@osclsd

Building continuous diffusion LMs 🚀 Research Intern @Apple MLR; PhD ML @UniofOxford; previously at @MSFTResearch, @EPFL, @imperialcollege

 Paris, France
olsdavis.github.io/
Joined May 2024
  • Tweets244
  • Following460
  • Followers887
28Media
Continuous Diffusion LMs went from niche to contender this year, but the recipe is shaky: why self-conditioning? How to embed tokens? 🤨 Our new work takes your one-hot flow from 4% to 50% on TinyGSM without self-conditioning, and explores the design space of CDLMs. 🔥🚀 (1/6)
14
54
6
211
17,798
Oscar Davis retweeted
Andrea Miele@andreamiele_9h
🔥 Diffusion LMs promise what autoregressive models can’t: fixing their mistakes. But new ones often change the noise and the sampler at once. Which matters? We tested it on the hypersphere. Noise: 0.8 points. Sampler: 25. We introduce Spherical Brownian Diffusion 🌐 👇🧵
16
42
3
186
8,228
🎉 Excited to bring our book The Principles of Diffusion Models to @NeurIPSConf 2026 as a tutorial—this time, all about diffusion LLMs! 🚀 🔹 How do ideas from continuous diffusion extend to language generation? 🔹 What are the latest advances and open frontiers in diffusion LLMs? From foundational principles to cutting-edge research. Stay tuned! 📆 Mon, Dec 7, 9 AM AEDT 📍 TikTok Ent Centre (Sydney, Australia) w/ organizers @ssahoo_ @mittu1204 @StefanoErmon
Subham Sahoo
@ssahoo_Oct 22
🎊 Excited to give a tutorial on diffusion LLMs at @NeurIPSConf 2026 with @StefanoErmon @JCJesseLai @mittu1204 📆 Mon, Dec 7, 9 AM AEDT 📍 TikTok Ent Centre (Sydney, Australia) Topics covered: > A beginner friendly introduction to diffusion-LLMs > Designing frontier diffusion-LLMs > Using Continuous diffusion for LLMs
2
15
1
73
3,387
Excited to announce the follow-up to our NeurIPS 2026 Oral: Improved Training of Strong Stochastic Flow Maps! We improve the training of SSFMs by unlocking derivative-based losses! Joint work with @antoniofrancaib @rmincam @ChristianKoke @Niklas_TR and @AlexanderTong7
1
36
3
171
11,693
did a group presentation today with @3blue1brown's manim style transitions. Sharing the template for anyone to build upon Brought to life with @NarekMaloyan's manim-web + reveal.js + claude + codex view template: slides.ramith.fyi view repo: github.com/ramithuh/protein-…
8
61
4
683
29,294
Can a language model be based purely on self-conditioning? 🤔 Yes! Meet LAW 👋 (a.k.a. Loopholing All the Way!) 🧵1/8
10
76
12
385
36,998
1/9 Current optimizers are static during training. What if the optimizer could think and react while the network trains? We let an agent watch the training dynamics and rewrite the optimizer's source code as training goes: a reactive optimizer. In every language and image setting we tried that has no tuned recipe, it matches or beats the best recipe one can one-shot, and it guards against loss spikes and overfitting by itself. In the near future, optimization decisions may belong to agents, not humans. 📝 xingjianbai.com/reactive-opt… 💻 Try it on your task: github.com/xingjian-bai/opal 🧵
73
199
65
1,518
210,034
Oscar Davis retweeted
Chanhyuk Lee
@chandavidleeOct 21
Can flow language models scale to billions of parameters and handle real generative tasks? Introducing 🌊 Lafa (Large flow language model), a flow LM scaled up to 8B that matches AR quality, with 🚀 2.5× AR throughput at 7B. Co-led with @ArnavChavan6 @UdbhavBamba. Joint work with @wognsfjq96 @hongseu33 @AdtRaghunathan @jw9730
9
51
9
217
22,741
Oscar Davis retweeted
Joey Bose
@bose_joeyOct 21
⁉️ Is model distillation of frontier models like DeepSeek-R1 and Opus 4.6 traceable to how robust each model's distilled family is 🤔? We find evidence of a completely new phenomenon that we term "Vulnerability Monoculture," where distilled models inherit the security risks of their teacher 😱 🚨 Check out our new preprint where we expose the Systemic Adversarial Robustness (SAR) of open-source frontier models Punchline: We show that models distilled from DeepSeek-R1 and Opus 4.6 are systemically less robust! In some cases, 30- 40% collectively less robust 🚨🚨🚨🚨!!!! 📝Blog: leoelm.github.io/blogs/syste… 📄Paper: arxiv.org/abs/2610.27353 w/ @leo_elm @LSzpruch @matthew_wicker 🧵1/7
3
4
2
31
1,594
Oscar Davis retweeted
Kieran Didi
@DidiKieranOct 21
One fun part of this project was @nscorley @RafiBrent @maxkazman and me sitting late in the office, testing out some ideas in the recurrence space and a week later seeing a paper that echoes our findings. Go checkout @osclsd's recent work, super cool stuff!
Oscar Davis
@osclsdOct 21
Super exciting to see the incredible advances of diffusion for bio too. Of course, with people like @DidiKieran, it's going to keep improving at incredible rates. Fun to see that self-conditioning is also falling in the protein space! Its days are numbered...
2
17
1,314
Oscar Davis retweeted
Kieran Didi
@DidiKieranOct 21
Replying to @DidiKieran @ArashVahdat @karsten_kreis @tomasgeffner @nscorley @RafiBrent @maxkazman
We also found things that echo recent flow language model work. We replaced our long-term enemy, self conditioning (@osclsd), with recurrent updates, which others concurrently presented as looped flows (@nmboffi). These “thinking modes” boost performance further. 11/30
1
3
1
14
3,049
Super exciting to see the incredible advances of diffusion for bio too. Of course, with people like @DidiKieran, it's going to keep improving at incredible rates. Fun to see that self-conditioning is also falling in the protein space! Its days are numbered...
Kieran Didi
@DidiKieranOct 21
Avengers assemble: 1 year BakerLab + NVIDIA GenAIR = 🔥 rfd4-proteina.org Presenting RFD4-Proteina, our latest protein design model, significantly better and faster than everything we compared against, both in silico and in the lab! 1/30
1
1
23
2,333
Oscar Davis retweeted
Michael Kirchhof@mkirchhof_Oct 21
When training agents, you add a length penalty for exceeding the budget/effort level. The fun thing is, every lab (Deepseek, Kimi, ...) uses a different one. We compare which works best in our new paper. 📄 arxiv.org/abs/2610.28409 🧵1/9
3
16
126
5,982
Oscar Davis retweeted
Joey Bose
@bose_joeyOct 20
🚨 Do you always have multiple rewards but don't know how to steer towards an expensive true reward? Don't fret, friends; we have the paper for you! 📣 Steered Not Stirred: Effective Reward Tilting using Surrogate Reward Mixing, led by the incredible @alec_sargood28 and team The Martini Algorithm 🍸 From 007: everyone now has a license to tilt 🤵 📜 Paper: arxiv.org/abs/2610.25502 🔗 Blog: alecsargood.github.io/martin…
Krisztina Sinkovics
@KristaSinkovicsOct 20
🚨Can we steer a generative model towards a gold reward we can't evaluate at inference time? Introducing 🍸 MARTINI — Steered Not Stirred🍸 We combine multiple imperfect reward surrogates from offline values OR preferences to steer without querying the oracle. Huge shout out to our dream team, brilliantly led by @alec_sargood28, with stellar work from @olivgallup and Noam Ghenassia, plus key input from Georg Maierhofer and @pduckw. A true honour to co-supervise with @bose_joey. 📄 Paper: arxiv.org/abs/2610.25502 🌐 Blog: alecsargood.github.io/martin… 🧵1/10
8
43
2,485
Oscar Davis retweeted
Joey Bose
@bose_joeyOct 19
🚨 New Paper Alert, 🎤 Accepted for an oral presentation at the NeurIPS 2026 STODY workshop! 📣 Introducing: Normalizing Flow Maps (NFM): Combining few-step transport from Flow maps with tractable likelihoods from Normalizing Flows. This is my first work with my first crop of new PhD students, @francescoshox and @tim_hitge, who genuinely knocked this project out of the park. 📄 Paper: arxiv.org/abs/2610.22711 📝 Blog: the-bose-lab.github.io/norma… 💻 Code: github.com/francescoshox/Nor… 🧵 1/8
4
51
5
235
16,542
Oscar Davis retweeted
Sander Dieleman
@sedielemOct 18
More progress on CDLMs: self-conditioning has always been a bit of a crutch, DoubleCat/SemiCat seems to be a principled way to get rid of it🎉
Oscar Davis
@osclsdOct 14
Continuous Diffusion LMs went from niche to contender this year, but the recipe is shaky: why self-conditioning? How to embed tokens? 🤨 Our new work takes your one-hot flow from 4% to 50% on TinyGSM without self-conditioning, and explores the design space of CDLMs. 🔥🚀 (1/6)
2
11
64
6,081
Oscar Davis retweeted
Rohit Dilip
@rohit_dilip_Oct 18
oscar leave some work for the rest of us 😅 very cool idea and exciting to see more principled explorations of self conditioning!
Oscar Davis
@osclsdOct 14
Continuous Diffusion LMs went from niche to contender this year, but the recipe is shaky: why self-conditioning? How to embed tokens? 🤨 Our new work takes your one-hot flow from 4% to 50% on TinyGSM without self-conditioning, and explores the design space of CDLMs. 🔥🚀 (1/6)
1
10
942
Oscar Davis retweeted
Ruixiang Zhang
@onloglognOct 16
Introducing RSI-Inference Bench from 🍎 Apple ML Research 🌐 rsi-inference.com 💻 github.com/apple-aiml-resear… Can AI agents improve the systems that run AI? We spent $100K API tokens, 50K GPU hours to find out. We built environments and benchmark from real-world #vLLM and #SGLang tasks, covering the full lifecycle of model inference engineering: 🚀 Day-0 Model Support ⚡ Inference Optimization 🔧 Bug Fix → Unsaturated: best agent at 26.7% pass@1 → Comprehensive coverage of the inference stack → Verifiable rewards: binary and continuous Watch the video to find out more!
61
96
23
884
77,971
Oscar Davis retweeted
Luca Ambrogioni
@LucaAmbOct 15
Replying to @Guanghan__Wang
Let's get it to sub 1 ;)
1
1
4
445
Oscar Davis retweeted
Niklas Rindtorff
@Niklas_TROct 16
Introducing Langevin Flow Maps TLDR: Neural Network Potentials that learn their own stochastic pathwise solution for faster simulation. - Transferable across molecular systems. - Transition dynamics are preserved. - No trajectory data are required. Work together with @sgmccallum, supervised by @AlexanderTong7, and @JamesFosterBath. Arxiv: arxiv.org/abs/2610.05998 Data: huggingface.co/datasets/nikl… Code: github.com/sammccallum/lfm
12
88
3
508
23,599
Introducing SCALLOP 💜 Our new paper accepted at NeurIPS 2026 🐨 🚀 A scalable, efficient way to train few-step likelihood-available flow maps, enabling effective Boltzmann generation! 📽️ project page: tonyauyeung.github.io/scallo… 🔗 paper: arxiv.org/pdf/2606.29110
2
22
3
185
20,163
Load more