Zhu_Yanqiao Profile Banner
Yanqiao ZHU Profile
Yanqiao ZHU

@Zhu_Yanqiao

Followers
930
Following
818
Media
9
Statuses
221

CS PhD @UCLA | AI for Science, Autonomous Scientific Discovery

Los Angeles
Joined June 2020
Don't wanna be here? Send us removal request.
@Xiaoxuan__Wang
Mandy
8 months
What kind of data should we prioritize during self-training? Confident โŒ Uncertain โœ… Weโ€™re excited to introduce ๐Ÿค”EAST ๐Ÿ˜Žโ€” a novel weighting strategy that prioritizes uncertain data during self-training. EAST uses a mapping function with a tunable sharpness parameter to
4
42
197
@sunjiao123sun_
Jiao Sun
11 months
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Canโ€™t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? ๐Ÿ˜ก
181
803
4K
@drjingjing2026
Jing-Jing Li
11 months
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.
180
565
4K
@zy27962986
Zongyu Lin
1 year
๐Ÿš€๐Ÿš€๐Ÿš€Want to develop a cutting-edge video generation model towards Sora? Please dive into Appleโ€™s latest recipe and studies for scalable video generation models๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ. In this work, we aim at providing a transparent and detailed recipe ๐Ÿ“– for model architecture, training
9
46
131
@chaitjo
Chaitanya K. Joshi
1 year
A big THANK YOU to each and every one of the participants, presenters, tutorials, and local organizers for making the third @LogConference possible! ๐Ÿ’™
0
6
27
@xbresson
Xavier Bresson
1 year
I will give a talk at the @LogConference on "Integrating Graph Neural Networks and Large Language Models". The conference is virtual, free to attend, live-streamed, and recorded. https://t.co/PwtgTz0Z4a Hope to see you there!
@LogConference
Learning on Graphs Conference 2025
1 year
See you in LoG 2024!
2
44
164
@LogConference
Learning on Graphs Conference 2025
1 year
See you in LoG 2024!
0
21
53
@Yihe__Deng
Yihe Deng
1 year
๐Ÿ˜„I did a brief intro of RLHF algorithms for the reading group presentation of our lab. It was a good learning experience for me and I want to share the github repo here holds the slides as well as the list of interesting papers: https://t.co/TFIcpwUqul Would love to hear about
7
27
259
@chenchenye_ccye
Chenchen Ye
1 year
๐Ÿ“ขNew LLM Agents Benchmark! Introducing ๐ŸŒŸMIRAI๐ŸŒŸ: A groundbreaking benchmark crafted for evaluating LLM agents in temporal forecasting of international events with tool use and complex reasoning! ๐Ÿ“œ Arxiv: https://t.co/ikuRg2SQtr ๐Ÿ”— Project page: https://t.co/hrMjFRk6gR ๐Ÿงต1/N
14
70
301
@Zhu_Yanqiao
Yanqiao ZHU
1 year
Check out our new work in LLMs for molecule optimization!
@YuanqiD
Yuanqi Du
1 year
๐Ÿงต1/n LLMs significantly improve Evolutionary Algorithms for molecular discovery! For 18 different molecular optimization tasks, we demonstrate how to achieve SOTA performance by incorporating different LLMs! Learn more in our new paper! Website: https://t.co/S0zw97Ialr(w/ Code)
0
0
3
@acbuller
Ziniu Hu
1 year
How to control LLM behavior with LLM-as-a-judge? Check our paper: "Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller" Website: https://t.co/PZoWUqrAHN Paper: https://t.co/Xwl8wEJX0g Code: https://t.co/x0yiK77qaW
2
13
47
@Yihe__Deng
Yihe Deng
1 year
๐Ÿ“ข New paper alert! Introducing STIC (Self-Training on Image Comprehension) that enhances the understanding and reasoning capabilities of LVLMs through self-generated data ๐ŸŒŸ ๐Ÿ“„ Read the paper: https://t.co/Pzwj5gCIZq ๐Ÿ”— Project page: https://t.co/y4GRQyKwii ๐Ÿ’ป GitHub Repo:
1
44
200
@Zhu_Yanqiao
Yanqiao ZHU
2 years
Our SciBench paper got accepted to #ICML2024! ๐Ÿ”ฌWe benchmarked leading open-source & proprietary LLMs, including multimodal models, on the updated SciBench Check out the paper at
Tweet card summary image
arxiv.org
Most of the existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations....
@Xiaoxuan__Wang
Mandy
2 years
๐ŸงธWe introduce SCIBENCH, a challenging college-level scientific dataset designed to evaluate the reasoning abilities of current LLMs (#gpt4, #chatgpt). ๐ŸปWe find that no current prompting methods or external tools improves all capabilities. Github: https://t.co/JXfGuDiJi7
1
6
33
@AIHealthMIT
MIT Jameel Clinic for AI & Health
2 years
6โƒฃ Check out MARCEL in Session 4 on May 8. MARCEL is a benchmark that comprehensively evaluates molecular conformations via 4 datasets covering diverse molecule- and reaction-level properties for drug discovery and enzyme design: https://t.co/wEvuFs9Oq5 #ICLR2024
1
3
8
@ritaranx
Ran Xu
2 years
๐Ÿงฌ Still using BM25 for biomedical retrieval? Try out BMRetriever! ๐Ÿ” Our new series of retrievers enhance biomedical search with various scales (410M-7B). ๐Ÿ”“ Model/Data: https://t.co/hJkgKZJKcB ๐ŸŒ  Github: https://t.co/Jkap1bJrOP #BiomedicalResearch #LLM #Retrieval #OpenScience
Tweet card summary image
github.com
[EMNLP 2024] This is the code for our paper "BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers". - ritaranx/BMRetriever
1
11
37
@mmbronstein
Michael Bronstein
2 years
We started releasing the first chapters of our Geometric Deep Learning book and the accompanying slides from the corresponding Oxford and Cambridge courses.
@PetarV_93
Petar Veliฤkoviฤ‡
2 years
After 3 years, it's time for us to start sharing the chapters of the GDL book! โค๏ธ Also included: companion slides from our @Cambridge_Uni & @UniofOxford courses ๐Ÿง‘โ€๐ŸŽ“ Chapter 1 is out **now**! More to follow soon ๐ŸŽ‰ https://t.co/g7SqyZBCgX ๐Ÿ“– @mmbronstein @joanbruna @TacoCohen
10
104
665
@LogConference
Learning on Graphs Conference 2025
2 years
๐Ÿš€ Great news! The @LogConference 2023 proceedings are now available on PMLR: https://t.co/exSXOOGLo8 โ€” thanks to the entire community! We also have some exciting updates about the next edition of LoG, coming soon... โŒ›๏ธ
0
15
94
@Zhu_Yanqiao
Yanqiao ZHU
2 years
Great work on scaling pretrained GNNs for molecular graphs! Our previous work ( https://t.co/RFB0UBiCh8) also studied the neural scaling behaviors by analyzing the impact of data quantity and quality on molecular representations.
Tweet card summary image
arxiv.org
Molecular Representation Learning (MRL) has emerged as a powerful tool for drug and materials discovery in a variety of tasks such as virtual screening and inverse design. While there has been a...
@gklambauer
Gรผnter Klambauer
2 years
On the Scalability of GNNs for Molecular Graphs "Scaling laws for GNNs" This is about activity/property prediction: - Pre-training on more molecules helps When you read the paper, keep in mind: SOTA for most tasks is descriptors+xgboost (Fig 4). P: https://t.co/ZajR1LfWuP
0
0
13