UC Santa Barbara NLP Group @ucsbNLP

NLP Researchers @ucsantabarbara. Profs. @WilliamWangNLP, @xwang_lk, Xifeng Yan, Simon Todd, @WenboGuo4, @CodeTerminator, acct run by @XiaoSophiaPu nlp.cs.ucsb.edu Santa Barbara, CA Joined July 2021

Tweets

253
Followers

2K
Following

732
Likes

563

UC Santa Barbara NLP Group @ucsbNLP

2 weeks ago

We did it! 🎉 12 papers from UCSB NLP accepted at #EMNLP2025 (7 Main + 5 Findings) Proud of everyone’s hard work—poster below 👇

0 9 36 7K 3

Download Image

Xin Eric Wang @xwang_lk

2 months ago

It is official: my first day at UCSB as a faculty. Happy to join the force to advance AI research and nurture talent. Let's go @ucsbNLP @ucsbcs!

18 11 448 29K 21

Download Image

William Wang @WilliamWangNLP

3 months ago

Congratulations to all! Super excited to graduate 7 PhD students this year: they are joining UW, Princeton, Google x 2, xAI, Amazon, and Meta. They are the future of AI!

Michael Saxon @m2saxon

3 months ago

Congratulations to all! Super excited to graduate 7 PhD students this year: they are joining UW, Princeton, Google x 2, xAI, Amazon, and Meta. They are the future of AI!

8 1 101 17K 2

Download Image

2 5 102 10K 3

Wenda Xu @WendaXu2

3 months ago

Finally completed this journey. Thanks a lot to my family, advisors and friends!

10 5 80 5K 4

Download Image

1/3 How can we reliably trace a student’s understanding with just a few exercise responses? In classrooms, it’s important for teachers to track students’ understanding and predict their future performance on exercises. However, existing knowledge tracing (KT) algorithms often…

1 2 4 837 1

Download Gif

UC Santa Barbara NLP Group @ucsbNLP

3 months ago

After all the papers, presentations, and sleepless nights... You can finally say it: Call me Doctor. 😎🎓 Congrats to the PhD Class of 2025! ❤️

Michael Saxon @m2saxon

3 months ago

After all the papers, presentations, and sleepless nights... You can finally say it: Call me Doctor. 😎🎓 Congrats to the PhD Class of 2025! ❤️

8 1 101 17K 2

Download Image

0 1 16 806 1

Kexun Zhang @kexun_zhang

3 months ago

RLVR is not just about RL, it's more about VR! Particularly for LLM coding, good verifiers (tests) are hard to get! In our latest work, we ask 3 questions: How good are current tests? How do we get better tests? How much does test quality matter? leililab.github.io/HardTests/

4 16 93 6K 55

Michael Saxon @m2saxon

3 months ago

If you're trying to decide which CVPR tutorial to attend, Check out @KaijieZhu07, @XiaoSophiaPu, @NieYuzhou, Hao Chen, and my tutorial on Evaluating Multimodal Models Unfortunately, I won't be able to attend, but my lovingly crafted slides are in the mix :)

1 7 40 3K 5

Download Image

UC Santa Barbara NLP Group @ucsbNLP

4 months ago

Lab celebration lunch after @XinyiWang98's defense!

3 5 29 3K 0

Download Image

Alfonso Amayuelas @AlfonAmayuelas

4 months ago

📰 Thrilled to be featured in my hometown newspaper🤯 @diariodeburgos as part of a series on people living abroad! The article discusses my journey from Burgos to California. Check out the article in español 🇪🇸🔗diariodeburgos.es/noticia/z35dd9…

3 1 19 3K 0

Download Image

Xinyi Wang @XinyiWang98

5 months ago

I’m attending #ICLR in Singapore! Also excited to share that I’m joining the Princeton Language and Intelligence Lab as a postdoc in July. In Fall 2026, I’ll be starting as an Assistant Professor at the University at Buffalo. I’ll be recruiting—feel free to reach out and chat!

23 12 162 18K 22

Sophia Xiao Pu @XiaoSophiaPu

5 months ago

🧠 Reasoning models often overthink. 🚀 In our new paper, we show: 1️⃣ Two overthinking scores. 2️⃣ DUMB500 — a benchmark of extremely easy questions. 3️⃣ THOUGHT TERMINATOR — a decoding method that reduces token waste by up to 90%, often improving accuracy. Details below 👇

4 12 101 20K 43

Download Image

Alfonso Amayuelas @AlfonAmayuelas

5 months ago

📜🚨 Check out our latest work on "Self-Resource Allocation in Multi-Agent LLM Systems" where we explore how LLMs can be used to optimize task allocation in multi-agent systems 🤖 🧵(1/3)

1 19 53 11K 37

Download Image

Weixi Feng @weixi_feng

6 months ago

🎉Thrilled to share my internship work with the @nvidia GenAIR team (accepted to #CVPR2025): BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations! 🚀BlobGEN-Vid is a model-agnostic framework that delivers: - SOTA layout controllability - Enhanced…

2 10 68 12K 16

Download Video

AK @_akhaliq

7 months ago

MLGym A New Framework and Benchmark for Advancing AI Research Agents

4 42 188 19K 73

Download Image

Yujie Lu @yujielu_10

7 months ago

I’m excited to share that I’ve joined @AIatMeta as a Research Scientist, where I’ll be working on Llama Post-training (multimodality). Can’t wait to work with the team and contribute to open-source multimodal AI! This new chapter comes right after successfully completing my PhD…

13 6 218 17K 19

Download Image

Jiachen Li @JiachenLi11

7 months ago

🚀🚀 Life update: I just defended my PhD and have joined @xai to advance the visual generation models with @hexianghu @tingchenai Words cannot describe how grateful I am to my awesome advisor, @WilliamWangNLP, and my committee members, Xifeng Yan and @WenhuChen. Huge thanks to…

41 11 505 38K 29

Download Image

William Wang @WilliamWangNLP

7 months ago

🚀 Excited to share the latest on our recent UCSB NLP alumni! 🎉 🔹 @JiachenLi11 (PhD '25) → xAI 🔹 @yujielu_10 (PhD '25) → Meta GenAI 🔹 @PanLiangming (Postdoc '24) → Asst. Prof., Arizona 🔹 @Qnolan4 (PhD '24) → Meta GenAI Proud of their achievements—onward and upward! 🚀

3 10 199 15K 21

UC Santa Barbara NLP Group @ucsbNLP

8 months ago

🚀🚀🚀Today's top SWEBench model, built using @anton_iades's SWE-Search

skcd @skcd42

8 months ago

🚀🚀🚀Today's top SWEBench model, built using @anton_iades's SWE-Search

9 6 130 41K 18

Download Image

1 2 13 3K 0

Antonis Antoniades @anton_iades

8 months ago

happy to see an approach that took inspiration from SWE-Search achieving SOTA on SWE-bench. while there is still plenty of room for improvement, search is a vital tool for navigating complex SWE environments, and I expect more approaches to follow suit.