchmarks with 4.75$\times$ speed up of sampling on average., Comment: NeurIPS 2023

Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen during training. Camera simulation provides a cost-effective solution to create a large dataset of images captured under different lighting conditions. Towards this goal, we propose LightSim, a neural lighting camera simulation system that enables diverse, realistic, and controllable data generation. LightSim automatically builds lighting-aware digital twins at scale from collected raw sensor data and decomposes the scene into dynamic actors and static background with accurate geometry, appearance, and estimated scene lighting. These digital twins enable actor insertion, modification, removal, and rendering from a new viewpoint, all in a lighting-aware manner. LightSim then combines physically-based and learnable deferred rendering to perform realistic relighting of modified scenes, such as altering the sun location and modifying the shadows or changing the sun brightness, producing spatially- and temporally-consistent camera videos. Our experiments show that LightSim generates more realistic relighting results than prior work. Importantly, training perception models on data generated by LightSim can significantly improve their performance., Comment: NeurIPS 2023. Project page: https://waabi.ai/lightsim/

Missing data is a pervasive issue in both scientific and engineering tasks, especially for the modeling of spatiotemporal data. This problem attracts many studies to contribute to data-driven solutions. Existing imputation solutions mainly include low-rank models and deep learning models. The former assumes general structural priors but has limited model capacity. The latter possesses salient features of expressivity but lacks prior knowledge of the underlying spatiotemporal structures. Leveraging the strengths of both two paradigms, we demonstrate a low rankness-induced Transformer to achieve a balance between strong inductive bias and high model expressivity. The exploitation of the inherent structures of spatiotemporal data enables our model to learn balanced signal-noise representations, making it generalizable for a variety of imputation problems. We demonstrate its superiority in terms of accuracy, efficiency, and versatility in heterogeneous datasets, including traffic flow, solar energy, smart meters, and air quality. Promising empirical results provide strong conviction that incorporating time series primitives, such as low-rankness, can substantially facilitate the development of a generalizable model to approach a wide range of spatiotemporal imputation problems., Comment: Accepted by KDD'24 (Research Track)

Randomization, as a key technique in clinical trials, can eliminate sources of bias and produce comparable treatment groups. In randomized experiments, the treatment effect is a parameter of general interest. Researchers have explored the validity of using linear models to estimate the treatment effect and perform covariate adjustment and thus improve the estimation efficiency. However, the relationship between covariates and outcomes is not necessarily linear, and is often intricate. Advances in statistical theory and related computer technology allow us to use nonparametric and machine learning methods to better estimate the relationship between covariates and outcomes and thus obtain further efficiency gains. However, theoretical studies on how to draw valid inferences when using nonparametric and machine learning methods under stratified randomization are yet to be conducted. In this paper, we discuss a unified framework for covariate adjustment and corresponding statistical inference under stratified randomization and present a detailed proof of the validity of using local linear kernel-weighted least squares regression for covariate adjustment in treatment effect estimators as a special case. In the case of high-dimensional data, we additionally propose an algorithm for statistical inference using machine learning methods under stratified randomization, which makes use of sample splitting to alleviate the requirements on the asymptotic properties of machine learning methods. Finally, we compare the performances of treatment effect estimators using different machine learning methods by considering various data generation scenarios, to guide practical research.