Kexin Chen

Haomin Qi, Yuyang Du, Lihao Zhang et al.

Large language models (LLMs) have demonstrated immense potential in computer-aided design (CAD), particularly for automated debugging and verification within electronic design automation (EDA) tools. However, Design for Testability (DFT) remains a relatively underexplored area. This paper presents VeriRAG, the first LLM-assisted DFT-EDA framework. VeriRAG leverages a Retrieval-Augmented Generation (RAG) approach to enable LLM to revise code to ensure DFT compliance. VeriRAG integrates (1) an autoencoder-based similarity measurement model for precise retrieval of reference RTL designs for the LLM, and (2) an iterative code revision pipeline that allows the LLM to ensure DFT compliance while maintaining synthesizability. To support VeriRAG, we introduce VeriDFT, a Verilog-based DFT dataset curated for DFT-aware RTL repairs. VeriRAG retrieves structurally similar RTL designs from VeriDFT, each paired with a rigorously validated correction, as references for code repair. With VeriRAG and VeriDFT, we achieve fully automated DFT correction -- resulting in a 7.72-fold improvement in successful repair rate compared to the zero-shot baseline (Fig. 5 in Section V). Ablation studies further confirm the contribution of each component of the VeriRAG framework. We open-source our data, models, and scripts at https://github.com/HarminChee/VeriRAG.

Kexin Chen, Guangyong Chen, Junyou Li et al.

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield prediction problem, which assists chemists in selecting high-yield reactions in a new chemical space only with a few experimental trials. To attack this challenge, we first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction, where the attention weight of a random forest is automatically optimized by the meta-learning framework and can be quickly adapted to predict the performance of new reagents while given a few additional samples. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method to determine valuable samples to be experimentally tested and then learned. Our methodology is evaluated on three different datasets and acquires satisfactory performance on few-shot prediction. In high-throughput experimentation (HTE) datasets, the average yield of our methodology's top 10 high-yield reactions is relatively close to the results of ideal yield selection.

Zihao Ye, Yung Hsiang Lu, Xiao Hu et al.

The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.

Liujianfu Wang, Yuyang Du, Jingqi Lin et al.

Large language models (LLMs) are being widely researched across various disciplines, with significant recent efforts focusing on adapting LLMs for understanding of how communication networks operate. However, over-reliance on prompting techniques hinders the full exploitation of the generalization ability of these models, and the lack of efficient fine-tuning methods prevents the full realization of lightweight LLMs' potential. This paper addresses these challenges by introducing our Rephrase and Contrast (RaC) framework, an efficient fine-tuning framework. RaC enhances LLMs' comprehension and critical thinking abilities by incorporating question reformulation and contrastive analysis of correct and incorrect answers during the fine-tuning process. Experimental results demonstrate a 63.73% accuracy improvement over the foundational model when tested on a comprehensive networking problem set. Moreover, to efficiently construct the dataset for RaC fine-tuning, we develop a GPT-assisted data mining method for generating high-quality question-answer (QA) pairs; furthermore, we introduce ChoiceBoost, a data augmentation technique that expands dataset size while reducing answer-order bias. Apart from these technical innovations, we contribute to the networking community by open-sourcing valuable research resources, including: 1) the fine-tuned networking model referred to as RaC-Net, 2) the training dataset used for fine-tuning the model, 3) three testing problem sets of different difficulties to serve as benchmarks for future research, and 4) code associated with the above resources.

Kexin Chen, Jiamin Lu, Junyou Li et al.

Recent AI research plots a promising future of automatic chemical reactions within the chemistry society. This study proposes Chemist-X, a comprehensive AI agent that automates the reaction condition optimization (RCO) task in chemical synthesis with retrieval-augmented generation (RAG) technology and AI-controlled wet-lab experiment executions. To begin with, as an emulation on how chemical experts solve the RCO task, Chemist-X utilizes a novel RAG scheme to interrogate available molecular and literature databases to narrow the searching space for later processing. The agent then leverages a computer-aided design (CAD) tool we have developed through a large language model (LLM) supervised programming interface. With updated chemical knowledge obtained via RAG, as well as the ability in using CAD tools, our agent significantly outperforms conventional RCO AIs confined to the fixed knowledge within its training data. Finally, Chemist-X interacts with the physical world through an automated robotic system, which can validate the suggested chemical reaction condition without human interventions. The control of the robotic system was achieved with a novel algorithm we have developed for the equipment, which relies on LLMs for reliable script generation. Results of our automatic wet-lab experiments, achieved by fully LLM-supervised end-to-end operation with no human in the lope, prove Chemist-X's ability in self-driving laboratories.

Kexin Chen, Yi Liu, Dongxia Wang et al.

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include implementing safeguards to ensure LLMs adhere to social ethics.However, despite such measures, the phenomenon of "jailbreaking" -- where carefully crafted prompts elicit harmful responses from models -- persists as a significant challenge. Recognizing the continuous threat posed by jailbreaking tactics and their repercussions for the trustworthy use of LLMs, a rigorous assessment of the models' robustness against such attacks is essential. This study introduces an comprehensive evaluation framework and conducts an large-scale empirical experiment to address this need. We concentrate on 10 cutting-edge jailbreak strategies across three categories, 1525 questions from 61 specific harmful categories, and 13 popular LLMs. We adopt multi-dimensional metrics such as Attack Success Rate (ASR), Toxicity Score, Fluency, Token Length, and Grammatical Errors to thoroughly assess the LLMs' outputs under jailbreak. By normalizing and aggregating these metrics, we present a detailed reliability score for different LLMs, coupled with strategic recommendations to reduce their susceptibility to such vulnerabilities. Additionally, we explore the relationships among the models, attack strategies, and types of harmful content, as well as the correlations between the evaluation metrics, which proves the validity of our multifaceted evaluation framework. Our extensive experimental results demonstrate a lack of resilience among all tested LLMs against certain strategies, and highlight the need to concentrate on the reliability facets of LLMs. We believe our study can provide valuable insights into enhancing the security evaluation of LLMs against jailbreak within the domain.

Kexin Chen, Yuyang Du, Junyou Li et al.

The development of AI-assisted chemical synthesis tools requires comprehensive datasets covering diverse reaction types, yet current high-throughput experimental (HTE) approaches are expensive and limited in scope. Chemical literature represents a vast, underexplored data source containing thousands of reactions published annually. However, extracting reaction information from literature faces significant challenges including varied writing styles, complex coreference relationships, and multimodal information presentation. This paper proposes ChemMiner, a novel end-to-end framework leveraging multiple agents powered by large language models (LLMs) to extract high-fidelity chemical data from literature. ChemMiner incorporates three specialized agents: a text analysis agent for coreference mapping, a multimodal agent for non-textual information extraction, and a synthesis analysis agent for data generation. Furthermore, we developed a comprehensive benchmark with expert-annotated chemical literature to evaluate both extraction efficiency and precision. Experimental results demonstrate reaction identification rates comparable to human chemists while significantly reducing processing time, with high accuracy, recall, and F1 scores. Our open-sourced benchmark facilitates future research in chemical literature data mining.

Haonan Zhang, Dongxia Wang, Yi Liu et al.

Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental trade-off -- reducing jailbreak increases over-refusal and vice versa. We identify the root cause: LLMs encode the decision to answer (answer vector $v_a$) and the judgment of input safety (benign vector $v_b$) as nearly orthogonal directions, treating them as independent processes. We propose LLM-VA, which aligns $v_a$ with $v_b$ through closed-form weight updates, making the model's willingness to answer causally dependent on its safety assessment -- without fine-tuning or architectural changes. Our method identifies vectors at each layer using SVMs, selects safety-relevant layers, and iteratively aligns vectors via minimum-norm weight modifications. Experiments on 12 LLMs demonstrate that LLM-VA achieves 11.45% higher F1 than the best baseline while preserving 95.92% utility, and automatically adapts to each model's safety bias without manual tuning. Code and models are available at https://hotbento.github.io/LLM-VA-Web/.

Ruiyang Ma, Yunhao Zhou, Yipeng Wang et al.

There is a growing body of work on using Graph Neural Networks (GNNs) to learn representations of circuits, focusing primarily on their static characteristics. However, these models fail to capture circuit runtime behavior, which is crucial for tasks like circuit verification and optimization. To address this limitation, we introduce DR-GNN (DynamicRTL-GNN), a novel approach that learns RTL circuit representations by incorporating both static structures and multi-cycle execution behaviors. DR-GNN leverages an operator-level Control Data Flow Graph (CDFG) to represent Register Transfer Level (RTL) circuits, enabling the model to capture dynamic dependencies and runtime execution. To train and evaluate DR-GNN, we build the first comprehensive dynamic circuit dataset, comprising over 6,300 Verilog designs and 63,000 simulation traces. Our results demonstrate that DR-GNN outperforms existing models in branch hit prediction and toggle rate prediction. Furthermore, its learned representations transfer effectively to related dynamic circuit tasks, achieving strong performance in power estimation and assertion prediction.

Haoran Yang, Yinan Zhang, Wenjie Zhang et al.

Nowadays, industrial hybrid modeling which integrates both mechanistic modeling and machine learning-based modeling techniques has attracted increasing interest from scholars due to its high accuracy, low computational cost, and satisfactory interpretability. Nevertheless, the existing industrial hybrid modeling methods still face two main limitations. First, current research has mainly focused on applying a single machine learning method to one specific task, failing to develop a comprehensive machine learning architecture suitable for modeling tasks, which limits their ability to effectively represent complex industrial scenarios. Second, industrial datasets often contain underlying associations (e.g., monotonicity or periodicity) that are not adequately exploited by current research, which can degrade model's predictive performance. To address these limitations, this paper proposes the Recurrent Perceptron-based Channel Attention Transformer Encoder (RP-CATE), with three distinctive characteristics: 1: We developed a novel architecture by replacing the self-attention mechanism with channel attention and incorporating our proposed Recurrent Perceptron (RP) Module into Transformer, achieving enhanced effectiveness for industrial modeling tasks compared to the original Transformer. 2: We proposed a new data type called Pseudo-Image Data (PID) tailored for channel attention requirements and developed a cyclic sliding window method for generating PID. 3: We introduced the concept of Pseudo-Sequential Data (PSD) and a method for converting industrial datasets into PSD, which enables the RP Module to capture the underlying associations within industrial dataset more effectively. An experiment aimed at hybrid modeling in chemical engineering was conducted by using RP-CATE and the experimental results demonstrate that RP-CATE achieves the best performance compared to other baseline models.

Ziyu Guo, Renrui Zhang, Xiangyang Zhu et al.

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

Ruichen Xu, Kexin Chen

Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness. The theoretical underpinnings of these phenomena in modern, non-convex neural networks remain largely unexplored. This paper introduces a unified feature-centric framework to analyze the feature learning dynamics of differentially private stochastic gradient descent (DP-SGD) in two-layer ReLU convolutional neural networks. Our analysis establishes test loss bounds governed by a crucial metric: the feature-to-noise ratio (FNR). We demonstrate that the noise required for privacy leads to suboptimal feature learning, and specifically show that: 1) imbalanced FNRs across classes and subpopulations cause disparate impact; 2) even in the same class, noise has a greater negative impact on semantically long-tailed data; and 3) noise injection exacerbates vulnerability to adversarial attacks. Furthermore, our analysis reveals that the popular paradigm of public pre-training and private fine-tuning does not guarantee improvement, particularly under significant feature distribution shifts between datasets. Experiments on synthetic and real-world data corroborate our theoretical findings.

Kexin Chen, Noelle Lim, Claire Lee et al.

We propose a pipeline for gaining insights into complex diseases by training LLMs on challenging social media text data classification tasks, obtaining explanations for the classification outputs, and performing qualitative and quantitative analysis on the explanations. We report initial results on predicting, explaining, and systematizing the explanations of predicted reports on mental health concerns in people reporting Lyme disease concerns. We report initial results on predicting future ADHD concerns for people reporting anxiety disorder concerns, and demonstrate preliminary results on visualizing the explanations for predicting that a person with anxiety concerns will in the future have ADHD concerns.

Xilin Dang, Kexin Chen, Xiaorui Su et al.

In clinical practice, physicians refrain from making decisions when patient information is insufficient. This behavior, known as abstention, is a critical safety mechanism preventing potentially harmful misdiagnoses. Recent investigations have reported the application of large language models (LLMs) in medical scenarios. However, existing LLMs struggle with the abstentions, frequently providing overconfident responses despite incomplete information. This limitation stems from conventional abstention methods relying solely on model self-assessments, which lack systematic strategies to identify knowledge boundaries with external medical evidences. To address this, we propose \textbf{KnowGuard}, a novel \textit{investigate-before-abstain} paradigm that integrates systematic knowledge graph exploration for clinical decision-making. Our approach consists of two key stages operating on a shared contextualized evidence pool: 1) an evidence discovery stage that systematically explores the medical knowledge space through graph expansion and direct retrieval, and 2) an evidence evaluation stage that ranks evidence using multiple factors to adapt exploration based on patient context and conversation history. This two-stage approach enables systematic knowledge graph exploration, allowing models to trace structured reasoning paths and recognize insufficient medical evidence. We evaluate our abstention approach using open-ended multi-round clinical benchmarks that mimic realistic diagnostic scenarios, assessing abstention quality through accuracy-efficiency trade-offs beyond existing closed-form evaluations. Experimental evidences clearly demonstrate that KnowGuard outperforms state-of-the-art abstention approaches, improving diagnostic accuracy by 3.93\% while reducing unnecessary interaction by 7.27 turns on average.

Haonan Zhang, Dongxia Wang, Yi Liu et al.

Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that undermines their reliability and usability. Current methods for testing this behavior are demonstrably inadequate, suffering from flawed benchmarks and limited test generation capabilities, as highlighted by our empirical user study. To the best of our knowledge, this paper introduces the first evolutionary testing framework, ORFuzz, for the systematic detection and analysis of LLM over-refusals. ORFuzz uniquely integrates three core components: (1) safety category-aware seed selection for comprehensive test coverage, (2) adaptive mutator optimization using reasoning LLMs to generate effective test cases, and (3) OR-Judge, a human-aligned judge model validated to accurately reflect user perception of toxicity and refusal. Our extensive evaluations demonstrate that ORFuzz generates diverse, validated over-refusal instances at a rate (6.98% average) more than double that of leading baselines, effectively uncovering vulnerabilities. Furthermore, ORFuzz's outputs form the basis of ORFuzzSet, a new benchmark of 1,855 highly transferable test cases that achieves a superior 63.56% average over-refusal rate across 10 diverse LLMs, significantly outperforming existing datasets. ORFuzz and ORFuzzSet provide a robust automated testing framework and a valuable community resource, paving the way for developing more reliable and trustworthy LLM-based software systems.

Ruichen Xu, Kexin Chen

Modern large language models excel in knowledge-intensive tasks, yet how transformers acquire (store) knowledge during pre-training and extract (retrieve) it during post-fine-tuning inference remains theoretically opaque. While prior theoretical work has begun to investigate these questions through the analysis of training dynamics, such studies are limited to single-layer, attention-only architectures. However, most existing studies suggest that MLPs are the most contributing components for storing knowledge in transformer-based language models. Meanwhile, our empirical investigations reveal that such simplified models, when trained using standard next-token prediction objectives, may be incapable of acquiring or extracting factual knowledge. To overcome this limitation, we introduce a tractable one-layer transformer framework that crucially incorporates both self-attention and MLP modules. By tracking its gradient dynamics, we establish convergence and generalization guarantees that illuminate the ability of knowledge acquisition and extraction. We prove that 1) Transformers can achieve near-optimal training loss during pre-training, signifying effective knowledge acquisition; 2) With a large fine-tuning dataset and specific data multiplicity conditions met, transformers can achieve low generalization error when tested on factual knowledge learned during pre-training but not reinforced during the fine-tuning, indicating successful knowledge extraction; 3) When the conditions are not satisfied, transformers exhibit high generalization loss, resulting in hallucinations. Our analysis includes both full fine-tuning and low-rank fine-tuning. Furthermore, our analysis offers theoretical insights into several pertinent empirical phenomena, such as the role of learning rate schedules. Experiments on synthetic and real-world PopQA datasets with GPT-2 and Llama-3.2-1B validate our results.

Kexin Chen, Dongxia Wang, Yi Liu et al.

Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance. In this paper, we systematically investigate such anomalous tokens, formally defining them and introducing an efficient detection method, Sticky Token Detector (STD), based on sentence and token filtering. Applying STD to 40 checkpoints across 14 model families, we discover a total of 868 sticky tokens. Our analysis reveals that these tokens often originate from special or unused entries in the vocabulary, as well as fragmented subwords from multilingual corpora. Notably, their presence does not strictly correlate with model size or vocabulary size. We further evaluate how sticky tokens affect downstream tasks like clustering and retrieval, observing significant performance drops of up to 50%. Through attention-layer analysis, we show that sticky tokens disproportionately dominate the model's internal representations, raising concerns about tokenization robustness. Our findings show the need for better tokenization strategies and model design to mitigate the impact of sticky tokens in future text embedding applications.

Ruichen Xu, Kexin Chen

Recent theoretical studies (Kou et al., 2023; Cao et al., 2022) have revealed a sharp phase transition from benign to harmful overfitting when the noise-to-feature ratio exceeds a threshold-a situation common in long-tailed data distributions where atypical data is prevalent. However, harmful overfitting rarely happens in overparameterized neural networks. Further experimental results suggested that memorization is necessary for achieving near-optimal generalization error in long-tailed data distributions (Feldman & Zhang, 2020). We argue that this discrepancy between theoretical predictions and empirical observations arises because previous feature-noise data models overlook the heterogeneous nature of noise across different data classes. In this paper, we refine the feature-noise data model by incorporating class-dependent heterogeneous noise and re-examine the overfitting phenomenon in neural networks. Through a comprehensive analysis of the training dynamics, we establish test loss bounds for the refined model. Our findings reveal that neural networks can leverage "data noise" to learn implicit features that improve the classification accuracy for long-tailed data. Our analysis also provides a training-free metric for evaluating data influence on test performance. Experimental validation on both synthetic and real-world datasets supports our theoretical results.

Yiyi Zhang, Xingyu Chen, Kexin Chen et al.

Recent years have witnessed extensive efforts to enhance Large Language Models (LLMs) across various domains, alongside growing attention to their ethical implications. However, a critical challenge remains largely overlooked: LLMs must balance between rejecting harmful requests for safety and accommodating legitimate ones for utility. This paper presents a Direct Preference Optimization (DPO) based alignment framework that achieves better overall performance by addressing this ethical-utility trade-off, using chemical domain applications as a proof-of-concept. Our alignment pipeline starts with a GPT-assisted three-phase data generation scheme, in which we create LibraChemQA, a chemical question-answering dataset comprising 31.6k triplet instances. By incorporating an innovative balanced seed in the data generation process, our framework systematically considers both legitimate and illegitimate requests. The framework also introduces a rephrasing mechanism for efficient data augmentation that enhances the model's chemical comprehension. We further develop a novel hybrid evaluation scheme with LLM judges for precise assessment of both safety and utility. Experimental results demonstrate our model's substantial improvements in overall performance where both safety and utility are considered - the resulting model outperforms leading LLMs including Claude-3, GPT-4o, and LLaMA-3 by margins of 13.44%, 7.16%, and 7.10% respectively on our released benchmark. At the end of this paper, we analyze experimental results obtained from testing DeepSeek-R1 on our benchmark and reveal the critical ethical concerns raised by this highly acclaimed model. We highlight that the long Chain-of-Thought (CoT) reasoning process employed by DeepSeek-R1, as well as other LLMs distilled from it, introduces significant ethical vulnerabilities when exposed to users.

Zhong Ji, Kexin Chen, Haoran Wang

Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the fine-grained cross-modal correspondence between image and text. Most previous methods rely on single-step reasoning to discover the visual-semantic interactions, which lacks the ability of exploiting the multi-level information to locate the hierarchical fine-grained relevance. Different from them, in this work, we propose a step-wise hierarchical alignment network (SHAN) that decomposes image-text matching into multi-step cross-modal reasoning process. Specifically, we first achieve local-to-local alignment at fragment level, following by performing global-to-local and global-to-global alignment at context level sequentially. This progressive alignment strategy supplies our model with more complementary and sufficient semantic clues to understand the hierarchical correlations between image and text. The experimental results on two benchmark datasets demonstrate the superiority of our proposed method.

Xinyun Zou, Eric O. Scott, Alexander B. Johnson et al.

Animals ranging from rats to humans can demonstrate cognitive map capabilities. We evolved weights in a biologically plausible recurrent neural network (RNN) using an evolutionary algorithm to replicate the behavior and neural activity observed in rats during a spatial and working memory task in a triple T-maze. The rat was simulated in the Webots robot simulator and used vision, distance and accelerometer sensors to navigate a virtual maze. After evolving weights from sensory inputs to the RNN, within the RNN, and from the RNN to the robot's motors, the Webots agent successfully navigated the space to reach all four reward arms with minimal repeats before time-out. Our current findings suggest that it is the RNN dynamics that are key to performance, and that performance is not dependent on any one sensory type, which suggests that neurons in the RNN are performing mixed selectivity and conjunctive coding. Moreover, the RNN activity resembles spatial information and trajectory-dependent coding observed in the hippocampus. Collectively, the evolved RNN exhibits navigation skills, spatial memory, and working memory. Our method demonstrates how the dynamic activity in evolved RNNs can capture interesting and complex cognitive behavior and may be used to create RNN controllers for robotic applications.

Jinwei Xing, Takashi Nagata, Kexin Chen et al.

Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage. The cross-domain consistency of LUSR allows the policy acquired from the source domain to generalize to other target domains without extra training. We first demonstrate our approach in variants of CarRacing games with customized manipulations, and then verify it in CARLA, an autonomous driving simulator with more complex and realistic visual observations. Our results show that this approach can achieve state-of-the-art domain adaptation performance in related RL tasks and outperforms prior approaches based on latent-representation based RL and image-to-image translation.