DK
Dohwan Ko
cs.CVcs.AIcs.CLcs.LGq-bio.MN
On Valency
published · living versionsW_555e4fx3·v1 · currentpublished
MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
with Seohyun Lee, Jongha Kim, Ji Soo Lee, Seoung Choi +2
1 version
Preprints & journals
15 papers in the corpus · 2022–2026MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records2610.27911v1 · Seohyun Lee, Jongha Kim, Dohwan Ko et al.2026 · 0 citationsarXivon Valency
SuperClip Pyramid for Video Temporal Grounding2610.26925v1 · Sanghyeok Lee, Juyeon Ko, Joonmyung Choi et al.2026 · 0 citationsarXiv
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation2609.38024v1 · Jaewon Chu, Ji Soo Lee, Jihwan Park et al.2026 · 0 citationsarXiv
SVMemAgent: A Streaming Video Memory Agent for Query-Agnostic Online Frame Selection2609.18540v1 · Dohwan Ko, Ji Soo Lee, Pierce Chuang et al.2026 · 0 citationsarXiv
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data2609.05405v1 · Ji Soo Lee, Xilun Chen, Pierce Chuang et al.2026 · 0 citationsarXiv
VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement2607.00446v1 · Seohyun Lee, Seoung Choi, Dohwan Ko et al.2026 · 0 citationsarXiv
DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning2604.22281v1 · Joonmyung Choi, Sanghyeok Lee, Jongha Kim et al.2026 · 0 citationsarXiv
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models2603.24984v2 · Dohwan Ko, Jinyoung Park, Seoung Choi et al.2026 · 0 citationsarXiv
Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval2507.23284v3 · Dohwan Ko, Ji Soo Lee, Minhyuk Choi et al.2025 · 4 citationsarXiv
ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models2503.19355v2 · Dohwan Ko, Sihyeon Kim, Yumin Suh et al.2025 · 0 citationsarXiv
LLaMo: Large Language Model-based Molecular Graph Assistant2411.00871v1 · Jinyoung Park, Minseong Bae, Dohwan Ko et al.2024 · 0 citationsarXiv
Large Language Models are Temporal and Causal Reasoners for Video Question Answering2310.15747v2 · Dohwan Ko, Ji Soo Lee, Wooyoung Kang et al.2023 · 37 citationsarXiv
Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models2308.09363v1 · Dohwan Ko, Ji Soo Lee, Miso Choi et al.2023 · 7 citationsarXiv
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models2303.13009v1 · Dohwan Ko, Joonmyung Choi, Hyeong Kyu Choi et al.2023 · 33 citationsarXiv
Video-Text Representation Learning via Differentiable Weak Temporal Alignment2203.16784v1 · Dohwan Ko, Joonmyung Choi, Juyeon Ko et al.2022 · 22 citationsarXiv
Career total: 18 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.