Picture for Kai-Wei Chang

Kai-Wei Chang

STIV: Scalable Text and Image Conditioned Video Generation

Add code
Dec 10, 2024
Viaarxiv icon

SafeWorld: Geo-Diverse Safety Alignment

Add code
Dec 09, 2024
Viaarxiv icon

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

Add code
Dec 03, 2024
Viaarxiv icon

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Add code
Nov 27, 2024
Viaarxiv icon

DRS: Deep Question Reformulation With Structured Output

Add code
Nov 27, 2024
Viaarxiv icon

Verbalized Representation Learning for Interpretable Few-Shot Generalization

Add code
Nov 27, 2024
Viaarxiv icon

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Add code
Nov 08, 2024
Viaarxiv icon

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

Add code
Oct 30, 2024
Figure 1 for SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Figure 2 for SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Figure 3 for SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Figure 4 for SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Viaarxiv icon

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

Add code
Oct 29, 2024
Viaarxiv icon

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness

Add code
Oct 24, 2024
Figure 1 for SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
Figure 2 for SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
Figure 3 for SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
Figure 4 for SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
Viaarxiv icon