Zekun Li on the job market!
@ZekunLi0323CS Ph.D. student @UCSBNLP, intern at #GoogleGemini, #MSFTResearch, Meta #RealityLabs, interested in #NLProc, #LLM, and #AI4HScience
Similar User
@jefffhj
@zhangzhuosheng
@wangchunshu
@shizhediao
@muhao_chen
@hanjie_chen
@yuz9yuz
@acbuller
@ucsbNLP
@SinclairWang1
@xc_feng
@TianbaoX
@huyushi98
@DrogoKhal4
@Yulongchen1010
🚨 Introducing “MMSci: A Multimodal Multi-Discipline Dataset for PhD-Level Scientific Comprehension” arxiv.org/abs/2407.04903 🧐Have current multimodal LLMs achieved PhD-level intelligence across diverse scientific disciplines? Are they ready to become AI scientific assistants?…
🧑💻 Human software engineers constantly re-evaluate their approaches through experience. 🤖 However, LLM-based software agents can often get stuck in ineffective dead ends. Introducing SWE-Search: a multi-agent framework integrating search and self-refinement to enable software…
Everyone talks about scaling inference compute after o1. But how exactly should we do that? We studied compute allocation for sampling -- a basic operation in most LLM meta-generators, and found that optimized allocation can save as much as 128x compute! arxiv.org/abs/2410.22480
I am on job market for full-time industry positions. My research focuses on text generation evaluation and LLM alignment. If you have relevant positions, I’d love to connect! Here are list of my publications and summary of my research:
🚀 Since its invention, the mouse has been our way to control computers. But what if it didn’t have to be? 🤔 Thrilled to introduce Agent S, a new state-of-the-art GUI agent framework that interacts with computers just like a human and takes on the toughest automation challenges.…
Checkout Generative Hierarchical Materials Search (GenMS) – a framework for generating crystal structures from natural language. Website: generative-materials.github.io Paper: arxiv.org/abs/2409.06762
I made a multi-agent system for multimodal retrieval and report generation 🎨 - check it out! 👇 Have talked to a lot of users recently that are interested in using agents to build the final document instead of getting back a chatbot response. There's a general feeling that this…
Building a Multimodal Report Generation Agent 🤖✍️🎨 Come learn how to automatically produce a multi-agent system that can do research over a multimodal RAG, compile into a knowledge bank, and generate a multimodal report containing interleaving text and images based on an…
👉 Check out our new paper on injecting misinformation and bias into LLMs via knowledge editing, as a new type of safety threat: editing threat. 🧐We found that: (1) Editing attach can inject both commonsense and long-tail misinformation into LLMs. (2) Editing attack can…
🤔Are your open-source LLMs really safe? 🚨It may be injected with misinformation or bias! Our new paper "𝐂𝐚𝐧 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 𝐋𝐋𝐌𝐬 𝐈𝐧𝐣𝐞𝐜𝐭 𝐇𝐚𝐫𝐦?" (Project website: llm-editing.github.io ) sheds light on the emerging challenges of LLMs, especially the…
🤔Are your open-source LLMs really safe? 🚨It may be injected with misinformation or bias! Our new paper "𝐂𝐚𝐧 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 𝐋𝐋𝐌𝐬 𝐈𝐧𝐣𝐞𝐜𝐭 𝐇𝐚𝐫𝐦?" (Project website: llm-editing.github.io ) sheds light on the emerging challenges of LLMs, especially the…
Thrilled to announce our work is accepted to #ACL2024 Main! We’re the first to solve zero-shot DST with Function Call/Tool Use, bridging the gap and achieving remarkable performance with both 7b/13b OSS models and GPT-3.5/4. More results coming soon. Code: github.com/facebookresear…
I'm pleased to announce that we have released the code at: github.com/facebookresear…. Welcome to explore and play with it. You can see what is tracked and generated during the conversation.
Similar observations and insights as discussed in our paper on exploring how various models prioritize system prompts and user instructions and guard against misleading instructions injected in web search results: arxiv.org/abs/2308.10819
Introducing the Instruction Hierarchy, our latest safety research to advance robustness for prompt injections and other ways of tricking LLMs into executing unsafe actions. More details: arxiv.org/abs/2404.13208
Thanks for sharing our work! 🚀 FnCTOD: a method that empowers chat-based LLMs with function-calling abilities, enabling them to handle complex, task-oriented conversations through the appropriate use of tools and API calls (DST, a type of database search API). 🧵 [1/n]
United States Trends
- 1. Rams 23,6 B posts
- 2. Eagles 48,8 B posts
- 3. #BaddiesMidwest 5.661 posts
- 4. #PrizePicksMilly 4.502 posts
- 5. $CUTO 6.924 posts
- 6. #married2med 3.690 posts
- 7. #RHOP 4.863 posts
- 8. AJ Brown 2.735 posts
- 9. #YellowstoneTV 2.072 posts
- 10. Brandon Graham 1.853 posts
- 11. 49ers 38,5 B posts
- 12. Sirianni 2.420 posts
- 13. Dinwiddie 3.142 posts
- 14. That's a TD 3.051 posts
- 15. Raiders 36,7 B posts
- 16. Jared Verse 1.169 posts
- 17. Packers 40,7 B posts
- 18. Niners 8.115 posts
- 19. Cowboys 62,4 B posts
- 20. Nakobe Dean 1.016 posts
Who to follow
-
Jie Huang
@jefffhj -
Zhuosheng Zhang
@zhangzhuosheng -
Wangchunshu Zhou
@wangchunshu -
Shizhe Diao
@shizhediao -
🌴Muhao Chen🌴
@muhao_chen -
Hanjie Chen
@hanjie_chen -
Yu Zhang
@yuz9yuz -
Ziniu Hu
@acbuller -
UC Santa Barbara NLP Group
@ucsbNLP -
Sinclair Wang
@SinclairWang1 -
Xiachong Feng
@xc_feng -
Tianbao Xie
@TianbaoX -
Yushi Hu
@huyushi98 -
Kai Zhang
@DrogoKhal4 -
Yulong Chen
@Yulongchen1010
Something went wrong.
Something went wrong.