Pan Lu (@lupantech) / X

Pan Lu

1,179 posts

Pan Lu

@lupantech

Postdoc @Stanford @stanfordnlp | PhD @CS_UCLA @uclanlp Amazon/Bloomberg/Qualcomm Fellows | Ex @Tsinghua_Uni @Microsoft | Eubiota/AgentFlow/MathVista/ScienceQA

Palo Alto

Joined April 2016

Pinned
Pan Lu
@lupantech
Apr 21
Excited to share that AgentFlow has been selected as an ICLR 2026 Oral 🎉 agentflow.stanford.edu Since launch, AgentFlow has also grown to 1.7K GitHub stars. Thank you so much for the support. AgentFlow is a trainable multi-agent system where specialized agents learn to plan
Pan Lu
@lupantech
Oct 8, 2025
🔥Introducing #AgentFlow, a new trainable agentic system where a team of agents learns to plan and use tools in the flow of a task. 🌐agentflow.stanford.edu 📄huggingface.co/papers/2510.05… AgentFlow unlocks full potential of LLMs w/ tool-use. (And yes, our 3/7B model beats GPT-4o)👇
19K
Pan Lu
@lupantech
Oct 8, 2025
🔥Introducing #AgentFlow, a new trainable agentic system where a team of agents learns to plan and use tools in the flow of a task. 🌐agentflow.stanford.edu 📄huggingface.co/papers/2510.05… AgentFlow unlocks full potential of LLMs w/ tool-use. (And yes, our 3/7B model beats GPT-4o)👇
137K
Pan Lu
@lupantech
Mar 29, 2023
🔥Excited to release LLaMA-Adapter! With only 1.2M learnable parameters and 52K instruction data, LLaMA-Adapter turns a #LLaMA into an instruction-following model within ONE hour, delivering high-quality responses! 🚀Paper: arxiv.org/abs/2303.16199 🚀Code: github.com/ZrrSkywalker/L…
117K
Pan Lu
@lupantech
Jun 1, 2023
🔥Thrilled to release LLaMa-Adapter Multimodal! 🎯Now supporting text, image, audio, and video inputs powered by #ImageBind. 🧵6 💻Codes for inference, pretraining, and finetuning ➕ checkpoints: github.com/ZrrSkywalker/L… demo: llama-adapter.opengvlab.com abs: arxiv.org/abs/2304.15010
103K
Pan Lu
@lupantech
Jun 12, 2023
🎉Exciting news: LLaMA-Adapter is now fully unlocked! 🧵6 1⃣ As a general-purpose #multimodal foundation model, it integrates various inputs like images, audio, text, video, and 3D point clouds, while providing image, text-based, and detection outputs. It uniquely accepts the
212K
Pan Lu
@lupantech
May 13, 2024
🚨 BREAKING: @OpenAI's new GPT-4o model outperforms humans on MathVista for the first time! 📊 Scores: Human avg: 60.3 GPT-4o: 63.8 📖 Learn more: OpenAI : openai.com/blog/gpt-4o/ MathVista: mathvista.github.io
OpenAI
@OpenAI
May 13, 2024
We're opening up access to our new flagship model, GPT-4o, and features like browse, data analysis, and memory to everyone for free (with limits). openai.com/index/gpt-4o-a…
480K
Pan Lu
@lupantech
Jul 31, 2023
🚀Introducing #LLaMA2-Accessory - an advanced open-source toolkit for large language models. Evolved from LLaMA-Adapter, we now support more datasets, tasks, visual encoders, and efficient optimization methods.🧠 🔗Code: github.com/Alpha-VLLM/LLa… 💡Key Features: 🎯 Pre-training
77K
Pan Lu
@lupantech
Feb 19, 2025
🐙 Introducing OctoTools: an agentic framework with extensible tools for complex reasoning! 🚀 🧵 🔗 Explore now: octotools.github.io OctoTools tackles challenges in complex reasoning—including visual understanding, domain knowledge retrieval, numerical reasoning, and
251K
Pan Lu
@lupantech
Aug 15, 2024
🚀 Truly impressed by the remarkable progress from @xai! Grok-2 and Grok-2 mini now hold the top two spots on #MathVista (mathvista.github.io/#leaderboard)! Even more impressive is the rapid boost by @xai, raising the Grok series' scores from 52.8% to 69% in just 4 months. Respect! 👏
41K
Pan Lu
@lupantech
Apr 28, 2023
🚀65B LLaMA-Adapter-V2 code & checkpoint are NOW ready at github.com/ZrrSkywalker/L…! 🛠️Big update enhancing multimodality & chatbot. 🔥LLaMA-Adapter-V2 surpasses #ChatGPT in response quality (102%:100%) & beats #Vicuna in win-tie-lost (50:14). ☕️Thanks to Peng Gao & @opengvlab! 2/2
00:00
89K
Pan Lu
@lupantech
Dec 21, 2022
🎉New paper! The survey of deep learning for mathematical reasoning (#DL4MATH) is now available. We've seen tremendous growth in this community since 2018, and this review covers the tasks, datasets, and methods from the past decade. Check it out now: arxiv.org/abs/2212.10535
53K
Pan Lu
@lupantech
Oct 25, 2023
🚀Excited to release our 112-page study on math reasoning in visual contexts via #MathVista. For the first time, we provide both quantitative and qualitative evaluations of #GPT4V, #Bard, & 10 other models. 📄✨Full paper: lupantech.github.io/papers/arxiv23… 🔗Proj: mathvista.github.io
85K
Pan Lu
@lupantech
Apr 26, 2023
LLaMA-Adapter V2, the next-gen multi-modal instruction model, boasts a model size multiple times larger than 7B! 🌟🔥 Chatbot systems, get ready for a major upgrade! 🤖💬 Stay tuned! Technical report & models coming soon. 📄🔜Keep up to date! 🔗github.com/ZrrSkywalker/L…
57K
Pan Lu
@lupantech
May 17, 2024
Congrats, @JeffDean @GoogleDeepMind! Gemini 1.5 Pro has shown substantial improvements from Feb to May, scoring 63.9% on our #MathVista (mathvista.github.io), outperforming humans and GPT-4o, which was out 4 days ago!🚀 AI Progress has never been this rapid and impressive!🌟
Jeff Dean
@JeffDean
May 17, 2024
Gemini 1.5 Model Family: Technical Report updates now published In the report we present the latest models of the Gemini family – Gemini 1.5 Pro and Gemini 1.5 Flash, two highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information
73K