🔥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

State space models are awesome, but the usually used pre-training scheme really clips their wings. Checkout Birdie, which really helps SSMs perform much much better on several tasks! More details and paper/code links here👇

New Liquid research: STAR -- Evolutionary Synthesis of Tailored Architectures. At Liquid we design foundation models with two macro-objectives: maximize quality and efficiency. Balancing the two is challenging. To make progress towards this goal, we built a new algorithm — STAR.

Check out our NeurIPS Conference paper that explores the connections between parallelizing *nonlinear* RNNs and Newton's method. Paper: arxiv.org/abs/2407.19115 With Xavier Gonzalez, a.w., and Scott Linderman. See Scott's thread below for more details.

So excited by our latest NeurIPS Conference paper on parallelizing nonlinear RNNs! With my amazing collaborators a.w., Jimmy Smith, and Scott Linderman. We are building on the beautiful DEER algorithm by YH Lim, Muhammad Firmansyah Kasim, et al. (arxiv.org/abs/2309.12252). Thread below!

I'm excited to share our #NeurIPS2024 paper, "Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems" 🧠✨ We introduce the gpSLDS, a new model for interpretable analysis of latent neural dynamics! 🧵 1/10

Presenting our paper today (Thursday) at NeurIPS at 11am! East Exhibit Hall A-C #4402 Stop by if you want to learn about our insights on weight space geometry, loss landscapes, model merging etc. Reach out to me if you want to chat about anything else at NeurIPS too!

I was sadly unable to make the trip to #NeurIPS2024 this year, but check out our poster #2010 with Xavier Gonzalez during the 11 am-2pm session! Poster info: neurips.cc/virtual/2024/p…

Also check out or new blog post!

We are announcing our Series A led by AMD Ventures! It is a privilege to work with such an amazing team. More to come soon!

🥳 Super happy to share the new model I've been working on: LFM-7B LFM-7B was designed for exceptional multilingual chat capabilities, including Arabic and Japanese. It's by far our best post-training piece to date at Liquid AI.

Excited to share LFM-7B! Incredibly proud of the strong work of our Liquid AI team.

Proud to have Liquid AI as TreeHacks' 2025 Official Edge AI Track Sponsor! 🧵 for prizes ->

🤏 Can small models be strong reasoners? We created a 1B reasoning model at Liquid AI that is both accurate and concise We applied a combination of SFT (to raise quality) and GRPO (to control verbosity) The result is a best-in-class model without specific math pre-training

Liquid AI open-sources a new generation of edge LLMs! 🥳 I'm so happy to contribute to the open-source community with this release on Hugging Face! LFM2 is a new architecture that combines best-in-class inference speed and quality into 350M, 700M, and 1.2B models.

We are excited to release our first open-weight LFM models, optimized for on-device deployments. Extremely proud of the entire team! Check them out here: huggingface.co/LiquidAI

Try LFM2 with llama.cpp today! We released today a collection of GGUF checkpoints for developers to run LFM2 everywhere with llama.cpp Select the most relevant precision for your use case and start building today. huggingface.co/LiquidAI/LFM2-…

LFM2-350M running on a Raspberry Pi ... with 42 tokens per second 🚀 (238 tokens per second prefill)

Trying out LFM2 350M from Liquid AI and was mind-blown 🤯 The responses were very coherent. Less hallucinations compared to models of the same size. Very well done!! The best part: Q4_K_M quantization is just 230 Megabytes, wow!

Extremely excited for our release of LEAP and Apollo. Our solutions for making it easy to develop apps powered by local LLMs. Check it out!

Finally, a dev kit for designing on-device, mobile AI apps is here: Liquid AI's LEAP venturebeat.com/business/final…