
UC Santa Barbara NLP Group
@ucsbNLP
Followers
2K
Following
564
Media
19
Statuses
252
NLP Researchers @ University of California, Santa Barbara. Profs. @WilliamWangNLP, Xifeng Yan, Simon Todd, @CodeTerminator; acct run by @XiaoSophiaPu
Santa Barbara, CA
Joined July 2021
RT @WilliamWangNLP: Congratulations to all! Super excited to graduate 7 PhD students this year: they are joining UW, Princeton, Google x 2,….
0
5
0
RT @kexun_zhang: RLVR is not just about RL, it's more about VR!. Particularly for LLM coding, good verifiers (tests) are hard to get!. In o….
leililab.github.io
We propose HardTestGen, a pipeline for synthesizing high-quality test cases and study how much it improves code evaluation and LLM post-training.
0
16
0
RT @m2saxon: If you're trying to decide which CVPR tutorial to attend,. Check out @KaijieZhu07, @XiaoSophiaPu, @nieyuzhou, Hao Chen, and my….
0
7
0
RT @AlfonAmayuelas: 📰 Thrilled to be featured in my hometown newspaper🤯 @diariodeburgos as part of a series on people living abroad! The ar….
0
1
0
RT @XinyiWang98: I’m attending #ICLR in Singapore! Also excited to share that I’m joining the Princeton Language and Intelligence Lab as a….
0
13
0
RT @XiaoSophiaPu: 🧠 Reasoning models often overthink. 🚀 In our new paper, we show: .1️⃣ Two overthinking scores. 2️⃣ DUMB500 — a benchmark….
0
12
0
RT @AlfonAmayuelas: 📜🚨 Check out our latest work on "Self-Resource Allocation in Multi-Agent LLM Systems" where we explore how LLMs can be….
0
19
0
RT @weixi_feng: 🎉Thrilled to share my internship work with the @NVIDIA GenAIR team (accepted to #CVPR2025): BlobGEN-Vid: Compositional Text….
0
10
0
RT @yujielu_10: I’m excited to share that I’ve joined @AIatMeta as a Research Scientist, where I’ll be working on Llama Post-training (mult….
0
6
0
RT @JiachenLi11: 🚀🚀 Life update: I just defended my PhD and have joined @xai to advance the visual generation models with @hexianghu @tingc….
0
11
0
RT @WilliamWangNLP: 🚀 Excited to share the latest on our recent UCSB NLP alumni! 🎉.🔹 @JiachenLi11 (PhD '25) → xAI.🔹 @yujielu_10 (PhD '25)….
0
10
0
RT @anton_iades: happy to see an approach that took inspiration from SWE-Search achieving SOTA on SWE-bench. while there is still plenty o….
0
3
0