Yong Jae Lee

Talk in Pieces, See in Whole: Disentangling and Hierarchical Aggregating Representations for Language-based Object Detection

Contamination Detection for VLMs Using Multi‑Modal Semantic Perturbations

TemporalBench: Evaluating Fine-Grained Temporal Dynamics Understanding for Multimodal Models

Multi-Resolution Fusion: An Effective Approach to Anomaly Detection

Vinoground: Today’s LMMs Don’t Understand Short Counterfactual Videos

Can Vision Models Mirror Human Understanding of Increasing Task Difficulty?

Real Deep Research from Foundation Model to Robotics

Aligned Datasets Improve Detection of Latent Diffusion-Generated Images

Matryoshka Multimodal Models

Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection

TemporalBench: Towards Fine-grained Temporal Understanding for Multimodal Video Models

Do Vision Models Develop Human-Like Progressive Difficulty Understanding?

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models