Junho Kim

arkimjh's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 1 month ago

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

Paper • 2506.01274 • Published Jun 2 • 3

authored 2 papers 7 months ago

Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing

Paper • 2411.19460 • Published Nov 29, 2024 • 11

SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis

Paper • 2411.16173 • Published Nov 25, 2024 • 10

authored 7 papers about 1 year ago

CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models

Paper • 2406.01920 • Published Jun 4, 2024 • 1

Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning

Paper • 2307.07250 • Published Jul 14, 2023 • 2

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression

Paper • 2303.01052 • Published Mar 2, 2023 • 3

Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck

Paper • 2204.02735 • Published Apr 6, 2022 • 4

Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network

Paper • 2204.02738 • Published Apr 6, 2022 • 3

Causal Unsupervised Semantic Segmentation

Paper • 2310.07379 • Published Oct 11, 2023 • 3

What if...?: Counterfactual Inception to Mitigate Hallucination Effects in Large Multimodal Models

Paper • 2403.13513 • Published Mar 20, 2024 • 1