🥳Updated the reading list for two fact-checking survey papers (TACL22/EMNLP23). Repo: github.com/Cartus/Automat… 🙌If you are interested in factuality/multimodal/LLM/misinformation, check out our 800+ paper list. Feel free to add more related works to our repo!

Super excited to finally share what I have been working on at OpenAI! o1 is a model that thinks before giving the final answer. In my own words, here are the biggest updates to the field of AI (see the blog post for more details): 1. Don’t do chain of thought purely via

🚀 Join us for the EMNLP 2024 Online Paper Sharing Event hosted by NICE & Soochou University AI Lab! 🤖📚 📅 Tentative Date: Mid-October 🔗 Sign-up: docs.qq.com/form/page/DU1J… 🌐 NICE Homepage: nice-nlp.github.io The event will be conducted in Chinese. Don’t miss out! 🔥

从互联网诞生以来，几乎所有成功的公司就是在信息的匹配、分发上进行了全局或局部的革命，而信息的产生和加工还是主要由人工进行。 大模型诞生之后，未来AI很可能会在信息的加工和产生上出现革命性的影响，也可能是AI未来最大的颠覆性。

🔔 new 𝗔𝗴𝗲𝗻𝘁-𝗮𝘀-𝗮-𝗝𝘂𝗱𝗴𝗲 paper: 𝗖𝗮𝗻 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗮𝘀 𝗲𝗳𝗳𝗲𝗰𝘁𝗶𝘃𝗲𝗹𝘆 𝗮𝘀 𝗵𝘂𝗺𝗮𝗻𝘀? 𝗬𝗲𝘀, 𝘁𝗵𝗲𝘆 𝗰𝗮𝗻! 📄 arxiv.org/abs/2410.10934… 👨‍💻 github.com/metauto-ai/age… Introducing 𝗔𝗴𝗲𝗻𝘁-𝗮𝘀-𝗮-𝗝𝘂𝗱𝗴𝗲, a

Happy to share our recent work on LLM/Agent personalization. Our AI Persona framework shed lights on how to effectively infer user profiles and continually update user profiles using human-AI interactions.

🎉Introducing our latest work on GUI Agents: "OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis" TLDR: We build an interaction-driven pipeline for synthesizing high-quality and diverse GUI agent trajectory data through reverse Task Synthesis.

⛄️Excited to share our work on causal analysis of LLMs at COLING 2025!💖Hongbo Linyi Yang Cunxiang Wang "How Likely Do LLMs with CoT Mimic Human Reasoning?" Paper: arxiv.org/pdf/2402.16048

很荣幸全程参与了在lmarena中位列Top9的新Zhipu GLM的诞生过程。不过如果能早几天出结果就更好了🤣 Honored to fully participate in the birth of the new Zhipu GLM, which ranks Top 9 in lmarena. But if would be better to see the results a few days earlier (before the new Qwen-max)🤣

Diving into the world of LLM agents! 🚀 Starting today, I'll share insights from the newest and sharpest papers I read. The agentic AI wave is rising—2025-2026 will be game-changing. Let’s explore, learn, and shape the future together! 🔥 #LLM #AgenticAI

Prospective PhD applicants: if you want me as your supervisor, please submit to dept. of applied science, under which you choose DATA SCIENCE program. I'm NOT in computer science. If you've submitted to CS, I CANNOT see you in our side.

🚀 New name, same mission — ChatGLM is now Z.ai. To mark this new chapter, we’re launching the fully open-source GLM-4-0414 model family under the MIT License — use it, build on it, profit from it. We’re open-sourcing six models across 9B and 32B sizes. Here

New 1.5B embedding and reranking models 🤩 !!! New choice between Qwen3-embedding-0.6B and 4B We release **Lychee-embed** and **Lychee-rerank**, based-on Qwen2.5-1.5B and our multi-stage training framework in COLM 2025 paper. #NLP #LLM #RAG #COLM2025

GLM-4.5 ranks at No.2 when "remove style control". lmarena.ai/leaderboard/te…

increadable

We are developing the next version of GLM. What features do you want the most?

All top open-weight models are now Chinese

A Chinese AI model just shattered our assumptions about the AI market. GLM-4.6 recorded the fastest adoption curve we've seen: 168 million → 15.9 billion tokens in 12 days. That's 94x growth. Here's why every developer needs to pay attention 🧵

GLM 4.6 #1 open model