Papers by Dongwon Kim

5 papers
LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles (2025.findings-emnlp)

Copied to clipboard

Challenge: Figure captions are crucial for helping readers understand and remember a figure’s key message.
Approach: They propose a dataset for personalized figure caption generation with multimodal figure profiles that provide inputs and profiles for each figure .
Outcome: The proposed dataset provides inputs and profiles for personalized figure caption generation with multimodal figure profiles.
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) excel at handling long-context sequences, but require substantial prefill computation and key-value (KV) cache.
Approach: They propose a KV cache compression framework that decouples prefill computation from decoding KV budget.
Outcome: The proposed framework reduces latency in prefill and decoding by leveraging the stabilization of token importance in later layers.
Extending CLIP’s Image-Text Alignment to Referring Image Segmentation (2024.naacl-long)

Copied to clipboard

Challenge: Referring Image Segmentation (RIS) is a cross-modal task that aims to segment an instance described by a natural language expression.
Approach: They propose a framework that leverages the cross-modal nature of CLIP for RIS by leveraging image-text alignment knowledge in CLIP's image-embedding space.
Outcome: The proposed framework outperforms CLIP-based methods on all three major RIS benchmarks and outperformed previous CLIP methods.
ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts (2025.findings-emnlp)

Copied to clipboard

Challenge: ScholarBench evaluates domain-specific knowledge of large language models (LLMs) prior benchmarks lack the scalability to handle complex academic tasks.
Approach: ScholarBench evaluates the academic reasoning ability of large language models . the benchmark is constructed through a three-step process .
Outcome: ScholarBench evaluates the academic reasoning ability of large language models . the benchmark comprises 5,031 examples in Korean and 5,309 examples in English .
Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to document retrieval are coarse and efficient, but expensive.
Approach: a plug-and-play two-stage hybrid-vector framework is proposed to retrieve visually rich documents . HEAVEN efficiently retrieves candidate pages using a single-vektor method over VS-Pages . it also reranks candidates with a multi-vecctor method while filtering query tokens by linguistic importance .
Outcome: HEAVEN achieves 99.87% of the Recall@1 performance of multi-vector models on average . it reduces per-query computation by 99.8%, achieving efficiency and accuracy .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations