Carles Domingo-Enrich
@cdomingoenrich
Followers
599
Following
83
Media
0
Statuses
31
Senior Researcher @ Microsoft Research New England. Formerly: Visiting Researcher @ Meta FAIR and CS PhD @ NYU.
Cambridge, MA
Joined September 2024
✨Masked Diffusion Language Models✨ are great for reasoning, but not just for the reasons you think! Fast parallel decoding? 🤔 Any-order decoding? 🤨 Plot twist: MDLMs offer A LOT MORE for inference and post-training! 🎢🧵
4
35
162
If you're a PhD student interested in interning with me or one of my amazing colleagues at Microsoft Research New England (@MSRNE, @MSFTResearch) this summer, please apply here https://t.co/DIkXUuK4zc (If you'd like to work with me, please include my name in your cover letter!)
8
71
427
Solving control problems can be hard. This is why we introduce trust region methods, approaching them iteratively in a systematic way. In fact, this can be understood as a geometric annealing from prior to target with adaptive steps. More at @NeurIPSConf, https://t.co/YS1VkDYBEB.
1
11
58
Announcing Flexible Masked Diffusion Models (FlexMDMs)—a new diffusion language model for flexible-length sequences. 🚨 Solves MDMs' fixed-length issue + retrains any-order sampling 🚨 <1000 GPU-hrs to fine-tune LLaDA-8B into FlexMDM (GSM8K 58→67%, HumanEval-infill: 52→65%)
3
61
368
thrilled to share The Dayhoff Atlas of protein language data and models 🚀 protein biology in the age of AI! https://t.co/4wP9kNRUoM we built + open source the largest natural protein dataset, w/ 3.3 billion seqs & a first-in-class dataset of structure-based synthetic proteins
4
78
311
In 1965, Margaret Dayhoff published the Atlas of Protein Sequence and Structure, which collated the 65 proteins whose amino acid sequences were then known. Inspired by that Atlas, today we are releasing the Dayhoff Atlas of protein sequence data and protein language models.
6
91
297
🌞🌞🌞 The third Structured Probabilistic Inference and Generative Modeling (SPIGM) workshop is **back** this year with @NeurIPSConf at San Diego! In the era of foundation models, we focus on a natural question: is probabilistic inference still relevant? #NeurIPS2025
1
18
109
We've open sourced Adjoint Sampling! It's part of a bundled release showcasing FAIR's research and open source commitment to AI for science. https://t.co/6oBTnael8p
https://t.co/rYmJ02KguC
github.com
code for "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching" - facebookresearch/adjoint_sampling
Announcing the newest releases from Meta FAIR. We’re releasing new groundbreaking models, benchmarks, and datasets that will transform the way researchers approach molecular property prediction, language processing, and neuroscience. 1️⃣ Open Molecules 2025 (OMol25): A dataset
1
23
117
Against conventional wisdom, I will be giving a talk with particular focus on the "how" and the various intricacies of applying stochastic control for generative modeling. Mon 9:50am Hall 1 Apex #ICLR2025 Also check out the other talks at https://t.co/7e2rJUmfIV!
9
33
260
New paper out with FAIR(+FAIR-Chemistry): Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching We present a scalable method for sampling from unnormalized densities beyond classical force fields. 📄: https://t.co/1lSxsvPUhV
1
19
113
🚀Excited to open source the code for Adjoint Matching --- as part of a new repo centered around reward fine-tuning via stochastic optimal control! https://t.co/KvPXYaa9mQ
github.com
Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching - microsoft/soc-fine-tuning-sd
New paper! We cast reward fine-tuning as stochastic control. 1. We prove that a specific noise schedule *must* be used for fine-tuning. 2. We propose a novel algorithm that is significantly better than the adjoint method*. (*this is an insane claim) https://t.co/EXfUEXi92q
1
13
59
This work was done during a PhD internship at FAIR NYC, thanks to my amazing supervisors @brandondamos , @RickyTQChen and Brian Karrer. Special thanks to our core contributors: @bkmi13
@bingyan4science @xiangfu_ml
@guanhorng_liu (and of course @cdomingoenrich)
0
1
7
Reward-driven algorithms for training dynamical generative models significantly lag behind their data-driven counterparts in terms of scalability. We aim to rectify this. Adjoint Matching poster @cdomingoenrich Sat 3pm & Adjoint Sampling oral @aaronjhavens Mon 10am FPI
1
6
18
Our MIT class “6.S184: Introduction to Flow Matching and Diffusion Models” is now available on YouTube! We teach state-of-the-art generative AI algorithms for images, videos, proteins, etc. together with the mathematical tools to understand them. https://t.co/wDJcM1YTxJ (1/4)
76
588
4K
This paper didn’t get the attention it deserves. Have you ever wondered why RLHF/reward fine-tuning is far less common for image generation models compared to large language models (LLMs)? This paper by @RickyTQChen and team explains it in details. 🧵
2
59
343
I’m excited to share our latest work on generative models for materials called FlowLLM. FlowLLM combines Large Language Models and Riemannian Flow Matching in a simple, yet surprisingly effective way for generating materials. https://t.co/xQ2TJnpusA
@bkmi13 @RickyTQChen @bwood_m
arxiv.org
Material discovery is a critical area of research with the potential to revolutionize various fields, including carbon capture, renewable energy, and electronics. However, the immense scale of the...
3
42
221
If you are a PhD student and want to intern with me or my colleagues at @MSRNE @MSFTResearch, please apply at
3
72
333
New paper out! We introduce “Generator Matching” (GM), a method to build GenAI models for any data type (incl. multimodal) with any Markov process. GM unifies a range of state-of-the-art models and enables new designs of generative models. https://t.co/6BTkr3ukYc (1/5)
8
70
342
Undergrad internship opportunities at MSR! If you are a rising junior or senior undergraduate student interested in working with me, apply here and mention my name: https://t.co/DtaA0m1IOk. Topics: fine-tuning and inference of generative models for continuous and discrete data.
microsoft.com
Accepting applications for 12-week summer research internships for juniors & senior undergrads w/ demonstrated leadership in diversity.
0
6
37