Youngjin Kim

Eunbi Choi, Kibong Choi, Seokhee Hong et al.

This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications.

Kartikeya Singh, Youngjin Kim, Yash Turkar et al.

Animals in nature combine multiple modalities, such as sight and feel, to perceive terrain and develop an understanding of how to walk on uneven terrain in a stable manner. Similarly, legged robots need to develop their ability to stably walk on complex terrains by developing an understanding of the relationship between vision and proprioception. Most current terrain adaptation methods are susceptible to failure on complex, off-road terrain as they rely on prior experience, particularly observations from a vision sensor. This experience-based learning often creates a Visual-Texture Paradox between what has been seen and how it actually feels. In this work, we introduce CART, a high-level controller built on a context-aware terrain adaptation approach that integrates proprioception and exteroception from onboard sensing to achieve a robust understanding of terrain. We evaluate our method on multiple terrains using an ANYmal-C robot on the IsaacSim simulator and a Boston Dynamics SPOT robot for our real-world experiments. To evaluate the learned contextual terrain properties, we adapt vibrational stability on the base of the robot as a metric. We compare CART with various state-of-the-art baselines equipped with multimodal sensing in both simulation and the real world. CART achieves an average success rate improvement of 5% over all baselines in simulation and improves the overall stability up to 45% and 24% in the real world without increasing the time taken by the robot to accomplish locomotion tasks.

Sung Jun Cheon, Jaekyung Cho, Seongho Choi et al.

We introduce A.X K1, a 519B-parameter Mixture-of-Experts (MoE) language model trained from scratch. Our design leverages scaling laws to optimize training configurations and vocabulary size under fixed computational budgets. A.X K1 is pre-trained on a corpus of approximately 10T tokens, curated by a multi-stage data processing pipeline. Designed to bridge the gap between reasoning capability and inference efficiency, A.X K1 supports explicitly controllable reasoning to facilitate scalable deployment across diverse real-world scenarios. We propose a simple yet effective Think-Fusion training recipe, enabling user-controlled switching between thinking and non-thinking modes within a single unified model. Extensive evaluations demonstrate that A.X K1 achieves performance competitive with leading open-source models, while establishing a distinctive advantage in Korean-language benchmarks.

Yash Turkar, Youngjin Kim, Karthik Dantu

Subterranean environments such as culverts present significant challenges to robot vision due to dim lighting and lack of distinctive features. Although onboard illumination can help, it introduces issues such as specular reflections, overexposure, and increased power consumption. We propose NightHawk, a framework that combines active illumination with exposure control to optimize image quality in these settings. NightHawk formulates an online Bayesian optimization problem to determine the best light intensity and exposure-time for a given scene. We propose a novel feature detector-based metric to quantify image utility and use it as the cost function for the optimizer. We built NightHawk as an event-triggered recursive optimization pipeline and deployed it on a legged robot navigating a culvert beneath the Erie Canal. Results from field experiments demonstrate improvements in feature detection and matching by 47-197% enabling more reliable visual estimation in challenging lighting conditions.

Youngjin Kim

The large thermal capacity of buildings enables heating, ventilating, and air-conditioning (HVAC) systems to be exploited as demand response (DR) resources. Optimal DR of HVAC units is challenging, particularly for multi-zone buildings, because this requires detailed physics-based models of zonal temperature variations for HVAC system operation and building thermal conditions. This paper proposes a new strategy for optimal DR of an HVAC system in a multi-zone building, based on supervised learning (SL). Artificial neural networks (ANNs) are trained with data obtained under normal building operating conditions. The ANNs are replicated using piecewise linear equations, which are explicitly integrated into an optimal scheduling problem for price-based DR. The optimization problem is solved for various electricity prices and building thermal conditions. The solutions are further used to train a deep neural network (DNN) to directly determine the optimal DR schedule, referred to here as supervised-learning-aided meta-prediction (SLAMP). Case studies are performed using three different methods: explicit ANN replication (EAR), SLAMP, and physics-based modeling. The case study results verify the effectiveness of the proposed SL-based strategy, in terms of both practical applicability and computational time, while also ensuring the thermal comfort of occupants and cost-effective operation of the HVAC system.

Youngjin Kim, Minjung Kim, Gunhee Kim

We propose an approach to address two issues that commonly occur during training of unsupervised GANs. First, since GANs use only a continuous latent distribution to embed multiple classes or clusters of data, they often do not correctly handle the structural discontinuity between disparate classes in a latent space. Second, discriminators of GANs easily forget about past generated samples by generators, incurring instability during adversarial training. We argue that these two infamous problems of unsupervised GAN training can be largely alleviated by a learnable memory network to which both generators and discriminators can access. Generators can effectively learn representation of training samples to understand underlying cluster distributions of data, which ease the structure discontinuity problem. At the same time, discriminators can better memorize clusters of previously generated samples, which mitigate the forgetting problem. We propose a novel end-to-end GAN model named memoryGAN, which involves a memory network that is unsupervisedly trainable and integrable to many existing GAN models. With evaluations on multiple datasets such as Fashion-MNIST, CelebA, CIFAR10, and Chairs, we show that our model is probabilistically interpretable, and generates realistic image samples of high visual fidelity. The memoryGAN also achieves the state-of-the-art inception scores over unsupervised GAN models on the CIFAR10 dataset, without any optimization tricks and weaker divergences.

Yunseok Jang, Yale Song, Youngjae Yu et al.

Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been one of the most successful ones, where the goal is to learn a model that understands visual content at region-level details and finds their associations with pairs of questions and answers in the natural language form. Despite the rapid progress in the past few years, most existing work in VQA have focused primarily on images. In this paper, we focus on extending VQA to the video domain and contribute to the literature in three important ways. First, we propose three new tasks designed specifically for video VQA, which require spatio-temporal reasoning from videos to answer questions correctly. Next, we introduce a new large-scale dataset for video VQA named TGIF-QA that extends existing VQA work with our new tasks. Finally, we propose a dual-LSTM based approach with both spatial and temporal attention, and show its effectiveness over conventional VQA techniques through empirical evaluations.