Publications

2026

1. 

   A.X K2 Technical Report

   Cheolseung Baek, Eunki Kim, Hyunho Yang, and 40 more authors

   Aug 2026

   Abs HTML PDF Code

   We introduce A.X K2, a 688B-parameter Mixture-of-Experts (MoE) language model trained from scratch as a high-performance foundation for agentic applications. Trained on approximately 8.5T tokens—fewer than its predecessor, A.X K1—on a smaller but higher-quality mixture with substantially expanded agentic and software-engineering data, it nonetheless improves over A.X K1 across the board, by over 30 percentage points on some benchmarks, reflecting large gains in token efficiency. To support long contexts efficiently, we introduce Sparse Gated Attention (SGA), which combines sparse attention with gated attention, and adopt Gated Norm (GN) to stabilize large-scale training. SGA is trained natively at 128K through a sparse indexer warmup that optimizes the indexer against its own sparse top-k selection rather than the dense attention distribution, making adaptation markedly cheaper: each query reads only 2,048 positions, yet long-context quality is unchanged and A.X K2 scores 94.6 on RULER out to 256K. The outlier suppression of GN in turn keeps 4-bit NVFP4 serving within one point of FP8 accuracy. A simple yet effective Think-Fusion recipe further lets users switch between thinking and non-thinking modes within a single unified model.

2. 

   A.X K1 Technical Report

   Sung Jun Cheon, Jaekyung Cho, Seongho Choi, and 57 more authors

   2026

   Abs DOI arXiv HTML PDF Code

   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.

2025

1. 

   TelAgentBench: A Multi-faceted Benchmark for Evaluating LLM-based Agents in Telecommunications

   Sunwoo Lee, Daseong Jang, Dhammiko Arya, and 12 more authors

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, Nov 2025

   Abs DOI PDF

   As Large Language Models (LLMs) evolve into powerful agentic systems, the telecommunications industry’s expansion into AI services necessitates industry-grounded benchmarks to evaluate their underexplored domain-specific capabilities. To address the gap left by generic benchmarks that fail to assess realistic, non-English performance, we present TelAgentBench, a Korean benchmark for the telecommunications domain evaluating five core agentic capabilities: Reasoning, Planning, Action (tool-use), Retrieval-Augmented Generation, and Instruction Following. Evaluations reveal significant performance disparities between models that employ explicit reasoning and those that do not, providing actionable insights for deploying agentic LLMs in real-world telecommunications tasks.

2024

1. 

   TelBench: A Benchmark for Evaluating Telco-Specific Large Language Models

   Sunwoo Lee, Dhammiko Arya, Seung-Mo Cho, and 9 more authors

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, Nov 2024

   Abs DOI PDF

   The telecommunications industry, characterized by its vast customer base and complex service offerings, necessitates a high level of domain expertise and proficiency in customer service center operations. Consequently, there is a growing demand for Large Language Models (LLMs) to augment the capabilities of customer service representatives. This paper introduces a methodology for developing a specialized Telecommunications LLM (Telco LLM) designed to enhance the efficiency of customer service agents and promote consistency in service quality across representatives. We present the construction process of TelBench, a novel dataset created for performance evaluation of customer service expertise in the telecommunications domain. We also evaluate various LLMs and demonstrate the ability to benchmark both proprietary and open-source LLMs on predefined telecommunications-related tasks, thereby establishing metrics that define telcommunications performance.

2022

1. 

   Deep-plane sweep generative adversarial network for consistent multi-view depth estimation

   Dong Wook Shu, Wonbeom Jang, Heebin Yoo, and 2 more authors

   Machine Vision and Applications, 2022

   DOI HTML