I’ll be at #COLM2026 in San Francisco Oct 6-9!
Excited to present our work:
SkillFoundry: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
📍 Imperial Ballroom #17
🗓️ Tue, Oct 6 | 4:30–6:30 PM
📄 arxiv.org/abs/2604.03964
1
11
558
Wenduo Cheng retweeted
Excited to be at #COLM2026 in SF, Oct 6–9! 🎉
We'll present "SkillFoundry: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources"
📍 Poster #17, Imperial Ballroom
🕟 Tue, Oct 6, 4:30–6:30 PM PDT
We would love to meet up and chat!
3
5
18
2,450
As a collaboration between my group at @SCSatCMU, Aviv Regev's team at @genentech, and @michellearning's team at @medra_ai, we are pleased to share our Perspective, "Towards human-led, agent-driven autonomous laboratories for the life sciences." 🤖 preprints.org/manuscript/202…
This preprint release is coordinated with a complementary Perspective by @MengdiWang10, @lecong, and colleagues: preprints.org/manuscript/202…. Together, the two Perspectives examine the future of autonomous science from complementary angles.
Our Perspective was Led by @WenduoC in my group, with @mishamamq, @ShenShuaik4260 and @zocean636 at CMU; Anna Hupalowska, Jennifer Rood, Christine Bakan, and Aviv Regev at @genentech/@Roche; and Gaurav Agrawal and @michellearning at @medra_ai.
🚀preprints.org/manuscript/202…
2
34
88
6,416
Very excited to share our @ScienceMagazine paper on single-cell #3D #genome reorganization in #Alzheimer's disease.
We jointly measured gene expression and 3D genome architecture in individual human brain cells using #GAGEseq, then integrated these data w/ chromatin accessibility and spatial transcriptomics. We uncovered increased #compartment #mingling and distance-dependent rewiring of gene regulatory contacts in AD.
We also developed #Hicformer, a transformer-based model that integrates DNA sequence with 3D genome features to predict cell type-specific gene expression and prioritize candidate regulatory elements.
Huge kudos to co-first authors @zocean636 and @xinyuelu1999; and many thanks to Zhijun Duan @UW, Hansruedi Mathys @PittTweet, & David Bennett @rushalzheimers for the wonderful collaboration, as well as to all our co-authors. @CarnegieMellon @SCSatCMU @CMUCompBio #AlzheimersDisease #3DGenome #SingleCell #AI
science.org/doi/10.1126/scie…
4
56
237
16,881
Happy to share that our SkillFoundry paper is now accepted to #COLM2026 @COLM_conf ! This space is moving incredibly fast around agentic AI for scientific discovery. @ShenShuaik4260 and @WenduoC in my group have been pushing on several exciting projects in this direction
We are sharing SkillFoundry, a framework for converting heterogeneous scientific resources into validated #agent #skills. In addition to benchmark improvements, we show utility on genomics workflows. Still early, but very encouraging. ma-compbio-lab.github.io/Ski…
1
7
34
4,726
Wenduo Cheng retweeted
Scientific agents are getting powerful, but they still rarely work together out of the box. Each agent has its own interface, assumptions, tools, and artifacts. Composing them into a reliable workflow still takes a lot of manual wiring.
We built AgentCo-Op to make agents cooperate. Given a task, AgentCo-Op retrieves relevant agents, tools, skills, repos, datasets, and workflow priors, then synthesizes an executable multi-agent workflow with typed artifact handoffs and bounded local repair. Instead of designing every workflow from scratch, AgentCo-Op turns existing scientific agents and tools into interoperable workflow components.
Project: ma-compbio-lab.github.io/Age…
Paper: arxiv.org/abs/2605.20425
Code: github.com/ma-compbio-lab/Ag…
Thanks to my co-authors @WenduoC, Shike Wang, @mishamamq, and @jmuiuc for guidance and support throughout this work.
#MultiAgent #LLMAgents #AI4Science #ComputationalBiology
5
10
4,665
The editors at Cell Systems asked: "How is agentic AI changing how we do science?" My response- it is exciting and already happening. But progress will depend on making agentic processes more trustworthy and accountable. The full Voices piece includes perspectives from several colleagues in the field. cell.com/cell-systems/fullte…
1
21
125
7,873
Wenduo Cheng retweeted
Excited to share that our paper “CodonMoE: DNA Language Models for Codon-Dependent mRNA Prediction” has recently been accepted by Bioinformatics! 🎉
CodonMoE is a lightweight plug-and-play adapter that enables existing DNA language models to perform mRNA analysis tasks effectively — without RNA-specific pretraining. Across tasks spanning mRNA stability, expression, and regulation, CodonMoE consistently improves DNA models while using substantially fewer parameters than specialized RNA models.🧬
📎 Paper: arxiv.org/abs/2508.04739
Big thanks to my collaborators and advisor: Litian Liang, Jiayi Li, and Carl Kingsford🙌
Comments and feedback are very welcome!
#GenomicLanguageModels #AIforScience #PEFT #mRNA
4
1
9
966
Wenduo Cheng retweeted
🧵 1/ Thrilled to announce I'm joining @BioMedDataSci @DartmouthGeisel as a tenure-track Assistant Professor in Biomedical Data Science! 🎉
10
7
22
8,436
Wenduo Cheng retweeted
A lot of scientific know-how already exists in Gtihub repos, APIs, notebooks, docs, and research papers. But agents still cannot really make use of it out of the box because it is scattered everywhere,
We built SkillFoundry to bridge that gap. It turns fragmented scientific resources into reusable #skills that agents can actually use.
The basic idea is to use a Domain Knowledge Tree to guide the search, mine candidate skills from heterogeneous resources, package them into executable skills, test them automatically, and then keep refining the library based on what works, what fails, and what overlaps.
With the agent skills automatically designed by SkillFoundry, we see gains on 5/6 MoSciBench datasets, and Codex + SkillFoundry does much better on cell annotation than Codex alone, while staying competitive with systems like SpatialAgent.
We also gave Biomni automatically designed skills from SkillFoundry for the scDRS workflow, and it outperformed Biomni running on its own.
Project: ma-compbio-lab.github.io/Ski…
Paper: arxiv.org/abs/2604.03964
Thanks to my co-authors @WenduoC @mishamamq @TurcanAlistair @martinjzhang and @jmuiuc for guidance and support throughout this work.
2
19
56
12,206
Wenduo Cheng retweeted
We are grateful to @NatureComms for featuring our #DNALONGBENCH as one of the #Editors #Highlights in #ComputationalBiology: nature.com/collections/cfhfe…
Happy to share #DNALONGBENCH @NatureComms. We challenge DNA #FoundationModels w/ long-range sequence context and hope this sparks more meaningful ways to evaluate growing AI+BIO models. Kudos to @WenduoC @ZhenqiaoSong @zocean636. Great collab w/ @lileics. nature.com/articles/s41467-0…
1
5
23
4,781
Wenduo Cheng retweeted
Happy to share #DNALONGBENCH @NatureComms. We challenge DNA #FoundationModels w/ long-range sequence context and hope this sparks more meaningful ways to evaluate growing AI+BIO models. Kudos to @WenduoC @ZhenqiaoSong @zocean636. Great collab w/ @lileics. nature.com/articles/s41467-0…
1
23
110
14,924
Wenduo Cheng retweeted
Final version of our L2G paper is now published at @TmlrOrg! Kudos to @WenduoC for leading this work.
Paper: openreview.net/forum?id=5NM4…
Can we skip genomic Foundation Model pretraining? Our work L2G repurposes language LLMs for genomics via cross-modal transfer, matching fine-tuned genomic FMs. Kudos to @WenduoC & amazing collab w/ @atalwalkar. L2G, language to genome; L2G, life’s too good biorxiv.org/content/10.1101/…
9
25
4,727
Wenduo Cheng retweeted
Happy to see a time series workshop @ NeurIPS 2025 motivated in part by our search for BERT moments in specialized foundation models (🧵here: nitter.siddz.com/khodakmoments/status/1…)
🚀 We are happy to organize the BERT²S workshop @NeurIPSConf 2025 on Recent Advances in Time Series Foundation Models.
🌐 berts-workshop.github.io
📜Submit by August 22
🎓Speakers and panelists: @ChenghaoLiu15 Mingsheng Long @zoe_piran @danielle_maddix @atalwalkar @qingsongedu
1
6
12
3,782
Wenduo Cheng retweeted
Excited to present our work at #ICLR2025!
Join us on Thursday, April 23 (Afternoon Session) to chat about the current state of foundation models in specialised domains 🧬📈
Hall3+2B #40
Joint work with @ZongzheX2001 @WenduoC @musishen @JunhongShen1 @atalwalkar @khodakmoments
🧵 on surprising revelations from our study of specialized foundation models (FMs beyond vision/text): after evaluating dozens of scientific & time series FMs we found that most weren’t even competitive with simple supervised models, some with as little as 513 parameters.
1/n
1
8
16
1,750
Wenduo Cheng retweeted
I have some news to share!
@datadoghq is forming a new AI research lab, and I'm excited to announce that I've joined as Chief Scientist to lead this effort. Datadog has a great work culture, lots of data and compute, and is committed to open science and open sourcing.
Our team is working on ambitious research areas grounded in real-world challenges in cloud observability and security, with three current areas of focus:
1. Observability Foundation Models for forecasting, anomaly detection, and multi-modal telemetry analysis (logs, metrics, traces, etc.).
2. Site Reliability Engineering (SRE) Agents to detect, diagnose, and resolve production incidents.
3. Production Code Repair Agents that leverage code, logs, and runtime data to identify and fix performance issues.
On a personal note, I'm thrilled to work with Oli and Alexis again (we worked together in the early aughts before they co-founded Datadog). I’m also excited that Datadog, as part of its expansion in AI, is partnering with CMU (note: I will continue to work part-time at CMU and maintain my research activities).
Datadog is actively hiring out of our NYC office!
25
31
286
31,079
Wenduo Cheng retweeted
Proper and meaningful benchmark datasets are crucial for advancing genomic LLMs/FMs, and ML methods for genomics in general. Fantastic collab w/ @lileics's group. Amazing work led by @WenduoC @ZhenqiaoSong @zocean636
DNALONGBENCH: A Benchmark Suite for Long-Range DNA Prediction Tasks biorxiv.org/cgi/content/shor… #biorxiv_bioinfo
6
31
4,178
Wenduo Cheng retweeted
Can we skip genomic Foundation Model pretraining? Our work L2G repurposes language LLMs for genomics via cross-modal transfer, matching fine-tuned genomic FMs. Kudos to @WenduoC & amazing collab w/ @atalwalkar. L2G, language to genome; L2G, life’s too good biorxiv.org/content/10.1101/…
1
22
114
17,258
Wenduo Cheng retweeted
🧵 on surprising revelations from our study of specialized foundation models (FMs beyond vision/text): after evaluating dozens of scientific & time series FMs we found that most weren’t even competitive with simple supervised models, some with as little as 513 parameters.
1/n
3
61
241
43,190