Chenxinran Elise Shen

CMC, VR, HAI and more… I have a cat named Hippo 🦛🐈

[Chenxinran Elise Shen @ChenxinranS]

Thrilled to receive my 2nd Honorable Mention paper at #CHI2024! Both awarded papers investigate how voice can influence interpersonal communication, one within the context of online dating and the other in a paid game teammate online community. Thanks to my collaborators!

[Meng XIA @Iriskie_Xia]

🎓 PhD Recruitment | Texas A&M CS
I am seeking 1–2 PhD students for Fall 2026 in Human–AI Interaction, with a focus on AI for education.

✅ Motivated and responsible
✅ CS background
✅ Full-stack development or LLM fine-tuning experience is a plus

📅 Deadline: Dec 15, 2025

[Yue Jiang @YueJiang_nj]

I’m hiring students who are interested in multimodal generative AI / UI agent-related topics.

My current vision is that we should have human-in-the-loop controllable UI generation models that adapt UIs to the diverse needs of designers and users + enhance human creativity.

[Chenxinran Elise Shen @ChenxinranS]

vancouver is getting into summer ✨

[Kaseya @Kaseya21159582]

Excited to present our #CHI2025 paper “HaloTouch: Using IR Multi-Path Interference to Support Touch Interactions with General Surfaces” at Yokohama tomorrow. The video is available on YouTube as well: https://t.co/YE5YILighC

[Jessica Bo @jbo_twt]

Thrilled to share that our paper "To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models" received an Honorable Mention at #CHI2025! 🔥

preprint >> https://t.co/719x04beT7
video >> https://t.co/jjv5Ozktfn

[Chenxinran Elise Shen @ChenxinranS]

Canadian research funding opportunity 👉

✨Launch of the new Harmonized Tri-agency Scholarship and Fellowship programs

https://t.co/2HmzrEZmIu

[Chenxinran Elise Shen @ChenxinranS]

My work from last summer in Finland with amazing scholars from @AaltoUniversity and @LMU_Muenchen has been published on Augmented Humans (AHs) International Conference
⭐How will humans collaborate with their "augmented" counterparts in the future? https://t.co/ihtIVrXOUU

[Chenxinran Elise Shen @ChenxinranS]

@luzc08 Thanks Zhicong!

[Chenxinran Elise Shen @ChenxinranS]

@nicolayr_ 😊 thanks Nicolay!

[Chenxinran Elise Shen @ChenxinranS]

200 citations reached!
https://t.co/5JGmcrmTik

[Daniel Buschek @DBuschek]

📢 Looking for current research on #HCI + #AI? Here's a collection of 200+ #CHI2025 preprints, collected via arXiv and your suggestions: https://t.co/SZnY8RrDir

[Hannah Overbye-Thompson @Hannah_Overbye]

New meta-analysis (2024) finds human-AI collaboration is task-dependent: performance increases for creative & open-ended tasks (like content creation), but performance drops for decision-making tasks; human-AI collaboration seems to work best when humans already outperform AI

[Rohan Paul @rohanpaul_ai]

Your brain's next 5 seconds, predicted by AI

Transformer predicts brain activity patterns 5 seconds into future using just 21 seconds of fMRI data

Achieves 0.997 correlation using modified time-series Transformer architecture

-----

🧠 Original Problem:

Predicting future brain states from fMRI data remains challenging, especially for patients who can't undergo long scanning sessions. Current methods require extensive scan times and lack accuracy in short-term predictions.

-----

🔬 Solution in this Paper:

→ The paper introduces a modified time series Transformer with 4 encoder and 4 decoder layers, each containing 8 attention heads

→ The model takes a 30-timepoint window covering 379 brain regions as input and predicts the next brain state

→ Training uses Human Connectome Project data from 1003 healthy adults, with preprocessing including spatial smoothing and bandpass filtering

→ Unlike traditional approaches, this model omits look-ahead masking, simplifying prediction for single future timepoints

-----

🎯 Key Insights:

→ Temporal dependencies in brain states can be effectively captured using self-attention mechanisms

→ Short input sequences (21.6s) suffice for accurate predictions

→ Error accumulation follows a Markov chain pattern in longer predictions

→ The model preserves functional connectivity patterns matching known brain organization

-----

📊 Results:

→ Single timepoint prediction achieves MSE of 0.0013

→ Accurate predictions up to 5.04 seconds with correlation >0.85

→ First 7 predicted timepoints maintain high accuracy

→ Outperforms BrainLM with 20-timepoint MSE of 0.26 vs 0.568

[Jing-Jing Li @drjingjing2026]

1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feeling uncomfortable. As a community, I believe we should take a moment to reflect on why such remarks in public discourse can be offensive and harmful.

[Jeff Clune @jeffclune]

The secret to doing good research is always to be a little underemployed. You waste years by not being able to waste hours. - Amos Tversky

[Gautam Kamath @thegautamkamath]

Politeness Tier List
Tier C: New Yorkers
Tier B: US Southerners
Tier A: Canadians
Tier S: ICLR authors when replying to reviewers

[Ishtiaque Ahmed @ishtiaqueSIA]

Move to Canada! University of Toronto Department of Computer Science is hiring tenure-stream faculty at all levels. Apply Now! https://t.co/adT1PLLqP5

[Shao ZHANG 🫡DAI2026 Call for paper @Alice_ShaoZHANG]

UPDATE: PCs gave a desk reject and mark it as plagiarism.

[Chenxinran Elise Shen @ChenxinranS]

Congrats Preeti ✨I am so happy for u girl

[Preeti Vyas, Ph.D. @preetivyas_]

Check out our work on ShearSense at #UIST2024 We demonstrate interplay between shear, pressure, and individuality evaluating affective touch on a soft capacitive sensor.
Not at UIST this year but my amazing colleagues are. Go say hi to
@dev_mclaren @jsonx99 ✨#affectivehaptics