📚 Journal club on discrete diffusion models 🎥 Replays available on YouTube! Contact: [email protected] Hosted by @ssahoo_, @jdeschena, @zhihanyang_
Joined August 2025
- Tweets270
- Following0
- Followers2.4K
- Likes255
Pinned Tweet
Drowning in the sea of Discrete Diffusion papers? 🌊
We got you.
Join our Reading Group!
From theory → empirics, and language → molecules — we’ll decode the chaos together 💫
Join the cult—uh, I mean community 😇
👉 Google Group: groups.google.com/g/diffusio…
(1 / 2)
Paper link: arxiv.org/abs/2609.35553
Discrete Diffusion Reading Group retweeted
Join our reading group next Monday!
Topic: Simplex Diffusion Models
Presenter: Justin Deschenaux
This Monday, Oct 19, Justin Deschenaux (@jdeschena) will present his paper:
Simplex Diffusion Models
This Monday, Oct 19, Justin Deschenaux (@jdeschena) will present his paper:
Simplex Diffusion Models
Diffusion-LLMs go mainstream 🚀
We added Uno training to NeMo AutoModel.
The neat idea: let the model draft for itself, then verify with the original AR model — no separate draft model needed.
Our Qwen3-0.6B run gets ~2 committed tokens per forward on GSM8K and 1.84 on HumanEval.
PR: github.com/NVIDIA-NeMo/Autom…
cc @IFM_AI @ssahoo_
Thanks @krasul and @Chonghan_Liu for getting this in 🙏
Discrete Diffusion Reading Group retweeted
Really excited to see Uno-adapters incorporated into @nvidia -Nemo
Thanks @huiying_lii @krasul @Chonghan_Liu
Learn more about Uno: xitter.cf/ssahoo_/status/2095741…
We added Uno training to NeMo AutoModel.
The neat idea: let the model draft for itself, then verify with the original AR model — no separate draft model needed.
Our Qwen3-0.6B run gets ~2 committed tokens per forward on GSM8K and 1.84 on HumanEval.
PR: github.com/NVIDIA-NeMo/Autom…
cc @IFM_AI @ssahoo_
Thanks @krasul and @Chonghan_Liu for getting this in 🙏
Missed the talk? Check out the recording on YouTube: youtu.be/STCXPRaO3L4
Discrete Diffusion Reading Group retweeted
Join our reading group next Monday!
Topic: Gumbel Straight Flow: Distilling Autoregressive Models into One-Step Flow Maps
Presenter: Yeongmin Kim
This Monday, Oct 12, Yeongmin Kim will present his paper:
Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps
✈️ Discrete Diffusion Meetup @COLM_conf
📅 Oct 8, 4-5 PM
📍Grand Ballroom, 3rd Floor
If you’re into discrete diffusion, come hang out, talk shop, and meet others working in the space.
hosts: @ssahoo_ @zhihanyang_
Missed the talk? Check out the recording: youtu.be/xZ7b-mS3SXc
This Monday, Oct 5, @ayhozade will present his paper:
MUX: Continuous Reasoning via Multiplexed Tokens
Discrete Diffusion Reading Group retweeted
Excited to share my work during summer internship at NVIDIA! We build the first large-scale continuous dLLM, reaching comparable and even better performance compared with masked dLLM trained under aligned budgets, and discover interesting properties its continuous dynamics!
💫 Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
📈 Comparable with discrete dLMs and AR on math and coding
🎛️ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
Discrete Diffusion Reading Group retweeted
💫 Large Language Continuous Diffusion Models
Presenting Sigma, the first large-scale (3B/8B) continuous diffusion LM (dLM) trained with likelihood.
📈 Comparable with discrete dLMs and AR on math and coding
🎛️ Enables meaningful study of inference-time interventions
Jointly led with Wei Guo (@WeiGuo01), Jean-Marie Lemercier (@jm_lemercier), Simon Welker (@_cobalamin)
Team: @YongganFu @mmkamani7 Sajad Norouzi @julberner @tomasgeffner @karsten_kreis @YongxinChen1 @MoleiTaoMath @jwthickstun @PavloMolchanov Ante Jukic @ArashVahdat @MardaniMorteza
This Monday, Oct 5, @ayhozade will present his paper:
MUX: Continuous Reasoning via Multiplexed Tokens
Discrete Diffusion Reading Group retweeted
I’ll be speaking at the EDPM workshop about our recent paper:
“Unlocking Lossless Speedups in LLMs via Discrete Diffusion.”
📅 October 7, 10:50–11:30 AM
In NYC until October 7. Reach out if you’d like to meet up and talk shop!
Register for the Zoom Link: simonsfoundation.zoom.us/web…
Diffusion LLMs have two limitations relative to AR models:
(1) Lower quality, and
(2) Slower inference at large batch sizes.
We address this "Uno"
> Retains the AR architecture of LLMs
> Each layer has two sets of weights: AR weights and Diffusion weights
> Diffusion weights enable parallel sampling from the AR distribution losslessly
Results:
💥Faster than all speculative decoding methods: DFlash and EAGLE-3
🔥 Beats ALL diffusion LLMs: Mercury 2, Diffusion Gemma, Llada
Links to the paper, models, code below
Missed the talk? Check out the recording on YouTube: youtube.com/watch?v=hfM0ULRC…
This Monday, Sep 28, @_sophia_tang_ will present her paper:
Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
