Skip to content
View xwinxu's full-sized avatar
💭
alignment and llms.
💭
alignment and llms.
275 followers · 128 following

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Starstruckx2Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Starstruckx2Achievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Highlights

  • Pro

Organizations

@for-ai @VectorInstitute @UTMIST

Block or report xwinxu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
xwinxu/README.md

I research scalable and principled methods for aligning large generative models. In the past, I worked at FAIR Labs at Meta, Google DeepMind and Stanford AI. I'm a graduate of CS, Math, and Stats at the University of Toronto where I began learning about latent variable models and probabilistic inference at the Vector Institute. I'm open to full-time ML research and engineering roles.

Like my models, I'm still learning (:

Pinned Loading

  1. ContextualAI/HALOs ContextualAI/HALOs Public

    A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

    Python 740 45

  2. bayeSDE bayeSDE Public

    Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

    Python 170 28

  3. google-research/cascades google-research/cascades Public

    Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.

    Python 195 14

  4. ermongroup/self-similarity-prior ermongroup/self-similarity-prior Public

    Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations

    Jupyter Notebook 25 4

  5. variational-mnist variational-mnist Public

    Fitting a recognition model (VAE) to do approximate inference on intractable posteriors of probabilistic models using an ELBO estimator.

    Python 10 1

  6. pruning-neural-nets pruning-neural-nets Public

    Generating structured sparsity in neural networks using weight and unit pruning techniques.

    Python 1