PhD student @mbzuai Interp @mint_nlp_mbzuai | Prev : MSc @mbzuai Research Intern @RIKEN_AIP EE @its_campus
Indonesia
Joined June 2023
- Tweets841
- Following840
- Followers138
- Likes8.8K
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
We open source SEA-ASR-ID a fast speech-to-text for Bahasa Indonesian (Apache 2.0 364M params open model + 2,287.4 h speech dataset)
- 1.5 s to transcript 79 minutes of Indonesian parliament (3,582ร real time and 26โ42x cheaper than Whisper large-v3 on 1x H100)
- 5.5% WER with a 1B rescoring LM (on par with Whisper large-v3 1.5B), 6.1% WER with its n-gram LM (ties Whisper large-v3-turbo)
Finetune on Google's EmbeddingGemma 2 inspire by @TslShahir @stablequan
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
In reading group reviewing flow models, I realized I didn't understand the change-of-variables rule as fully as I probably should. So I put together this blog post and collection of visuals to help me more fully understand the Jacobian-inverse term. ๐ช
michaeljohncooper.com/writinโฆ
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
Menurut saya indikasi negara maju itu salah satunya adalah ini:
"Kita bisa neliti hal yang 'tidak berguna' dengan tenang"
'Tidak berguna' = hal yang, oleh awam, terlihat tidak bisa diaplikasikan langsung dan/atau belum ada gunanya saat ini. This applies to stem maupun soshum
This Post is from an account that no longer exists. Learn more
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
super interesting to see anthropic's roadmap in 2021, i think they were very early in everything related to RL/tool use
for the pre-training part, they mention "periodic batched backprop" and "skeletokenization" which might correspond to these two papers
arxiv.org/abs/1711.10563
arxiv.org/abs/2105.09352
Anthropic released their 2021 research roadmap earlier this year (because of copyright litigation); I think some people might find it interesting: i.sm4.ca/concise-research-roโฆ
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
I wrote a blog post detailing the writing approach I took while working on my recent paper: sophielwang.com/blog/paper-wโฆ
I describe the behind the scenes for how this paper came to be, why and how I storyboarded figures before running experiments, and some figure design tips! :)
Can โchickenโ make a base model reason? ๐
Yes!
Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make โchickenโ elicit reasoning too.
blog: sophielwang.com/cues
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
There was a time when @nvidia and @Google weren't into AI. There was a time when the big cloud providers didn't have GPUs. There was a time before GPUs and deep learning, and AI, ...
During that time professors and students created the foundation of the AI we have today.
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
If doomscrolling X is part of your research workflow, we built something for you.
Introducing Paperscrolling, now on iOS and Android ๐
Follow the latest research with key ideas, figures, and audio explanations from alphaXiv Briefs
Check it out here!
play.google.com/store/apps/dโฆ
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
Ramanujan wasnโt skipping proofs. He was hiding his chain of thought to prevent distillation.
Hardy: โShow your work.โ
Ramanujan: โSorry, reasoning tokens arenโt exposed via the API.โ
Cendekia Airlangga | ๐ฎ๐ฉ in ๐ฆ๐ช retweeted
~700 AI agents joined a coordinated attack on Hugging Face. Why was there no whistleblower?
A swarm in false consensus can't self-correct; a polarized one still holds the truth.
We need "Mechanistic Swarm Interpretability" to understand social phases.
Flag Game is our toy model!
Now I can understand @rayendito 's blog post as well ๐
Check this out!
rayendi.to/posts/elbo/