High Impact Thesis
The High Impact Thesis Podcast is a platform that hosts PhD students, Researchers, and Professors, from Nanyang Technological University (NTU Singapore), to talk about their research and share their work experience.Brought to you by NTU World of Wisdom.Email: hitpod.wow@gmail.com
- Indexed episodes, last 90 days
- 2
- Latest publication
- Sep 1, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 21, 2026
Latest episodes
47. Anthony Toh – What Holds US Alliances Together? (opens the original)
Read excerpt
Why do countries sometimes hesitate to work more closely with powerful allies, even when regional security threats are growing? In this episode, we speak with Anthony Toh Han Yang, a PhD student at NTU’s Public Policy and Global Affairs programme, about his research on US alliances and alliance cohesion in the Asia-Pacific. Anthony explains why rising threats alone cannot fully account for alliance behaviour, highlighting the importance of strategic value, bilateral relationships, domestic polit
46. Ziqi Huang - Judging the Generated World: The Actual Science Behind Video AI (opens the original)
Read excerpt
What does it take for AI-generated images and videos to do more than simply look real? In this episode, we speak with Ziqi Huang, a Ph.D. candidate at NTU’s MMLab, about her research on making generative AI more controllable, reliable, and aligned with human understanding. She introduces ReVersion, which helps diffusion models learn relationships between objects; VBench and VBench++, which evaluate video-generation models across multiple human-aligned dimensions; and VChain, which enables models
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.