Allison Chen

53 posts

Allison Chen banner
Allison Chen

Allison Chen

@allisonchen_227

Computer Science PhD student @Princeton University working in computer vision and human-ai interaction | hummus enthusiast

Katılım Mart 2023
123 Takip Edilen305 Takipçiler
Alex
Alex@nociza68·
@allisonchen_227 Super interesting design! Any links to the paper itself?
English
1
0
0
8
Allison Chen
Allison Chen@allisonchen_227·
How should we talk about LLMs? Does it matter if we frame them as a machines 📠, tools ⚒️, or companions 👥? In our #CHI2026 paper, that these framings can alter what people believe about LLMs and how they use them. See 🧵for more!
Allison Chen tweet media
English
4
15
46
5K
Allison Chen
Allison Chen@allisonchen_227·
(5/6) 📌This matters because it shows that even brief messages about LLMs can shape how people understand, trust, and rely on them. As these systems become embedded in everyday life, the way we talk about them—across research, media, and product design—has real consequences.
English
1
0
2
212
Allison Chen retweetledi
Xindi Wu
Xindi Wu@cindy_x_wu·
New #NVIDIA Paper We introduce Motive, a motion-centric, gradient-based data attribution method that traces which training videos help or hurt video generation. By isolating temporal dynamics from static appearance, Motive identifies which training videos shape motion in video generation. 🔗 research.nvidia.com/labs/sil/proje… 1/10
English
11
119
579
106.2K
Allison Chen retweetledi
Tyler Zhu
Tyler Zhu@tyleryzhu·
Today seems to be a fitting day for @GoogleDeepMind news, so I'm excited to announce our new preprint! Prior work suggests that text & img repr's are converging, albeit weakly. We found these same models actually have strong alignment; the inputs were too impoverished to see it!
Tyler Zhu tweet media
English
11
25
141
35.3K
Allison Chen retweetledi
Ye Zhu
Ye Zhu@szyezhu·
Prof. Johannes Lutzeyer (@JLutzeyer) and I are co-recruiting a fully funded PhD student at the Department of Computer Science, École Polytechnique in France, to start in September 2026. Details below or at l-yezhu.github.io/assets/PhD_Hir… #PhDhiring #AI
Ye Zhu tweet media
English
2
5
22
2.5K
Allison Chen retweetledi
William Yang
William Yang@YangWilliam_·
Text-to-image (T2I) models can generate rich supervision for visual learning but generating subtle distinctions still remains challenging. Fine-tuning helps, but too much tuning → overfitting and loss of diversity. How do we preserve fidelity without sacrificing diversity (1/8)
English
2
13
39
23.3K
Allison Chen
Allison Chen@allisonchen_227·
(5/6) Our work demonstrates the importance of messaging around AI technology in shaping people’s beliefs about them, as people are still navigating how to conceptualize AI. It also highlights the need for appropriate science communication of AI for the general public.
English
1
0
1
255