GenBio AI

Many “virtual cell” efforts restrict themselves to cell-level assays like scRNA-seq. To build a true world model for biology, we need to move beyond the individual cell and model the tissue context as well. GenBio-PathFM is a new histopathology foundation model from GenBio AI. It is the only SOTA model trained without using proprietary image archives, and the strongest open-weight model to date. Highlights: - SOTA performance on public pathology benchmarks (THUNDER, HEST, PathoROB - shown below). - Unprecedented data efficiency, requiring 5x-15x fewer WSIs for training. - Novel two-stage pretraining strategy combining DINO and JEPA. Blog post: genbio.ai/genbio-pathfm Paper: genbio.ai/papers/genbio-… GitHub: github.com/genbio-ai/genb…

Cells aren't islands. Their representation and function depend on neighbors. We introduce AIDO.Tissue, a foundation model that learns biology by thinking in cellular neighborhoods. It not only outperforms competing models but also demonstrates a scaling behavior with neighboring context. Learn more👇 genbio.ai/aido-tissue/

Big thanks to our presenter @anshulkundaje, our host @probablybots, and everyone who joined today's #FM4Bio seminar. We'll be posting the talk "Lightweight, Interpretable Supervised and Self-Supervised Deep Learning Models of Regulatory DNA" on our YouTube channel soon. Stay tuned: @genbioai" target="_blank" rel="nofollow noopener">youtube.com/@genbioai

Happening in a few minutes! Tune in: x.genbio.ai/fm4bio-seminar

⏰ Last chance to register! Tomorrow at 9AM PT, Professor @anshulkundaje @Stanford joins the #FM4Bio Seminar to discuss his work on lightweight, interpretable models that outperform massive foundation models for decoding the regulatory genome. Don't miss it 👇 x.genbio.ai/fm4bio-seminar

Bigger isn't always better in genomics AI Join us Tue, Mar 24 at 9 AM PT for the next #FM4Bio Seminar with Professor @anshulkundaje @Stanford — on building smarter, interpretable models of regulatory DNA that outperform massive foundation models. x.genbio.ai/fm4bio-seminar

Predicting how cells respond to genetic or chemical changes is a fundamental challenge in drug discovery. While the potential of biological Foundation Models (FMs) has been widely discussed, their actual superiority over simple statistical baselines has remained a subject of significant debate in the field. In our latest preprint, we provide a definitive evaluation of FMs for perturbation prediction. By benchmarking over 600 model variants, we demonstrate that FMs, when trained on the right modalities and integrated effectively, provide a significant leap in predictive accuracy. Our findings confirm that FMs are not just a theoretical improvement, but a practical tool for building accurate, actionable simulations of cellular behavior. Preprint: biorxiv.org/content/10.648… Code and data: github.com/genbio-ai/foun… Blog post: genbio.ai/foundation-mod…

Don’t miss GenBio AI Co-Founder & Chief Scientific Advisor @Prof_Lundberg at #NVIDIAGTC: 🧬Scaling Laws in Biology: Why Bigger Models Alone Aren’t Enough [S81652] March 18, 10:00–10:40 AM PT An in-person panel on breaking the data wall in Bio x AI through at-scale data generation and new scaling laws. Save your seat → nvda.ws/3OAKT1T 🎟️ Register → nvda.ws/4cCOiY2 v/ @NVIDIAHealth

If you're excited about AI scientists and biology simulators, we're looking for FTEs and interns @genbioai. Come work with an elite team of nobel laureates and titans of science+engineering on products that both people and agents use to accelerate biomedical research. DM or email

In @theinnovator’s Interview of the Week, GenBio AI Co-Founder and Chief Scientist @ericxing shares his view on the next phase of intelligence and why AI for biology must move beyond pattern matching toward world models. Read the full interview ↓ theinnovator.news/interview-of-t… @jennschenker

Insightful remarks from GenBio AI Co-Founder and Chief Scientist @ericxing at #WEF26 on why the next phase of AI will be defined by world models, reasoning, and interaction, not just larger language models. Learn more 👇

It was a pleasure to share the stage with @Yoshua_Bengio, @YejinChoinka, @harari_yuval, and @nxthompson, at #WEF26 in Davos to discuss "Next Phase of Intelligence". I shared my reservation of current LLM-based systems bringing us toward AGI very soon, and spoke for the needs for substantial innovations in representation, architecture, and learning paradigm before we can reach truly physical, social, and philosophical intelligence. My candid response to @nxthompson's questions on what to go next, and what existing architecture to avid is: we must move past LLMs to focus on World Model to unlock physical intelligence, and we can't build a consistent, safe, and interactable world model by learning only in the "thought space" (i.e. latent space". We need new architectures like the GLP (Generative Latent Prediction) that support stateful representation, long-horizon reasoning, action-conditioning, and most importantly, close-loop training where learning takes place in both latent (thoughts) and observation (reality) space to ensure grounding, fidelity, and certifiability; and we also must go beyond passive self-supervised learning on pattern matching and reconstruction with a stationary model, but active and proactive learning on task-completion objectives and cost-conscious rewards over a non-stationary model that can improve not just during pre-train, but also in- and post-action during serving. Our PAN world model builds on such design principles.

GenBio AI Co-Founder and Chief Scientist @ericxing is speaking today at the World Economic Forum in Davos on The Next Phase of Intelligence. The discussion explores how AI systems learn, plan, and act at scale, questions central to how we think about modeling complex systems in biology. Tune in 👇 #WEF26 weforum.org/meetings/world…

Super excited to see that @genbioai was highlighted in Dr. @LisaSu's keynote talk. Thank you so much, @AMD — we look forward to what we will achieve together in 2026!

Chair and Chief Executive Officer at AMD, Dr. @LisaSu, highlighted our partnership during her CES 2026 keynote. At #CES2026 in Las Vegas, GenBio AI joined @AMD to share a vision for advancing biology with AI. Together, we are building the foundation for personalized treatments made just for you. Learn more and stay tuned → x.genbio.ai/amd-genbio-ces…

2025 has been a productive year for me as a researcher and engineering lead. I managed to spend time working on three exciting technical projects in addition to my duty of running the university, and made some significant progress:    1: PAN: a world model built for simulation, prediction, and agentic reasoning over arbitrary time/space horizon, rather than just generating shot video clips as other “world models” do. In the CWM paper (arxiv.org/abs/2507.05169), we proposed a new architecture called Generative Latent Prediction (#GLP) for structured latent-space reasoning while maintaining fidelity to the physical environment, which is defined by three key components: 1- Latent Reasoning Backbone — an LLM/DM-driven module that produces structured, stateful representations conditioned on history and action; 2- Generative Supervision — a diffusion-based decoder that renders the consequences of latent transitions back into the perception space, providing explicit grounding in observable reality; and 3- Closed-loop Learning Objective — a training strategy that continually aligns simulated dynamics with real-world evidence, reducing drift and reinforcing causal consistency.  At the Institute of Foundation Models (IFM) of @mbzuai, we built the PAN world model (ifm.ai/pan/) based on this architecture, which moves PAN beyond correlation-driven prediction toward mechanistic understanding, enabling the model to learn how and why the environment changes rather than relying solely on abstract latent dynamics. The combination of generative grounding, stepwise verification, and action-conditioned reasoning provides robustness in settings where interpretability, causal structure, and physical consistency are essential, and allows PAN to exceed significantly over existing WMs on novel and challenging benchmarks beyond mere short-horizon video constancy, such as Action Simulation Fidelity, Long-Horizon Consistency, and Simulative Reasoning and Planning Quality.  These capabilities are particularly relevant across domains such as personalized game, agentic and embodied robotics, and multi-physics simulation.    2: AIDO: the AI-driven Digital Organism (arxiv.org/abs/2412.06993) is an AI system that enables simulation of all biological, physiological, and clinical events occurring within a living organism — outputs how a real biological system would respond, against any expressible and actionable biological interaction, intervention, and manipulation, through a digital interface – like a World Model would do in world simulation upon action prompting. This contrasts existing works under the banner of “virtual cell” whereas in reality focusing on functional approximation in classical machine learning style to predict RNA counts of N-k genes upon perturbation of k genes (where k typically equals to 1, and represents an abstract, isolated, and idealistic binary “action” not actually realizable in real biological experiments). At @genbioai (genbio.ai), we are building the Virtual Cell, corresponding to the cellular level of the AIDO, as a world model of the cell that simulates biological possibilities at both molecular (e.g., RNA count distributions, but also other molecular phenomenon such as drug interactions) and cellular level (such as cell shape, dynamics, and function). It is built on a novel neural architecture that integrates multimodal biological data with unconventional tokenization schemes; learns representations of sequence, structure, interaction, sub-cellular units, and higher-order biological entities in a causal and hierarchical manner; leverages innovative pre-train and post-train schemes, and allows action-conditioned generation of biological outputs across scales. Our AIDO system features in-context molecular design and holistic cell simulation platforms, and an Agent Interface to enable researchers performing in silico experiments on the virtual-bio engine over a wide range of tasks like discovering new targets and simulating drugs and diseases mechanisms. Our system ranks No. 1 Out of 97 Methods in ProteinGym Benchmark, and is hosted by Chan Zuckerberg Initiatives as a Representative FM for Virtual Cell. We will soon release the agentic Virtual Cell Lab to the scientific community for simulative biological research and experiments.    3: K2 LLMs: including K2-v2 (ifm.ai/k2/) — world’s strongest fully open LLM in its class (70B), rivaling open-weight leaders and approaches the performance of models over three times its size, and K2-think (k2think.ai/k2think) —  world’s fastest and most parameter-efficient reasoning LLM post-trained from K2-v2, both from the @llm360 initiative and from the IFM. In a world where most U.S. frontier models dominate performance, but remain completely closed, while Chinese open-weight systems occupy a large semi-open middle band, our K2 models represent an effort to better serve the AI community and the public users with truly open-source foundation models that are transparent, reproducible, and competitive, with a 360-open approach: making public not just model weights, but also training data, mid-training checkpoints, logs and methodology, and fine-tuning recipes. In K2-v2 (arxiv.org/abs/2512.06201), We actively infuse domain knowledge, reasoning, long-context, and tool use throughout the training process, which explicitly prepares the model for complex reasoning tasks after post-training. In K2-think (arxiv.org/abs/2509.07604), the key technical elements underlying the remarkable performance include: 1) long chain-of-thought supervised fine tuning, 2) reinforcement learning with verifiable rewards, 3) agentic planning before reasoning, 4) test-time scaling, 5) speculative decoding, and 6) inference optimized hardware. Our models punched above their weights and with their 360-degree transparency, directly address reproducibility, auditability, and governance the constraints that will define real-world deployment.    As we say goodbye to 2025, I’d like to thank my collaborators, developers, and students from IFM, GenBio, MBZUAI, CMU for the wonderful collaboration. More to come in 2026, you will see bigger and more powerful K2 (LLM), PAN (WM), and AIDO releases, and more advancements in architectural and system work!

Happy Holidays from all of us at GenBio AI! 🎄⭐️🎅

In this feature from our ongoing series, GenBio AI Co-Founder and Chief Strategic Advisor @Prof_Lundberg shares her perspective on how AI and biological research come together to drive progress in understanding life. Watch the clip below ↓ youtube.com/shorts/DmNaKh5… Stay tuned for the next part of the series featuring one of GenBio AI’s co-founders.

Join GenBio AI Co-Founder and Chief Scientist @ericxing at #NeurIPS2025 for his invited talk at the Biosecurity Safeguards for Generative AI Workshop. He will discuss how AIDO supports molecular design and cell-level modeling, including AI-based perturbation simulation. 📍 Room 27AB 🕒 3:35 to 4:05 PM PT Full details → biosafe-gen-ai.github.io/index.html

Don't miss out, GenBio AI Co-Founder and Chief Scientist @ericxing will speak at the #NeurIPS2025 AI Virtual Cells and Instruments workshop. Join us on December 6 at the San Diego Convention Center, Upper Level Room 28A–E. Sessions ↓ • Panel: Building AI Virtual Cells and Instruments at 8:35 am PT • Talk: AIDO and Virtual Cell Architecture and Principles at 10:00 am PT Full details on the workshop website → ai4d3.github.io/2025/schedule.…