Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Page Not Found

<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">Page not found. Your pixels are in another canvas.

</p>

</a>

Tianqi Chen — Diffusion models, generative AI

<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">Statistics PhD candidate at UT Austin working on diffusion models, generative AI, and trustworthy ML.

</p>

</a>

Archive Layout with Content

</a>

Posts by Category

</a>

Posts by Collection

</a>

CV — Tianqi Chen

</a>

</a>

Markdown

</a>

Page not in menu

<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a page not in th emain menu

</p>

</a>

Page Archive

</a>

Portfolio

</a>

Projects

</a>

Publications

</a>

Sitemap

</a>

Posts by Tags

</a>

Talk map

</a>

Talks and presentations

</a>

Teaching

</a>

Terms and Privacy Policy

</a>

Blog posts

</a>

</a>

</a>

</a>

</a>

</a>

</a>

</a>

</a>

</a>

</a>

Jupyter notebook markdown generator

</a>

</a>

</a>

</a>

Posts

Future Blog Post

January 2199
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

</p>

</a>

Blog Post number 4

August 2015
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

</p>

</a>

Blog Post number 3

August 2014
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

</p>

</a>

Blog Post number 2

August 2013
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

</p>

</a>

Blog Post number 1

August 2012
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

</p>

</a>

portfolio

Portfolio item number 1

<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">Short description of portfolio item number 1

</p>

</a>

Portfolio item number 2

<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">Short description of portfolio item number 2 

</p>

</a>

publications

Immuno-mimetic Deep Neural Networks (Immuno-Net)

The 2021 ICML Workshop on Computational Biology · 2021
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">In this paper we introduce a different type of biomimetic model, one that borrows concepts from the immune system, for designing robust deep neural networks.

</p>

</a>

RAILS: A Robust Adversarial Immune-Inspired Learning System

IEEE Access · 2022
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">We develop a novel adversarial defense framework inspired by the adaptive immune system: the Robust Adversarial Immune-inspired Learning System (RAILS)

</p>

</a>

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

IEEE Access · 2022
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">In this work, we first introduce an information-theoretic surrogate loss for DkNN-based classification, based upon which we then propose an attack algorithm and a defense algorithm achieve SOTA adversarial results on ...</p>

</a>

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

ICML · 2023
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">We propose a binomial/Poisson-based hierarchical variational autoencoding framework that are well suited for modeling non-standard non-negative distributions that exhibit sparsity, skewedness, heavy-tailedness and/or ...</p>

</a>

Beta Diffusion

NeurIPS · 2023
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">A diffusion model defined directly on the simplex via Beta distributions, well-suited for bounded, normalized, or compositional data such as images and probability vectors.

</p>

</a>

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference

ICML · 2024
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">A dense-reward perspective on aligning text-to-image diffusion with human preference, turning the entire denoising trajectory — not just the final sample — into the optimization signal.

</p>

</a>

Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

ICLR · 2025
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">A swift, data-free machine unlearning algorithm that rapidly removes target classes or concepts from diffusion models while preserving the original generative capability of others — with up to 1000× sampling speedup, ...</p>

</a>

talks

Talk 1 on Relevant Topic in Your Field

March 2012
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!

</p>

</a>

Tutorial 1 on Relevant Topic in Your Field

March 2013
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">More information here

</p>

</a>

Talk 2 on Relevant Topic in Your Field

February 2014
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">More information here

</p>

</a>

Conference Proceeding talk 3 on Relevant Topic in Your Field

March 2014
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

</p>

</a>

teaching

Teaching experience 1

Undergraduate course · University 1, Department · 2014
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a description of a teaching experience. You can use markdown like any other post.

</p>

</a>

Teaching experience 2

Workshop · University 1, Department · 2015
<p style="margin: 10px 0 0; color: var(--fg-muted); font-size: 0.95rem;">This is a description of a teaching experience. You can use markdown like any other post.

</p>

</a>