News (Page 2) | Liquid AI
Publications
- AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization (03.02.2026)
- Low-Pass Flow Matching (03.02.2026)
- Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models (01.26.2026)
- Learning residue level protein dynamics with multiscale Gaussians (01.26.2026)
- The Curious Case of In-Training Compression of State Space Models (01.26.2026)
- Zero-Overhead Introspection for Adaptive Test-Time Compute (01.26.2026)
- LFM2 Technical Report (12.01.2025)
Models
- LFM2-24B-A2B: Scaling Up the LFM2 Architecture (02.24.2026)
- LFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB (01.20.2026)
- The Future of Meeting Summarization: Local, Fast, Private, and Fully Secure (01.07.2026)
- Introducing LFM2.5: The Next Generation of On-Device AI (01.05.2026)
- LFM2-ColBERT-350M: One Model to Embed Them All (10.28.2025)
- LFM2-VL-3B: A New Efficient Vision-Language for the Edge (10.22.2025)
- LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts (10.07.2025)
News
- From Cloud to AI PC: Launching Liquid’s Largest LFM2 Model Alongside Our Growing Partner Ecosystem (02.24.2026)
- The Future of AI Isn't Just Bigger; It’s Specialized and Hybrid (01.14.2026)
- Introducing Liquid Labs: Defining the Frontier of Intelligence through Innovation (12.04.2025)
- Liquid AI Announces Multi‑Year Partnership with Shopify to Bring Sub‑20ms Foundation Models to Core Commerce Experiences (11.13.2025)
- Agentic Robotics at the Edge: Liquid AI, AMD, and Robotec.ai Demonstrate LFM2-VL-3B in Embedded Autonomy (10.23.2025)
External Articles
- The case for liquid foundation models (01.21.2026)
- MIT offshoot Liquid AI releases blueprint for enterprise-grade small-model training (12.01.2025)
- Driving intelligent automotive manufacturing: how robotics and AI are transforming OEM operations (11.26.2025)
- AI Factories - Data Centers of the Future (11.21.2025)
- The “Humanity” Hack: How One MIT Scientist Is Rewiring Robots To Beat Big Tech (10.31.2025)
- Ramin Hasani, Liquid AI | theCUBE +NYSE Wired: AI Factories - Data Centers of the Future (10.21.2025)
- Liquid AI Releases LFM2-8B-A1B: An On-Device Mixture-of-Experts with 8.3B Params and a 1.5B Active Params per Token (10.10.2025)