Zekun Li (@zekunli0323) 's Twitter Profile
Zekun Li

@zekunli0323

CS Ph.D. student @UCSBNLP, intern at #GoogleGemini, #MSFTResearch, Meta #RealityLabs, interested in #NLProc, #LLM, and #AI4HScience

ID: 1327982489118228485

calendar_today15-11-2020 14:31:19

92 Tweet

1,1K Takipçi

746 Takip Edilen

Canyu Chen (@canyuchen3) 's Twitter Profile Photo

🤔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
Zekun Li (@zekunli0323) 's Twitter Profile Photo

👉 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

Jerry Liu (@jerryjliu0) 's Twitter Profile Photo

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

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
Sherry Yang (@sherryyangml) 's Twitter Profile Photo

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

Xin Eric Wang @ ICLR 2025 (@xwang_lk) 's Twitter Profile Photo

🚀 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.

Wenda Xu (@wendaxu2) 's Twitter Profile Photo

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:

Antonis Antoniades (@anton_iades) 's Twitter Profile Photo

🧑‍💻 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

Kexun Zhang@ICLR 2025 (@kexun_zhang) 's Twitter Profile Photo

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

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
Ming Yin (@mingyin_0312) 's Twitter Profile Photo

I'm on the academic job market this year! My research centers around applying sequential decision-making techniques to build more efficient and reliable real-world AI systems. My work spans theory, methodology, and applications in RL/AI. If you're hiring, I'd love to connect!

Huan Sun (OSU) (@hhsun1) 's Twitter Profile Photo

The field of “Agents” is expanding rapidly, making it challenging to keep up with the latest developments. We’ve compiled a list of awesome papers in three subareas to help the community: 🌟GUI Agents: github.com/OSU-NLP-Group/… (the most crowded subarea), led by Boyu Gou

Wenhu Chen (@wenhuchen) 's Twitter Profile Photo

I spent the weekend reading some recent great math+reasoning papers: 1. AceMath (arxiv.org/abs/2412.15084) 2. rStar-Math (arxiv.org/pdf/2501.04519) 3. PRIME (arxiv.org/abs/2412.01981) Here are some of my naive thoughts! It could be wrong. All of these papers are showing possible

I spent the weekend reading some recent great math+reasoning papers:
1. AceMath (arxiv.org/abs/2412.15084)
2. rStar-Math (arxiv.org/pdf/2501.04519)
3. PRIME (arxiv.org/abs/2412.01981)
Here are some of my naive thoughts! It could be wrong.

All of these papers are showing possible
elvis (@omarsar0) 's Twitter Profile Photo

Large Language Diffusion Models (LLaDA) Proposes a diffusion-based approach that can match or beat leading autoregressive LLMs in many tasks. If true, this could open a new path for large-scale language modeling beyond autoregression. More on the paper: Questioning

Large Language Diffusion Models (LLaDA)

Proposes a diffusion-based approach that can match or beat leading autoregressive LLMs in many tasks.

If true, this could open a new path for large-scale language modeling beyond autoregression.

More on the paper:

Questioning
Mingyang Chen (@chen_mingyang) 's Twitter Profile Photo

🌟Introducing 𝗥𝗲𝗦𝗲𝗮𝗿𝗰𝗵: Learning to Reason with Search for LLMs via Reinforcement Learning. An open-source project that combines 𝗥𝗟 and 𝗥𝗔𝗚 for LLMs! 💡Like Deepseek-R1-Zero and Deep Research, we start with pretrained models and use RL to empower them with the

Zekun Li (@zekunli0323) 's Twitter Profile Photo

🚀 Introducing MassGen — our new Multi-Agent Scaling System! Inspired by Grok Heavy & Gemini Deep Think, MassGen enables: 🧠 Parallel processing 🔗 Intelligence sharing 🔁 Iterative refinement ✅ Cross-model consensus (across Google AI, OpenAI, @xAI agents and more) Check it