@esaliya Profile picture

Saliya Ekanayake

@esaliya

Principal Software Engineer at d-Matrix, Accelerating AI

Joined July 2008
Similar User
Srinath Perera photo

@srinath_perera

Chanaka Jayasena photo

@chanaka3d

CharithWiki photo

@charithwiki

Miyuru Wanninayaka photo

@miyurudw

Saliya Ekanayake Reposted

The reality of the Turing test

karpathy's tweet image. The reality of the Turing test

Saliya Ekanayake Reposted

Easily the most impressive uncut autonomous video I've ever seen, from @physical_int


I created a video to help explain how LLMs work. Hope you'll find it useful! youtube.com/watch?v=6o0Xnl… P.S. Creating videos is hard, but kind of fun experience


Saliya Ekanayake Reposted

Hi all prospective grad students! Our Equal Access to Application Assistance (EAAA) program for @Berkeley_EECS is now accepting applications! Any PhD applicant to @Berkeley_EECS can submit their application for feedback by Oct. 6th 11:59PM PST forms.gle/rYVtXyaE9qE8ug…


This seems like a cool research place to join mlcollective.org/?s=09


Saliya Ekanayake Reposted

Real2Code -- translating real-world articulated objects to sim using code generation! With the code representation, this method scales well wrt the number of object parts, check out the 10-drawer table it reconstructed 😉

Here’s something you didn’t know LLMs can do – reconstruct articulated objects! Introducing Real2Code – our new real2sim approach that scalably reconstructs complex, multi-part articulated objects. arxiv.org/abs/2406.08474



Saliya Ekanayake Reposted

Llama3 8B and 70B are out, with pretty exciting results! * The ~400B is still training but results already look promising. * Meta's own Chat interface is also live at meta.ai * TorchTune integration is shortly going live: github.com/pytorch/torcht…

It’s here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs. Key highlights • 8B and 70B parameter openly available pre-trained and fine-tuned models. • Trained on more…

Ahmad_Al_Dahle's tweet image. It’s here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs.

Key highlights

  • 8B and 70B parameter openly available pre-trained and fine-tuned models.
  • Trained on more…


Saliya Ekanayake Reposted

It's been a wild ride. Just 20 of us, burning through thousands of H100s over the past months, we're glad to finally share this with the world! 💪 One of the goals we’ve had when starting Reka was to build cool innovative models at the frontier. Reaching GPT-4/Opus level was a…

Meet Reka Core, our best and most capable multimodal language model yet. 🔮 It’s been a busy few months training this model and we are glad to finally ship it! 💪 Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core thinks of the 3 body…



Totality 2024!

esaliya's tweet image. Totality 2024!

Saliya Ekanayake Reposted

Speedup Open-Sora's training by 3x and inference by 2x with our novel DSP (Dynamic Sequence Parallelism)! For 10s 512x512 videos, Open-Sora's inference time: 1xH800: 106s 8xH800: 45s 8xH800+DSP: 22s DSP can be seamlessly adapted to all multi-dimensional transformers, unlocking…

YangYou1991's tweet image. Speedup Open-Sora's training by 3x and inference by 2x with our novel DSP (Dynamic Sequence Parallelism)! For 10s 512x512 videos, Open-Sora's inference time:
1xH800: 106s
8xH800: 45s
8xH800+DSP: 22s

DSP can be seamlessly adapted to all multi-dimensional transformers, unlocking…

Saliya Ekanayake Reposted

1/ Given high-dim time series data (e.g., video, text), we'd like to know "what happens in the future?" and "what happened between A and B?" Turns out temporal contrastive learning provably answers these questions! Paper+Code: arxiv.org/abs/2403.04082 Backstory and details below

ben_eysenbach's tweet image. 1/ Given high-dim time series data (e.g., video, text), we'd like to know "what happens in the future?" and "what happened between A and B?" Turns out temporal contrastive learning provably answers these questions!

Paper+Code: arxiv.org/abs/2403.04082
Backstory and details below

I didn't know people go to the toilet to just flush toilet tissue -- must be some fun game even my kids would love

esaliya's tweet image. I didn't know people go to the toilet to just flush toilet tissue -- must be some fun game even my kids would love

cmd+shift+A is the best thing I found in a long while -- it allows to search open tabs in the browser :)

esaliya's tweet image. cmd+shift+A is the best thing I found in a long while -- it allows to search open tabs in the browser :)

Saliya Ekanayake Reposted

New Resource: Foundation Model Development Cheatsheet for best practices We compiled 250+ resources & tools for: 🔭 sourcing data 🔍 documenting & audits 🌴 environmental impact ☢️ risks & harms eval 🌍 release & monitoring With experts from @AiEleuther, @allen_ai,…


PawboTax consultant

esaliya's tweet image. PawboTax consultant

Proof that I am from the future

esaliya's tweet image. Proof that I am from the future

My work buddy

esaliya's tweet image. My work buddy

United States Trends
Loading...

Something went wrong.


Something went wrong.