
Professor of #computerscience @Stanford; Co-founder at https://xitter.gq/t.co/hhm1j5wP0f #machinelearning #graphs.
Stanford, CA
Joined August 2007
- Tweets1.5K
- Following435
- Followers46.2K
- Likes1.3K
Jure Leskovec retweeted
Introducing CUDA Rust!
CUDA Rust lets you write GPU kernels natively in Rust, not just launch them from it.
Two paths: cuda-oxide for SIMT kernels compiled to PTX, and cutile-rs for Tile-based programming on stable Rust. Both can catch aliasing errors at compile time.
Technical blog: nvda.ws/4hm1bHS
Jure Leskovec retweeted
Today, we're excited to share that Biomni is published in @ScienceMagazine.
Biomedical research is still fragmented, manual, and difficult to scale. In this work, we introduce Biomni - the first general-purpose biomedical AI agent with an integrated biology environment that can reason, plan, and execute end-to-end scientific workflows.
We show that, with the right environment and harness, AI can automate large-scale omics analyses, orchestrate laboratory robotics, optimize molecular properties, and even train new AI models for biology.
We also introduce a reinforcement learning recipe for continually improving biomedical AI agents, enabling open-source models to achieve frontier-level performance.
It's surreal to look back. We started the Biomni project in early 2024, when agentic AI was still nascent. It is exciting to see tens of thousands of biologists collaborating with agents every day to accelerate science.
Try Biomni: biomni.phylo.bio
Read more: science.org/doi/10.1126/scie…
This work is not possible without this truly inter-disciplinary team: @serena2z @hcwww_ @YuanhaoQ Minta Lu, Ryan Li, @yusufroohani Lin Qiu @shiyi_c98 Gavin Junze Di @rickwierenga @kavi_deniz Sherry @TianweiShe Shruti Jennefer Xin Zhou @MWheelerMD Jon Bernstein @MengdiWang10 @PengHeAtlas @zhou_jingtian @SnyderShot @lecong Aviv Regev @jure
@StanfordAILab @genentech @phylo_bio @arcinstitute @UW @berkeley_ai @RetroBio_ @tamarindbio @Princeton @UCSF
Jure Leskovec retweeted
Cancer diagnosis is informed by cellular annotations of histopathology, but assays are expensive or rely on manual annotations.
At #ICML2026, we present SpatialWhisperer, a trimodal model that zero-shot annotates cell types in histopathology images. 🧵👇
Jure Leskovec retweeted
🎉🎉 PluRel will be presented at #ICML2026 🎉🎉
Date: Tue, Jul 7, 2026 • 10:30 AM – 12:15 PM KST
Location: HALL A #2715
by co-author: @_rishabhranjan_ !
Also checkout our latest website for interactive visualizations, access to code, models and data:
star-project.stanford.edu/pl…
Relational Foundation Models face a scaling problem: diverse training datasets are rarely public due to privacy constraints 🔒.
🚀 We are excited to introduce "PluRel": a framework that synthesizes diverse multi-table relational databases from scratch, unlocking scaling laws for RFMs. 🧵
Kudos to the amazing collaborators at @StanfordAILab @Kumo_ai_team , and @SAP : @_rishabhranjan_ @VHudovernik @vijaypradwi @johanneshoffart @guestrin @jure
Jure Leskovec retweeted
Excited to share a research collaboration with @ScaleAILabs - we rigorously evaluate bio agents on different models across 82 drug discovery tasks - interesting findings include:
(1) know-how/environment >>> models
(2) different LLMs have different strength - highlighting a need for model-routing for biology agents:
We get this question a lot: "Which model is best for drug discovery?"
Our new benchmark announced today with @ScaleAILabs, DrugDiscoveryBench (82 tasks from working drug discovery scientists, run on Biomni Open Source Environment), has a clear answer: the model matters far less than what you build around it.
🧵3 key takeaways →
Jure Leskovec retweeted
Biology doesn't happen in one place.
We're bringing Biomni Lab from your browser to your phone, your desktop, and your agent of choice via MCP. Biomni comes with you wherever your work happens.
Sign up for the closed beta (Mobile and Desktop): forms.gle/JbB4vV4GdaZcaLU19
Use Biomni MCP today: mcp.phylo.bio/mcp
Blog: phylo.bio/blog/biomni-everyw…
Jure Leskovec retweeted
Can reasoning models become overly reliant on chain-of-thought examples? 🤔
Our #ACL2026 work shows excessive CoT supervision is not always beneficial, and gives a recipe for tuning the CoT fraction to improve novel-task accuracy. 🧵
Website: kvignesh1420.github.io/cot-i…
Jure Leskovec retweeted
Proteo-R1 (ICML 2026), the first reasoning protein foundation model for protein design, is out! 🚀🧬
Most protein design models generate structures without ever *reasoning* about which residues matter. We think that's backwards.
Human protein engineers👩🔧 don't work this way. They identify critical interaction residues first — charged anchors, hydrophobic hotspots, specificity-determining motifs — and only then optimize geometry around those decisions.
━━━━━━━━━━━━━━━━
🔬 THE CORE IDEA
━━━━━━━━━━━━━━━━
A dual-expert architecture that explicitly decouples molecular understanding from geometric generation:
→ ⚡A multimodal LLM (understanding expert) analyzes protein sequences, structures, and text to identify key functional residues governing binding and specificity
→ ⚡A diffusion model (generation expert) then co-designs sequence + structure — but with those residues locked in as hard constraints
━━━━━━━━━━━━━━━━
📐 HOW IT'S TRAINED
━━━━━━━━━━━━━━━━
Three-stage curriculum:
① Multimodal Alignment — freeze the LLM, train projections to bridge ESM-2 + AF3-style structural features into language space
② Structural Reasoning Mid-Training — unfreeze the LLM, teach it residue grounding → pairwise geometry → interface localization → hotspot prediction
③ Joint Reasoning-Guided Design — end-to-end on antibody-antigen complexes. Gradients from the diffusion objective flow back through the reasoning expert.
━━━━━━━━━━━━━━━━
📊 RESULTS
━━━━━━━━━━━━━━━━
Evaluated on simultaneous multi-CDR redesign and the RAbD CDR-H3 benchmark:
✅ Best RMSD & DockQ on RAbD — redesigned H3 loops are geometrically accurate *and* docked well
✅ Lowest backbone dihedral divergence (JSDbb) among all baselines
✅ Reduced intra- and inter-chain steric clashes
✅ Generated sequences score lower perplexity than native antibodies under IgLM & AbLang
✅ Plug-and-play: swapping the diffusion backend to UniMoMo still improves RMSD and IMP
━━━━━━━━━━━━━━━━
💡 WHY IT MATTERS
━━━━━━━━━━━━━━━━
Proteo-R1 isn't just a better antibody design model. It's a blueprint for coupling deliberative LLM reasoning with any physical generative process — interpretable, modular, and backend-agnostic.
📄 Paper: arxiv.org/abs/2605.02937
💻 Code: github.com/smiles724/Proteo-…
🌐 Demo: smiles724.github.io/r1/
Great thanks to my wonderful collaborators Weihao Xuan, Heli Qi, @Hanqun_CAO, Heng-Jui Chang, @KKuanPang @XiangruTang Zehong Wang, @hcwww_ , @KejunYing @lupantech Chiho Im, Seungju Han, @richardxp888 @tikgiau. Also appreciate the guidance from advisors @YejinChoinka @jure @erranlli Naoto Yokoya, Masashi Sugiyama.
Jure Leskovec retweeted
We’re working with world-class experts to encode the latest research techniques and best practices into reusable skills that any scientist can use.
First up: rare-variant gene burden analysis, demonstrated on UK Biobank data for obesity.
Read the case study here:
Introducing the Genetic Target Hypothesis skill, co-developed with Prof. Manuel Rivas at Stanford, which transforms rare-variant burden statistics from UK Biobank into ranked therapeutic target hypotheses in minutes.
In a BMI/obesity case study, the system rediscovered canonical biology such as MC4R with the correct inhibit/activate direction, while surfacing novel candidate targets for follow-up.
Learn more in the blog post: phylo.bio/blog/turning-uk-bi…
Jure Leskovec retweeted
We are excited to announce Biomni Lab has exited research preview and is now generally available!
Over the last month, we received and incorporated valuable feedback from our global community of 10K+ scientists. We were amazed to learn that Biomni Lab power users accomplished ~20 months of work in just one.
We are introducing a Pro tier (alongside the free tier) with higher usage limits, priority HPC access, and more concurrent tasks so our users can get even more done, faster.
Accelerate your science today → biomni.phylo.bio
Jure Leskovec retweeted
We've been building nonstop since our public launch, and this week we're officially celebrating with the Biomni community! 🚀
On Thursday, join us virtually for a live demo of Biomni Lab by co-founders @KexinHuang5 and @YuanhaoQ, plus recent product updates and how we think about evaluating AI agents in biology.
On Friday, we'll feature demos + lightning talks from scientific co-founders @jure and @lecong, plus free swag, drinks, small bites, and plenty of time to mingle. We only have a few spots left, so RSVP soon.
• Virtual: luma.com/l5ryjaij
• South SF: luma.com/n8k8qb0n
We can't wait to see you there!
Jure Leskovec retweeted
Scientific analysis doesn’t stop when computation finishes. Results need to be clearly visualized and communicated to be shared and built upon.
We’ve revamped visual outputs in Biomni Lab:
• Automatic slide deck generation
• Reports exportable to HTML, Word, or PDF with embedded figures
• Substantial improvements to scientific figure quality
Biomni Lab now takes rigorous analyses through to presentation-ready outputs.
Try Biomni Lab: biomni.phylo.bio/
Jure Leskovec retweeted
🚀 Biomni v0.0.7 is live!
New features:
📜 PDF export for agent chats
🦠 SOTA cell type transfer algorithms
🔬LazySlide pathology support
🔍Claude web search
🌟Bioimaging pipeline tools
🧬Gene conversion & ESM embeddings
🪴Glycoengineering capabilities
Plus improved commercial licensing & data handling!
👉 Try it here: github.com/snap-stanford/Bio…
Jure Leskovec retweeted
✨ Optimas is fully open-sourced at github.com/snap-stanford/opt…
🏋🏻 Contribute by:
1) Submitting PRs for your own compound AI systems.
2) Extending the optimization infra.
3) Creating issues (we're happy to help optimize your systems, explore why they work or fail, and go from there 😉)
Introducing 🔥Optimas🔥: The first unified framework to optimize compound AI systems composed of multiple components like trainable/API-based LLMs, tools, model routers, and traditional ML models! 🌐
👉🏻 optimas.stanford.edu/
🌟 Why Optimas?
AI systems today combine diverse elements—prompts, model parameters, hyperparameters, and model router. Optimizing the entire system effectively is tough!
Optimas tackles this with an intuitive strategy: Globally Aligned Local Rewards (LRFs), ensuring each component's optimization directly boosts overall system performance!
📈 Impressive Results:
Tested rigorously on 5 real-world compound AI tasks: Product Recommendation, Medical QA, Complex Retrieval, Multi-hop QA, and Code Generation.
🤩 Delivers an impressive average boost of 11.92% over top baselines (e.g., LLMSelector, TextGrad, DSPy).
🔧 Here's the magic behind Optimas:
① Assigns each component a Local Reward Function (LRF).
② Aligns these LRFs with global objectives, enabling independent yet coordinated optimizations.
③ Adaptively updates LRFs for efficient, coherent improvements across diverse configurations.
💡 Compatible with popular agentic frameworks
Easily optimize your own systems!
Integrates with popular agentic frameworks like @DSPyOSS, @crewAIInc, @pyautogen, TextGrad, and OpenAI Agent SDK @OpenAIDevs!
Proudly developed by an outstanding collaboration between @StanfordAILab, @AmazonScience, and more!
Grateful to work with team @parthsarthi03, Shiyu, Aaron, @krypticmouse, @Diyi_Yang, @james_y_zou, @jure etc.!
Check out more!
📄 Paper: arxiv.org/abs/2507.03041
💻 Code: github.com/snap-stanford/opt… (to be open-sourced soon!)
#CompoundAISystem #LLM #Optimization #MachineLearning
Jure Leskovec retweeted
🎧 New ASEF Podcast!
“Meet the Fellows” episode: Lana Nastja Anžur & Adrian Mladenić Grobelnik on sustainable heritage research & commonsense AI at Stanford 🎓✨
🔗 buzzsprout.com/1753090/episo…
Jure Leskovec retweeted
We’re thrilled to share that the first in-person LoG conference is officially happening December 10–12, 2025 at Arizona State University logconference.org/
Important Deadlines:
Abstract: Aug 22
Submission: Aug 29
Reviews: Sept 3–27
Rebuttal: Oct 1–15
Notifications: Oct 20
Jure Leskovec retweeted
🧬Uncovering how a genetic variant leads to disease can take hours of deep reasoning—digging through RegulomeDB, ENCODE, ClinVar, PubMed, and more.
Biomni automates these steps and delivers a structured report in minutes.
Try it at biomni.stanford.edu
Jure Leskovec retweeted
Graphs provide a powerful way to model & solve many real-life problems, from traffic prediction to understanding why molecules smell. Learn more about the recent history of graph-based #ML & the role that Google researchers have played in the field →goo.gle/42aABbR
Jure Leskovec retweeted
This work is now accepted in ICWSM'25!! Updated version here: arxiv.org/pdf/2408.16629v2
We added many new experiments, including ablations of demographic variables and scaling the networks by 6x. The core result stays the same: LLMs overemphasize political homophily/polarization.
So excited to share our new preprint, “LLMs generate structurally realistic social networks but overestimate political homophily”! Joint work co-led by @a_chaszczewicz, along with Emma Wang, Maya Josifovska, @2plus2make5, and @jure
Paper: arxiv.org/abs/2408.16629































