mlsanityData to 7 Oct 2026

EXAONE 4.5 Technical Report

arXiv 2604.08644 ↗First posted 9 Apr 2026cs.CLcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, enabling native multimodal pretraining over both visual and textual modalities. The model is trained on large-scale data with careful curation, particularly emphasizing document-centric corpora that align with LG's strategic application domains. This targeted data design enables substantial performance gains in document understanding and related tasks, while also delivering broad improvements across general language capabilities. EXAONE 4.5 extends context length up to 256K tokens, facilitating long-context reasoning and enterprise-scale use cases. Comparative evaluations demonstrate that EXAONE 4.5 achieves competitive performance in general benchmarks while outperforming state-of-the-art models of similar scale in document understanding and Korean contextual reasoning. As part of LG's ongoing effort toward practical industrial deployment, EXAONE 4.5 is designed to be continuously extended with additional domains and application scenarios to advance AI for a better life.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 27 of its 37 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

27 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts27 Aug
  2. 2024Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM Collaboration24 Jun
  3. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?29 Mar

Other references · 24

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  7. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  8. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
  9. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  10. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  11. 2016A Diagram Is Worth A Dozen Imagescited by 793
  12. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
12 more
  1. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 558
  2. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  3. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 344
  4. 2025MathArena: Evaluating LLMs on Uncontaminated Math Competitionscited by 275
  5. 2025MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understandingcited by 212
  6. 2025Generalizing Verifiable Instruction Followingcited by 178
  7. 2024OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Textcited by 58
  8. 2024MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokenscited by 47
  9. 2026BabyVision: Visual Reasoning Beyond Languagecited by 39
  10. 2025EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modescited by 26
  11. 2025KoBALT: Korean Benchmark For Advanced Linguistic Taskscited by 12
  12. 2025OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learningcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026K-EXAONE Technical Report
  2. 2026K-EXAONE 2.0 Technical Report
  3. 2025EXAONE Deep: Reasoning Enhanced Language Models
  4. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
  5. 2024ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
  6. 2026AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model
  7. 2024LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
  8. 2024Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models