🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Our FreedomIntelligence (github.com/FreedomIntelli…) ranks the 14th and the number of total dataset likes ranks the 6th. Keep open and contribute to the community!

Thanks for sharing, we are ranking 14th.

For those attending the EMNLP 2023 who have not yet secured their accommodations, we are delighted to inform you that rooms are still available at Hotel Ora!🛏️🏨 Booking by this link: idem.events/r/emnlp-confer… #EMNLP2023 #NLProc

Designed by our team

ALLaVA: Harnessing GPT4V-synthesized Data for A Lite Vision-Language Model Collects and open-sources the largest (4 mil) GPT-4V dataset for VLM training, which consists of fine-grained captions, complex instructions and detailed answers arxiv.org/abs/2402.11684

[CL] ALLaVA: Harnessing GPT4V-synthesized Data for A Lite Vision-Language Model arxiv.org/abs/2402.11684 The article presents the ALLaVA model, which trains a lite vision-language model using a high-quality dataset synthesized by GPT-4V to address the computational resource

MathScale Scaling Instruction Tuning for Mathematical Reasoning Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate.

This is the multilingual verision of HuatuoGPT.

Our first try on Operations Research using large languaage models. It performs better than GPT-4 in solving real-world Operations problems.

🔥Today, we announce the #MotionLLM💃, an LLM-based motion/video model for human behavior understanding! 📖Paper: arxiv.org/pdf/2405.20340 🏠Project page: lhchen.top/MotionLLM 🤗Demo: demo.humotionx.com ✍️Blogpost: research.lhchen.top/blogpost/motio… 💻Code: github.com/IDEA-Research/…

The first official version for multi-modal HuatuoGPT, we nearly open source eveything.

Two Papers Accepted in COLM 2024. The medical LLM "HuatuoGPT-2" (arxiv.org/abs/2311.09774) surpassed GPT-4 and many other LLMs at the time and the knowledge injection was quite distinctive. MileBench (arxiv.org/abs/2404.18532) has sounded the horn for long-context multimodal LLMs.

Medical LLMs for more languages

HuatuoGPT-o1 Towards Medical Complex Reasoning with LLMs

🚀 Excited to share TwinMarket! A scalable multi-agent framework using LLMs to simulate financial markets & emergent behavior 🎯📈 #Agent #LLM #Social 📄 Read more: huggingface.co/papers/2502.01…

What are the best AI tools for research? Nature’s guide nature.com/articles/d4158… I discuss a little bit on deployment-efficient DeepSeek and o1/R1 -like reasoning for complex diagnosis.

If you're also interested in: AI + social simulation，multi-agent systems, please attend the Financial AI Workshop@ICLR on 4.28 at 11:40 a.m., Hall 4 #2. We will present our latest research: TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets.

Learning from Peers in Reasoning Models Large Reasoning Models often get stuck when they start reasoning incorrectly (the "Prefix Dominance Trap"). Propose LeaP (Learning from Peers), a method where parallel reasoning paths share intermediate summaries to learn from each other

ShareGPT-4o-Image Aligning Multimodal Models with GPT-4o-Level Image Generation