Hyunwoo J. Kim

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

ICCV 2025

ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models

arXiv 2025

Representation Shift: Unifying Token Compression with FlashAttention

ICCV 2025

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

arXiv 2025

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

CVPR 2025 1

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

arXiv 2024

Constant Acceleration Flow

constant-acceleration-flow

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

arXiv 2024

vid-TLDR: Training Free Token merging for Light-weight Video Transformer

CVPR 2024 1

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

CVPR 2024 1

LLaMo: Large Language Model-based Molecular Graph Assistant

arXiv 2024

DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations

arXiv 2024

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

ICCV 2023 1

Large Language Models are Temporal and Causal Reasoners for Video Question Answering

arXiv 2023

Read-only Prompt Optimization for Vision-Language Few-shot Learning

ICCV 2023 1

Distribution-Aware Prompt Tuning for Vision-Language Models

ICCV 2023 1

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

ICCV 2023 1