Dongjun Lee

Dongjun Lee, Seokwon Song, Jihee Suh et al.

In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to downstream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre-trained weights frozen. However, learnable prompts can affect the internal representation within the self-attention module, which may negatively impact performance variance and generalization, especially in data-deficient settings. To address these issues, we propose a novel approach, Read-only Prompt Optimization (RPO). RPO leverages masked attention to prevent the internal representation shift in the pre-trained model. Further, to facilitate the optimization of RPO, the read-only prompts are initialized based on special tokens of the pre-trained model. Our extensive experiments demonstrate that RPO outperforms CLIP and CoCoOp in base-to-new generalization and domain generalization while displaying better robustness. Also, the proposed method achieves better generalization on extremely data-deficient settings, while improving parameter efficiency and computational overhead. Code is available at https://github.com/mlvlab/RPO.

Wonseok Hwang, Dongjun Lee, Kyoungyeon Cho et al.

The recent advances of deep learning have dramatically changed how machine learning, especially in the domain of natural language processing, can be applied to legal domain. However, this shift to the data-driven approaches calls for larger and more diverse datasets, which are nevertheless still small in number, especially in non-English languages. Here we present the first large-scale benchmark of Korean legal AI datasets, LBOX OPEN, that consists of one legal corpus, two classification tasks, two legal judgement prediction (LJP) tasks, and one summarization task. The legal corpus consists of 147k Korean precedents (259M tokens), of which 63k are sentenced in last 4 years and 96k are from the first and the second level courts in which factual issues are reviewed. The two classification tasks are case names (11.3k) and statutes (2.8k) prediction from the factual description of individual cases. The LJP tasks consist of (1) 10.5k criminal examples where the model is asked to predict fine amount, imprisonment with labor, and imprisonment without labor ranges for the given facts, and (2) 4.7k civil examples where the inputs are facts and claim for relief and outputs are the degrees of claim acceptance. The summarization task consists of the Supreme Court precedents and the corresponding summaries (20k). We also release realistic variants of the datasets by extending the domain (1) to infrequent case categories in case name (31k examples) and statute (17.7k) classification tasks, and (2) to long input sequences in the summarization task (51k). Finally, we release LCUBE, the first Korean legal language model trained on the legal corpus from this study. Given the uniqueness of the Law of South Korea and the diversity of the legal tasks covered in this work, we believe that LBOX OPEN contributes to the multilinguality of global legal research. LBOX OPEN and LCUBE will be publicly available.

Dongjun Lee, Ga-eun Bae, Insu Yun

Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag (CTF) benchmarks. However, current CTF benchmarks reuse existing challenges, which exposes them to data contamination and potential cheating. Notably, we confirmed these issues in practice by integrating web search tools into an existing agent. To address these limitations, we present CTFusion, a streaming evaluation framework built on Live CTFs. To achieve this, CTFusion preserves per-agent independence under a single team account and reduces competition impact by forwarding only the first correct flag per challenge. Moreover, we implement CTFusion as a Model Context Protocol (MCP) server on the widely used CTFd platform, which offers broad applicability to diverse CTF events and agent types. Through experiments with three LLMs, two agents, and five Live CTFs, we demonstrate that existing CTF benchmarks can be unreliable in assessing LLM-based agents, while CTFusion can serve as a robust solution for evaluating cybersecurity agents. We release CTFusion as open source to foster future research in this area.

Dongjun Lee, Juyong Lee, Kyuyoung Kim et al.

Recent advances in large language models (LLMs) have led to a growing interest in developing LLM-based agents for automating web tasks. However, these agents often struggle with even simple tasks on real-world websites due to their limited capability to understand and process complex web page structures. In this work, we introduce LCoW, a framework for Learning language models to Contextualize complex Web pages into a more comprehensible form, thereby enhancing decision making by LLM agents. LCoW decouples web page understanding from decision making by training a separate contextualization module to transform complex web pages into comprehensible format, which are then utilized by the decision-making agent. We demonstrate that our contextualization module effectively integrates with LLM agents of various scales to significantly enhance their decision-making capabilities in web automation tasks. Notably, LCoW improves the success rates of closed-source LLMs (e.g., Gemini-1.5-flash, GPT-4o, Claude-3.5-Sonnet) by an average of 15.6%, and demonstrates a 23.7% average improvement in success rates for open-source LMs (e.g., Llama-3.1-8B, Llama-3.1-70B) on the WorkArena benchmark. Moreover, the Gemini-1.5-flash agent with LCoW achieves state-of-the-art results on the WebShop benchmark, outperforming human experts. The relevant code materials are available at our project page: https://lcowiclr2025.github.io.

Byeongchan Lee, Jonghoon Lee, Dongyoung Kim et al.

Recently, large language models (LLMs) have demonstrated strong performance, ranging from simple to complex tasks. However, while large proprietary models (e.g., models with over 100B parameters) achieve remarkable results across diverse tasks, they are often accessible through costly APIs, making frequent use too costly for many applications. In contrast, small open-source models (e.g., models with fewer than 3B parameters) are freely available and easy to deploy locally, but their performance on complex tasks remains limited. This trade-off raises a natural question: how can small and large models efficiently collaborate to combine their complementary strengths? To bridge this trade-off, we propose COPE, a test-time collaboration framework. A planner model first generates a plan, a high-level abstraction of the task, and this plan serves as a lightweight intermediate that guides a downstream executor model. Small and large models take turns acting as planner and executor, exchanging plans in a multi-stage cascade to collaboratively solve tasks. Through comprehensive experiments on benchmarks spanning mathematical reasoning, code generation, open-ended tasks, and agent tasks, we demonstrate that COPE achieves performance comparable to large proprietary models, while drastically reducing the inference API cost. These results highlight planning as an effective prior for cost-efficient inference.

HyunGi Kim, Jisoo Mok, Dongjun Lee et al.

Utilizing the complex inter-variable causal relationships within multivariate time-series provides a promising avenue toward more robust and reliable multivariate time-series anomaly detection (MTSAD) but remains an underexplored area of research. This paper proposes Causality-Aware contrastive learning for RObust multivariate Time-Series (CAROTS), a novel MTSAD pipeline that incorporates the notion of causality into contrastive learning. CAROTS employs two data augmentors to obtain causality-preserving and -disturbing samples that serve as a wide range of normal variations and synthetic anomalies, respectively. With causality-preserving and -disturbing samples as positives and negatives, CAROTS performs contrastive learning to train an encoder whose latent space separates normal and abnormal samples based on causality. Moreover, CAROTS introduces a similarity-filtered one-class contrastive loss that encourages the contrastive learning process to gradually incorporate more semantically diverse samples with common causal relationships. Extensive experiments on five real-world and two synthetic datasets validate that the integration of causal relationships endows CAROTS with improved MTSAD capabilities. The code is available at https://github.com/kimanki/CAROTS.

Sungjoon Park, Jihyung Moon, Sungdong Kim et al.

We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Named Entity Recognition, Relation Extraction, Dependency Parsing, Machine Reading Comprehension, and Dialogue State Tracking. We build all of the tasks from scratch from diverse source corpora while respecting copyrights, to ensure accessibility for anyone without any restrictions. With ethical considerations in mind, we carefully design annotation protocols. Along with the benchmark tasks and data, we provide suitable evaluation metrics and fine-tuning recipes for pretrained language models for each task. We furthermore release the pretrained language models (PLM), KLUE-BERT and KLUE-RoBERTa, to help reproducing baseline models on KLUE and thereby facilitate future research. We make a few interesting observations from the preliminary experiments using the proposed KLUE benchmark suite, already demonstrating the usefulness of this new benchmark suite. First, we find KLUE-RoBERTa-large outperforms other baselines, including multilingual PLMs and existing open-source Korean PLMs. Second, we see minimal degradation in performance even when we replace personally identifiable information from the pretraining corpus, suggesting that privacy and NLU capability are not at odds with each other. Lastly, we find that using BPE tokenization in combination with morpheme-level pre-tokenization is effective in tasks involving morpheme-level tagging, detection and generation. In addition to accelerating Korean NLP research, our comprehensive documentation on creating KLUE will facilitate creating similar resources for other languages in the future. KLUE is available at https://klue-benchmark.com.

Dongjun Lee, Choongwon Park, Jaehyuk Kim et al.

Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human experts on benchmarks that include complex schemas and queries, such as BIRD. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. Specifically, we robustly refine the database schema through schema linking using multiple prompts. Thereafter, we generate various candidate SQL queries based on the refined schema and diverse prompts. Finally, the candidate queries are filtered based on their confidence scores, and the optimal query is obtained through a multiple-choice selection that is presented to the LLM. When evaluated on the BIRD and Spider benchmarks, the proposed method achieved execution accuracies of 65.5\% and 89.6\%, respectively, significantly outperforming previous ICL-based methods. Moreover, we established a new SOTA performance on the BIRD in terms of both the accuracy and efficiency of the generated queries.

Suchae Jeong, Jaehwi Song, Haeone Lee et al.

Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across different viewpoints. In this work, we introduce Cross-View Relations (XVR), a large-scale dataset designed to teach VLMs spatial reasoning across multiple views. XVR comprises 100K vision-question-answer samples derived from 18K diverse 3D scenes and 70K robotic manipulation trajectories, spanning three fundamental spatial reasoning tasks: Correspondence (matching objects across views), Verification (validating spatial relationships), and Localization (identifying object positions). VLMs fine-tuned on XVR achieve substantial improvements on established multi-view and robotic spatial reasoning benchmarks (MindCube and RoboSpatial). When integrated as backbones in Vision-Language-Action models, XVR-trained representations improve success rates on RoboCasa. Our results demonstrate that explicit training on cross-view spatial relations significantly enhances multi-view reasoning and transfers effectively to real-world robotic manipulation.

Jongseon Kim, Hyungjoon Kim, HyunGi Kim et al.

Time series forecasting is a critical task that provides key information for decision-making. After traditional statistical and machine learning approaches, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series forecasting. However, recent research has shown that alternatives such as simple linear layers can outperform Transformers. These findings have opened up new possibilities for using diverse architectures, ranging from fundamental deep learning models to emerging architectures and hybrid approaches. In this context, architectural modeling of time series forecasting has now entered a renaissance. This survey not only provides a historical context for time series forecasting but also offers comprehensive and timely analysis of the movement toward architectural diversification. By comparing and re-examining deep learning models, we uncover new perspectives and present recent trends, including hybrid, diffusion, Mamba, and foundation models. By focusing on the inherent characteristics of time series data, we also address open challenges that have gained attention in time series forecasting, such as channel dependency, distribution shift, causality, and feature extraction. These contributions help lower entry barriers for newcomers by providing a systematic understanding of the diverse research areas in time series forecasting (TSF), while offering seasoned researchers broader perspectives and new opportunities through in-depth exploration of TSF challenges. (Shortened due to arXiv's 1,920-character limit. Full version in the paper.)

Bong Gyun Kang, Dongjun Lee, HyunGi Kim et al.

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture long-range dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results.

Dongjun Lee, Changho Hwang, Kimin Lee

Unit testing is a core practice in programming, enabling systematic evaluation of programs produced by human developers or large language models (LLMs). Given the challenges in writing comprehensive unit tests, LLMs have been employed to automate test generation, yet methods for training LLMs to produce high-quality tests remain underexplored. In this work, we propose UTRL, a novel reinforcement learning framework that trains an LLM to generate high-quality unit tests given a programming instruction. Our key idea is to iteratively train two LLMs, the unit test generator and the code generator, in an adversarial manner via reinforcement learning. The unit test generator is trained to maximize a discrimination reward, which reflects its ability to produce tests that expose faults in the code generator's solutions, and the code generator is trained to maximize a code reward, which reflects its ability to produce solutions that pass the unit tests generated by the test generator. In our experiments, we demonstrate that unit tests generated by Qwen3-4B trained via UTRL show higher quality compared to unit tests generated by the same model trained via supervised fine-tuning on human-written ground-truth unit tests, yielding code evaluations that more closely align with those induced by the ground-truth tests. Moreover, Qwen3-4B trained with UTRL outperforms frontier models such as GPT-4.1 in generating high-quality unit tests, highlighting the effectiveness of UTRL in training LLMs for this task.

Yongjin Yang, Sinjae Kang, Juyong Lee et al.

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill acquisition faces several challenges. Manual trajectory collection requires significant human effort. Another approach, where LLMs directly propose tasks to learn, is often invalid, as the LLMs lack knowledge of which tasks are actually feasible. Moreover, the generated data may not provide a meaningful learning signal, as agents often already perform well on the proposed tasks. To address this, we propose a novel automatic skill discovery framework EXIF for LLM-powered agents, designed to improve the feasibility of generated target behaviors while accounting for the agents' capabilities. Our method adopts an exploration-first strategy by employing an exploration agent (Alice) to train the target agent (Bob) to learn essential skills in the environment. Specifically, Alice first interacts with the environment to retrospectively generate a feasible, environment-grounded skill dataset, which is then used to train Bob. Crucially, we incorporate an iterative feedback loop, where Alice evaluates Bob's performance to identify areas for improvement. This feedback then guides Alice's next round of exploration, forming a closed-loop data generation process. Experiments on Webshop and Crafter demonstrate EXIF's ability to effectively discover meaningful skills and iteratively expand the capabilities of the trained agent without any human intervention, achieving substantial performance improvements. Interestingly, we observe that setting Alice to the same model as Bob also notably improves performance, demonstrating EXIF's potential for building a self-evolving system.

Juhyeon Shin, Jonghyun Lee, Saehyung Lee et al.

In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label. We developed a gradient alignment loss to precisely manage the adaptation process, ensuring that changes made for some data don't negatively impact the model's performance on other data. We introduce a prototype feature of a class as a proxy measure of the negative impact. To make GAP regularizer feasible under the TTA constraints, where model can only access test data without labels, we tailored its formula in two ways: approximating prototype features with weight vectors of the classifier, calculating gradient without back-propagation. We demonstrate GAP significantly improves TTA methods across various datasets, which proves its versatility and effectiveness.

Donggeun Ko, Dongjun Lee, Namjun Park et al.

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative Adversarial Networks (GANs) to mitigate biases. We introduce DiffuBias, a novel pipeline for text-to-image generation that enhances classifier robustness by generating bias-conflict samples, without requiring training during the generation phase. Utilizing pretrained diffusion and image captioning models, DiffuBias generates images that challenge the biases of classifiers, using the top-$K$ losses from a biased classifier ($f_B$) to create more representative data samples. This method not only debiases effectively but also boosts classifier generalization capabilities. To the best of our knowledge, DiffuBias is the first approach leveraging a stable diffusion model to generate bias-conflict samples in debiasing tasks. Our comprehensive experimental evaluations demonstrate that DiffuBias achieves state-of-the-art performance on benchmark datasets. We also conduct a comparative analysis of various generative models in terms of carbon emissions and energy consumption to highlight the significance of computational efficiency.

Donggeun Ko, Sangwoo Jo, Dongjun Lee et al.

Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous efforts have focused on debiasing models either by developing novel debiasing algorithms or by generating synthetic data to mitigate the prevalent dataset biases. However, generative approaches to date have largely relied on using bias-specific samples from the dataset, which are typically too scarce. In this work, we propose, DiffInject, a straightforward yet powerful method to augment synthetic bias-conflict samples using a pretrained diffusion model. This approach significantly advances the use of diffusion models for debiasing purposes by manipulating the latent space. Our framework does not require any explicit knowledge of the bias types or labelling, making it a fully unsupervised setting for debiasing. Our methodology demonstrates substantial result in effectively reducing dataset bias.

Jaemin Yoon, Minji Lee, Dongwon Son et al.

We propose a novel fast and accurate simulation framework for contact-intensive tight-tolerance robotic assembly tasks. The key components of our framework are as follows: 1) data-driven contact point clustering with a certain variable-input network, which is explicitly trained for simulation accuracy (with real experimental data) and able to accommodate complex/non-convex object shapes; 2) contact force solving, which precisely/robustly enforces physics of contact (i.e., no penetration, Coulomb friction, maximum energy dissipation) with contact mechanics of contact nodes augmented with that of their object; 3) contact detection with a neural network, which is parallelized for each contact point, thus, can be computed very quickly even for complex shape objects with no exhaust pair-wise test; and 4) time integration with PMI (passive mid-point integration), whose discrete-time passivity improves overall simulation accuracy, stability, and speed. We then implement our proposed framework for two widely-encountered/benchmarked contact-intensive tight-tolerance tasks, namely, peg-in-hole assembly and bolt-nut assembly, and validate its speed and accuracy against real experimental data. It is worthwhile to mention that our proposed simulation framework is applicable to other general contact-intensive tight-tolerance robotic assembly tasks as well. We also compare its performance with other physics engines and manifest its robustness via haptic rendering of virtual bolting task.

Jeongmin Lee, Minji Lee, Dongjun Lee

We propose a novel multibody dynamics simulation framework that can efficiently deal with large-dimensionality and complementarity multi-contact conditions. Typical contact simulation approaches perform contact impulse-level fixed-point iteration (IL-FPI), which has high time-complexity from large-size matrix inversion and multiplication, as well as susceptibility to ill-conditioned contact situations. To circumvent this, we propose a novel framework based on velocity-level fixed-point iteration (VL-FPI), which, by utilizing a certain surrogate dynamics and contact nodalization (with virtual nodes), can achieve not only inter-contact decoupling but also their inter-axes decoupling (i.e., contact diagonalization). This then enables us to one-shot/parallel-solve the contact problem during each VL-FPI iteration-loop, while the surrogate dynamics structure allows us to circumvent large-size/dense matrix inversion/multiplication, thereby, significantly speeding up the simulation time with improved convergence property. We theoretically show that the solution of our framework is consistent with that of the original problem and, further, elucidate mathematical conditions for the convergence of our proposed solver. Performance and properties of our proposed simulation framework are also demonstrated and experimentally-validated for various large-dimensional/multi-contact scenarios including deformable objects.

Yunho Kim, Bukun Son, Dongjun Lee

There is a growing interest in learning a velocity command tracking controller of quadruped robot using reinforcement learning due to its robustness and scalability. However, a single policy, trained end-to-end, usually shows a single gait regardless of the command velocity. This could be a suboptimal solution considering the existence of optimal gait according to the velocity for quadruped animals. In this work, we propose a hierarchical controller for quadruped robot that could generate multiple gaits (i.e. pace, trot, bound) while tracking velocity command. Our controller is composed of two policies, each working as a central pattern generator and local feedback controller, and trained with hierarchical reinforcement learning. Experiment results show 1) the existence of optimal gait for specific velocity range 2) the efficiency of our hierarchical controller compared to a controller composed of a single policy, which usually shows a single gait. Codes are publicly available.

Hiun Kim, Jisu Jeong, Kyung-Min Kim et al.

Building a shopping product collection has been primarily a human job. With the manual efforts of craftsmanship, experts collect related but diverse products with common shopping intent that are effective when displayed together, e.g., backpacks, laptop bags, and messenger bags for freshman bag gifts. Automatically constructing a collection requires an ML system to learn a complex relationship between the customer's intent and the product's attributes. However, there have been challenging points, such as 1) long and complicated intent sentences, 2) rich and diverse product attributes, and 3) a huge semantic gap between them, making the problem difficult. In this paper, we use a pretrained language model (PLM) that leverages textual attributes of web-scale products to make intent-based product collections. Specifically, we train a BERT with triplet loss by setting an intent sentence to an anchor and corresponding products to positive examples. Also, we improve the performance of the model by search-based negative sampling and category-wise positive pair augmentation. Our model significantly outperforms the search-based baseline model for intent-based product matching in offline evaluations. Furthermore, online experimental results on our e-commerce platform show that the PLM-based method can construct collections of products with increased CTR, CVR, and order-diversity compared to expert-crafted collections.

Dongjun Lee, Junhyeong Ahn, Heesoo Park et al.

We present IntelliCAT, an interactive translation interface with neural models that streamline the post-editing process on machine translation output. We leverage two quality estimation (QE) models at different granularities: sentence-level QE, to predict the quality of each machine-translated sentence, and word-level QE, to locate the parts of the machine-translated sentence that need correction. Additionally, we introduce a novel translation suggestion model conditioned on both the left and right contexts, providing alternatives for specific words or phrases for correction. Finally, with word alignments, IntelliCAT automatically preserves the original document's styles in the translated document. The experimental results show that post-editing based on the proposed QE and translation suggestions can significantly improve translation quality. Furthermore, a user study reveals that three features provided in IntelliCAT significantly accelerate the post-editing task, achieving a 52.9\% speedup in translation time compared to translating from scratch. The interface is publicly available at https://intellicat.beringlab.com/.

Dongjun Lee, Jaesik Yoon, Jongyun Song et al.

Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries. Recently, template-based and sequence-to-sequence approaches were proposed to support complex queries, which contain join queries, nested queries, and other types. However, Finegan-Dollak et al. (2018) demonstrated that both the approaches lack the ability to generate SQL of unseen templates. In this paper, we propose a template-based one-shot learning model for the text-to-SQL generation so that the model can generate SQL of an untrained template based on a single example. First, we classify the SQL template using the Matching Network that is augmented by our novel architecture Candidate Search Network. Then, we fill the variable slots in the predicted template using the Pointer Network. We show that our model outperforms state-of-the-art approaches for various text-to-SQL datasets in two aspects: 1) the SQL generation accuracy for the trained templates, and 2) the adaptability to the unseen SQL templates based on a single example without any additional training.

Dongjun Lee

Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries over a single table. We focus on the Spider dataset, a complex and cross-domain text-to-SQL task, which includes complex queries over multiple tables. In this paper, we propose a SQL clause-wise decoding neural architecture with a self-attention based database schema encoder to address the Spider task. Each of the clause-specific decoders consists of a set of sub-modules, which is defined by the syntax of each clause. Additionally, our model works recursively to support nested queries. When evaluated on the Spider dataset, our approach achieves 4.6\% and 9.8\% accuracy gain in the test and dev sets, respectively. In addition, we show that our model is significantly more effective at predicting complex and nested queries than previous work.

Jinwoong Kim, Minkyu Kim, Heungseok Park et al.

Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance. Here we propose a novel cloud-based HyperOpt (CHOPT) framework which can efficiently utilize shared computing resources while supporting various HyperOpt algorithms. We incorporate convenient web-based user interfaces, visualization, and analysis tools, enabling users to easily control optimization procedures and build up valuable insights with an iterative analysis procedure. Furthermore, our framework can be incorporated with any cloud platform, thus complementarily increasing the efficiency of conventional deep learning frameworks. We demonstrate applications of CHOPT with tasks such as image recognition and question-answering, showing that our framework can find hyperparameter configurations competitive with previous work. We also show CHOPT is capable of providing interesting observations through its analysing tools