Today, we’re expanding our Nemotron family of open models with Nemotron 3.5 Super VL.
Bringing visual understanding, reasoning, and tool use together to help AI agents complete more work in less time.
Open models ➡️ more control to customize, deploy, and build on your own terms.
Dive into what’s new:
Narbe Mardirossian retweeted
👋 Say hello to faster structure prediction
NVIDIA BioNeMo Inference Runtime is in public beta. This open, PyTorch-native library speeds up biomolecular inference on NVIDIA GPUs.
Optimize models including Boltz-2, OpenFold2, and Protenix v2 with specialized kernels and, where supported, CUDA Graphs - then scale with Ray-powered GPU replicas.
🙌 Huge thanks to our collaborators at @apheris_AI, @AurekaBio, @Biomap_IMI, @boltz_bio, @dataiku, @UWproteindesign, @Latent_Labs, MoleculeMind, @nebiusai, @openmsf, @open_fold, @proximabio, @SandboxAQ, @Terray_Tx, and @Xaira_Thera for partnering with us on this work.
📃 nvda.ws/46PDmlL
Narbe Mardirossian retweeted
If we're rewriting football history now, I have a small suggestion:
I'd like FIFA to rescind the yellow card shown to Michael Ballack in the 2002 World Cup semifinal, the one that ruled him out of the final.
And while we're at it, we might as well replay the final against Brazil.
Narbe Mardirossian retweeted
Heading to Seoul for ICML. Looking forward to seeing old friends and meeting new ones! We're also hiring ML scientists and research engineers @Terray_Tx - reach out to grab coffee👋
Narbe Mardirossian retweeted
Last week we shared some of our recent work on TerraSynth, a generative synthesis planner that addresses the synthesis bottleneck in small-molecule drug discovery.
While generative models are good at proposing molecules with desirable properties, they often propose molecules that are difficult to synthesize in practice, slowing down DMTA cycles.
TerraSynth makes synthesis planning a native part of the design loop rather than a problem to solve afterward. Integrating TerraSynth into our EMMI platform has helped us focus on the molecules that are worth making to advance our programs.
Thanks to Zack and @mileswhen for their incredible work on this.
Narbe Mardirossian retweeted
@Terray_Tx AI powered experimentation for small-molecule drug discovery!
Narbe Mardirossian retweeted
Terray has been built at the intersection from the moment it was founded, and we recently expanded our digital and visual footprint to reflect this.
Our CEO, Jacob Berlin, PhD and CFO, Eli Berlin went into the philosophy at Terray, what makes us stand apart, and how we are bringing together experimentation and AI to transform the speed, cost, and, most importantly, success rate of small molecule drug discovery.
Check out our new video about our approach and how EMMI, our platform for drug discovery and development, enables our teams to innovate.
For the full blog check out the link in comments!
Narbe Mardirossian retweeted
Congrats to Matteo Rossi, Ryan Pederson, Stephan Thaler, and the rest of the team on the ICML paper. arxiv.org/html/2602.07735v1
Narbe Mardirossian retweeted
Last week we announced a big leap forward for universal potency models with EMMI Predict: TerraBind. TerraBind delivers best-in-class potency prediction while running 26x faster and reducing inference cost by 96% relative to standard industry potency models.
A key driver of this performance is our collaboration with @nvidia and the integration of the NVIDIA cuEquivariance library. By centering its computational core on triangle attention and multiplication, TerraBind's architecture is uniquely positioned to fully leverage cuEquivariance's GPU-optimized kernels, providing a 3-4x speedup compared to standard implementations.
With EMMI Predict: TerraBind at the center of our Generate-Predict-Select workflow, this combination of proprietary data, purpose-built models, and NVIDIA-accelerated hardware is transforming how we discover and optimize small-molecule therapeutics. We're excited to keep pushing the boundaries of predictive chemistry with partners like NVIDIA as we work to bring better medicines to patients faster.
Read our blog terraytx.com/insights/emmi-p…
Read our arxiv paper arxiv.org/abs/2602.07735
Narbe Mardirossian retweeted
NEW: Terray has taken a contrarian AI approach, building a non-diffusion-based model for binding affinity predictions
They shared some H2H results against Boltz-2, a popular open-source model, showing 20% more accuracy + 26x faster to run:
endpoints.news/terray-says-i…
Narbe Mardirossian retweeted
Most AI drug discovery tools can only evaluate thousands of molecules at a time.
Powered by Nvidia, Terray's new model TerraBind can screen billions 26x faster and with better accuracy.
Faster screening = faster cures 🚀🧬 Proud investor in @Terray_Tx
terraytx.com/insights/emmi-p…
Narbe Mardirossian retweeted
Today we announced EMMI Predict: TerraBind, our universal potency model that dramatically expands Terray’s ability to move molecules to the clinic faster. Far outpacing publicly available models, TerraBind is a cornerstone of Terray’s end-to-end workflow for small molecule discovery and development.
Read our blog: terraytx.com/insights/emmi-p…
Narbe Mardirossian retweeted
Awesome new results and great use of NVIDIA accelerated computing libraries for life sciences!
Today we announced EMMI Predict: TerraBind, our universal potency model that dramatically expands Terray’s ability to move molecules to the clinic faster. Far outpacing publicly available models, TerraBind is a cornerstone of Terray’s end-to-end workflow for small molecule discovery and development.
Read our blog: terraytx.com/insights/emmi-p…
Narbe Mardirossian retweeted
How does this have traction? What gains does anyone think this gets over GPUs to get 20x over H100s, or do they assume the audience isn't sophisticated enough to ask that question with any rigor and just sees nonsense like "burned the transformer into the chip"?
unavailable
Narbe Mardirossian retweeted
BREAKING — Senator Lee has just withdrawn his public lands sell-off provision!
Thanks to your efforts, the American people — and our public lands — have won!
🏔️🏔️🏔️
Narbe Mardirossian retweeted
Definitely a cool dataset! An Allegro-Tensormol Behaving physically and optimizing off RdKit after like 30k rows of training. After a little validation, happy to OS for anyone who like minimalist, scalable, charged UFFs.
Narbe Mardirossian retweeted
We're Hiring. ats.rippling.com/terraytx/jo…





















