<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Projects | Tianlang (Jackie) Chen</title><link>https://jackiectl2.github.io/projects/</link><atom:link href="https://jackiectl2.github.io/projects/index.xml" rel="self" type="application/rss+xml"/><description>Projects</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 19 May 2024 00:00:00 +0000</lastBuildDate><image><url>https://jackiectl2.github.io/media/icon.svg</url><title>Projects</title><link>https://jackiectl2.github.io/projects/</link></image><item><title>AI-Guided Environmental Sensing &amp; Adaptive Monitoring</title><link>https://jackiectl2.github.io/projects/r3/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/r3/</guid><description>&lt;p&gt;Reproducible ingestion → reconstruction → uncertainty-quantification workflow for the sparse, seasonal Great Lakes, comparing random / grid / uncertainty-aware sensor-placement rules.&lt;/p&gt;</description></item><item><title>Applets for Data Analytics in Materials Science</title><link>https://jackiectl2.github.io/projects/r4/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/r4/</guid><description>&lt;p&gt;JavaScript front end + Python back end serving the materials community: users upload datasets and analyze them with SOTA models and fitting methods, built as reusable FAIR-compliant modules.&lt;/p&gt;</description></item><item><title>EPCOT Foundation Model — TSS-to-Expression Data Pipeline</title><link>https://jackiectl2.github.io/projects/r2/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/r2/</guid><description>&lt;p&gt;Pseudobulk pipeline from raw snMultiome (1 bp sparse ATAC → 600 kb HDF5 windows; CP10K-normalized 19,264-gene RNA vectors across 7 cell types). Five bit-equivalent training optimizations for a 2–5× speedup at identical numerics. Reset-head fine-tuning for small-data generalization. Located and fixed a ~50 kb TSS-bin offset.&lt;/p&gt;</description></item><item><title>Functional Genomic Representation Learning for Microbial Communities</title><link>https://jackiectl2.github.io/projects/r5/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/r5/</guid><description>&lt;p&gt;Proteogenic k-mer tokenization yields interpretable, parameter-free genome encodings that plug into both classical statistics and pretrained sequence models (Evo, ESM, ProtT5). Abundance-weighted community embeddings, leakage-safe features, permutation tests and honest cross-validation.&lt;/p&gt;</description></item><item><title>LLM for Incentive Design in Mobility Systems</title><link>https://jackiectl2.github.io/projects/r1/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/r1/</guid><description>&lt;p&gt;An LLM-guided workflow that generates and evaluates interpretable incentive policies for ride-hailing, transit, and shared vehicles — pairing learning-based methods with classical optimization.&lt;/p&gt;</description></item><item><title>More steamers on the next cart · 敬請期待</title><link>https://jackiectl2.github.io/projects/more/</link><pubDate>Wed, 31 Dec 2025 00:00:00 +0000</pubDate><guid>https://jackiectl2.github.io/projects/more/</guid><description>&lt;p&gt;More projects are in progress.&lt;/p&gt;</description></item></channel></rss>