Kai-Wei Chang

Tunghai University — Taiwan

Computer Science · Physical Sciences

52h-index16.3kcitations527works1.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(278), Natural Language Processing Techniques(210), Multimodal Machine Learning Applications(94), Domain Adaptation and Few-Shot Learning(48), Adversarial Robustness in Machine Learning(42)

Publications526 total

Short- vs. long-axis ultrasound-guided injections for the proximal and distal parts of the posterior interosseous nerve: a cadaveric study
Journal of Medical Ultrasonics·2026
A Study on Computational Thinking Teaching Strategies to Reduce Learning Technical Barriers Using Google Form
Lecture notes in educational technology·2026
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
arXiv (Cornell University)·2025Open Access
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions
arXiv (Cornell University)·2025Open Access
Measuring Narrative Complexity Among Suicide Deaths in the National Violent Death Reporting System (2003–2021 NVDRS)
Information·2025Open Access
Re-imagining Virtual Communities: Ethical Guidelines for Studying Black Twitter
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2025Open Access
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
arXiv (Cornell University)·2025Open Access
HoneyBee: Data Recipes for Vision-Language Reasoners
arXiv (Cornell University)·2025Open Access
BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation
arXiv (Cornell University)·2025Open Access
Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
arXiv (Cornell University)·2025Open Access
Energy-Driven Steering: Reducing False Refusals in Large Language Models
arXiv (Cornell University)·2025Open Access
Towards Unsupervised Speech Recognition at the Syllable-Level
arXiv (Cornell University)·2025Open Access
FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Exploring Patients' Perceptions of an Advance Care Planning Intervention in the Emergency Department: A Qualitative Study
Academic Emergency Medicine·2025Open Access
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
SuperIntelligence - Robotics - Safety & Alignment·2025Open Access
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models
2025· 3 citedOpen Access
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
2025· 2 cited
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
arXiv (Cornell University)·2025Open Access
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
arXiv (Cornell University)·2025Open Access
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
arXiv (Cornell University)·2025Open Access
page 1 of 27Next →

Frequent Co-authors

Jieyu Zhao(10), Mark Yatskar(8), Nanyun Peng(7), Tianlu Wang(6), Vicente Ordóñez(6), Cho‐Jui Hsieh(5), Wasi Uddin Ahmad(5), Yizhou Sun(4), Prem Natarajan(4), Tolga Bolukbasi(3), James Zou(3), Venkatesh Saligrama(3), Adam Tauman Kalai(3), Liunian Harold Li(3), Da Yin(3), Ziniu Hu(3), Emily Sheng(3), Muhao Chen(3), Dan Roth(3), Moustafa Alzantot(2)