Sihang (Nagi) Zhao

CS PhD student @NYU_Courant | Knowledge Editing, AI for Education, Personalized Learning| Prev. @ImperialCollege @CUHKSZ

[Sihang (Nagi) Zhao @SihangZhao]

王虹教授的几段采访，说本科时“数学忽然变得困难起来”，让她“felt discouraged”；谈及自己在巴黎尝试转建筑，最终发现自己还是更喜欢数学时笑得很灿烂又好像带着点不好意思；讲到导师时显得非常幸福，言语中充满感激…

我的天分和努力都不及王虹教授的万分之一，但她谈到的这些内容以及谈及它们时的神情却让我深深共鸣并眼眶湿润：我也是高考陆本，欧洲读研最终来美国读博（非常巧合的，博士和王虹教授在同一个系）。回望本科及以前的学习生涯，就像一场漫长的溺水，十余年里我在过度自信和自我怀疑之间反复挣扎，学习的唯一动力就是证明自己的聪明，而失去了“聪明”仿佛就会失去了有关自我的一切，在这种基于初始的恐惧和焦虑（而非正反馈）的惯性下的“泄气”，和王虹教授所说的discouraged大概类似。

后来我也尝试了许多方向，几度想放弃学业，幸运的是，我后来也陆续遇到了生命中最重要的朋友和导师，他们给我了无条件的相信和支持，让我终于忘记自己“有没有天赋”这件事，得以自由地探索自己热爱且好奇的领域，并收获了快乐。

我大概一生无法达到也不奢望能达到王虹教授万分之一的成就，但我却希望能拥有她百分之一百的做自己热爱之事的纯粹平静与幸福。

恭喜王虹教授获得了这份实至名归的荣誉。我没有任何理由与有荣焉，只是感谢在这么近的距离之内能看到这样好的榜样，给我许多力量和希望。

[Sihang (Nagi) Zhao @SihangZhao]

Grateful to Martin @ziqiao_ma for the invitation to join this ACL Mentorship panel.

I hope I can bring the perspective of those of us still early in our PhD journeys.

I’d love to hear from other students and early-career NLP researchers: what questions or concerns would you want us to discuss for this topic? Feel free to comment or DM me, and I’ll try to bring your questions to the panel!

[ACL Mentorship @aclmentorship]

📢 Join us for the ACL Mentorship Session
@aclmeeting #ACL2026NLP
Location: Grand Hall Foyer - Level 1

We’re excited to have an amazing group of mentors joining us:
@Lianhuiq
@ManlingLi_
@zhaofeng_wu
@SihangZhao
@shannonzshen
@ziqiao_ma

We’re also launching a new initiative to connect mentors and mentees across the AI/NLP community! If you’re interested in participating, sign up here:
🔗 https://t.co/CEqWQ2ixsp

[Sihang (Nagi) Zhao @SihangZhao]

@jocelynjshen @MIT Congrats!

[Sihang (Nagi) Zhao @SihangZhao]

Paper link: https://t.co/dCwW3jNilT
Website: https://t.co/Yv5zPrrYUe

[Sihang (Nagi) Zhao @SihangZhao]

My first work in PhD study is accepted as oral presentation @aclmeeting !

We take the first step towards unifying and formalizing safe, helpful and pedagogical behaviors with knowledge‑mastery graphs for educational LLMs.

Meet me at Oral Session C: NLP Applications 2, July 5!

[Andrej Karpathy @karpathy]

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc.

More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage:

1) raw text (hard/effortful to read)
2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default
3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default
...4,5,6,...
n) interactive neural videos/simulations

Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral https://t.co/z21CP5iQfu

There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen.

TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

[Sihang (Nagi) Zhao @SihangZhao]

Legend

[Catherine Yeo @catherinehyeo]

Love seeing Naomi Osaka honor the CLRS Algorithms textbook at this year's Met Gala

[Sihang (Nagi) Zhao @SihangZhao]

The elevator at CDS has been fixed. What else can't be done? I am full of confidence in everything.

[Sihang (Nagi) Zhao @SihangZhao]

@claudeai @DarioAmodei Same thing happened to me. My account has been suspended twice (included an https://t.co/pwSim4Te7p account), no warning, no explanation, all dialogue just gone. And support team repeatedly replied they are unable to confirm the reasons.

[Min Choi @minchoi]

Anthropic shut down an entire company's Claude access overnight

60+ employees. No explanation. Just an email.

Want to appeal? Fill out a Google Form.

Integrations gone. Histories gone. Everything built on Claude... gone.

Never let one vendor own your workflow.

[Sihang (Nagi) Zhao @SihangZhao]

@jocelynjshen Congrats!!

[Xiang 'Anthony' Chen @_xiang_chen_]

Some thoughts on important problems for HCI: https://t.co/coQI09syk0

[Sihang (Nagi) Zhao @SihangZhao]

@cyodyssey ppt应该99%可能性不是自己做的😂

[Sihang (Nagi) Zhao @SihangZhao]

The gap between people’s abilities will be defined by how proactively they use these resources. Maybe we are witnessing the biggest paradigm shift in education in the whole human history.

[Andrej Karpathy @karpathy]

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.

[Hua Shen✨ @huashen218]

🧐Are values in LLMs aligned with humans? 1️⃣
And if they are — do LLMs stay honest to those values, or sometimes say one thing but act another? 2️⃣

✨ We explore these questions in two papers presented at #EMNLP2025:
1️⃣ ValueCompass: https://t.co/oN2p9yciqY (WiNLP Workshop)
2️⃣ Mind the Value–Action Gap: https://t.co/TGi8oZ1RSl (Main Track)
🔍 Dataset & Code: https://t.co/CxTfTNiMVF

🌱 I’m also #Hiring multiple PhD students for Fall 2026 @ NYU Courant Computer Science!
If you’re passionate about #Human_AI_Alignment, #Value_Alignment, or broad #AI + #Human (society) research, let’s connect at EMNLP2025, NeurIPS2025, or over Zoom!
🎓 NYU CS PhD Apply (NYU Shanghai Track): https://t.co/wjazsiwub8

💜 This year I’m also co-organizing the #EMNLP2025 WiNLP Workshop and supporting the amazing #Tutorial on Spoken Conversational Agents with LLMs (a short 15min talk)!
Come say hi 👋 — I’d love to chat and connect with old and new friends at #EMNLP2025!
🔗 WiNLP Workshop: https://t.co/1XvgLfPKMl
🔗Tutorial on Spoken Conversational Agents: https://t.co/rpVYqwXxBq

💗Huge thanks to my wonderful paper collaborators — @tanmit,@YunHuang_HCI,@tknearem,@reshmigh,Nicholas Clark,Yu-Ju Yang — and my inspiring workshop/tutorial collaborators @huckiyang, Andreas Stolcke,@TYSSSantosh2,@therealthapa,@MeryemMhamdi1,Chen Zhang, Peerat Limkonchotiwat, Wiem Ben Rim.... 🤗Truly grateful and enjoyable to work with you all! 💫

#HumanAIAlignment #PhDOpening #NYU #NYUShanghai #ValueAlignment #HAI

[Sihang (Nagi) Zhao @SihangZhao]

@TongPetersb eyes wide clo…opened👏

[Alexis Ross @alexisjross]

Can LLMs reason like a student? 👩🏻‍🎓📚✏️

For educational tools like AI tutors, modeling how students make mistakes is crucial.

But current LLMs are much worse at simulating student errors ❌ than performing correct ✅ reasoning.

We try to fix that with our method MISTAKE 🤭👇

[Sihang (Nagi) Zhao @SihangZhao]

@LukasNLP You should get a best poster award in *CL

[Sihang (Nagi) Zhao @SihangZhao]

@cyodyssey 举手捞捞我🥹

[Sihang (Nagi) Zhao @SihangZhao]

@cyodyssey 有ACM学生会员之后很多会注册费会便宜不少