Bettina Schlager @_bschlag

Building 3D User Interfaces @Columbia University #XR #3DUI Joined March 2012

Tweets

48
Followers

98
Following

220
Likes

1K

Liquid AI @LiquidAI_

3 weeks ago

Big step for on-device AI: Liquid AI’s Edge Platform, LEAP, now supports @AMD Ryzen™ and Ryzen AI™ processors, bringing powerful, low-latency AI directly to laptops. Here’s what it means for developers and enterprises 🧵

12 34 193 65K 49

Download Image

Bettina Schlager @_bschlag

4 weeks ago

Every time I try an “AI plugin” for Zotero, I’m reminded that dreams and reality are very different things. Would love to see a make a Zotero-Cursor hybrid

0 0 1 92 0

Ramin Hasani @ramin_m_h

2 months ago

we will be having 3 grand hackathons soon at @LiquidAI_ offices in Boston, SF, and Tokyo. This is called “Bohemian Rhapsody, the Liquid edition”. you will build a wild ai agent with a swarm of tiny models to match/surpass frontier models in the real-world app of choice. join…

5 8 66 249K 12

Liquid AI @LiquidAI_

2 months ago

Today, we release LEAP, our new developer platform for building with on-device AI — and Apollo, a lightweight iOS application for vibe checking small language models directly on your phone. With LEAP and Apollo, AI isn’t tied to the cloud anymore. Run it locally when you want,…

12 46 291 1.7M 137

Download Image

Liquid AI @LiquidAI_

2 months ago

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-…

6 36 127 29K 46

Download Image

Liquid AI @LiquidAI_

2 months ago

Today, we release the 2nd generation of our Liquid foundation models, LFM2. LFM2 set the bar for quality, speed, and memory efficiency in on-device AI. Built for edge devices like phones, laptops, AI PCs, cars, wearables, satellites, and robots, LFM2 delivers the fastest…

13 65 300 334K 90

Download Image

Liquid AI @LiquidAI_

11 months ago

LFMs are Memory efficient LFMs have a reduced memory footprint compared to transformer architectures. This is particularly true for long inputs, where the KV cache in transformer-based LLMs grows linearly with sequence length.

5 13 152 20K 14

Download Image

Alan Zucconi @AlanZucconi

3 years ago

In case you are wondering, an empty Unity 2022 URP project is 1.35Gb and counts 32.542 files. 💀

37 43 641 86K 20

Bettina Schlager @_bschlag

3 years ago

I grab the wrong USB-C cable all the time. It should be easier to distinguish between data-only and charging USB.

0 0 1 247 0

jjorge @jjorge

4 years ago

An all-star panel to kick-off #IEEEVR2022

1 5 40 0 1

Download Image

Sonia Cesteros @soniacesteros89

6 years ago

The mysterious and beautiful movement of trees

0 12 28 0 1

Roberto Alonso González Lezcano @robertoglezcano

7 years ago

This is a simple visualization behind the formula to calculate the surface of a sphere

1 45 86 0 0

Bettina Schlager @_bschlag

7 years ago

"Travelling is crucial for a fact-based perspective on our society and the world" - Love the book, the stats and the stories! from @HansRosling @AnnaGapminder @OlaRosling "Factfulness" #BookRecommendations

0 0 4 0 0

Bettina Schlager @_bschlag

7 years ago

Checking out the fire demo from @metaglasses workspace with my buddy, don't be shy.. say hello! #augmentedreality tried Meta2 AR glasses for the first time today, and I gotta say, pretty impressive field of view and occlusion mapping, excited whats going to come the next years!