What if we can trace the source of capabilities arising from LLM/other pre-training 🤖? 📢Introducing STRIDE, a framework to trace generations back to training data scalably ⚡️>12x faster for LLM pretraining 🚀more accurate 🦣feasible for large models

<megaphone> The incredible @rishit-dagli.bsky.social took VoMP, his volumetric material predictor, and made it adaptive! This increases the detail of SimReady assets dramatically <see below>

rishit dagli@rishit-dagli.bsky.social · last mo.

What if we can take a few photos and turn it into an interactive physically realistic virtual world🌎? 📢Introducing AdaVoMP (ICML 26): generates volumetric physics fields at high spatial resolution making objects interactive and deformable🦾 🦣16^3x higher res (1024^3) ⚡️more accurate

What if we can take a few photos and turn it into an interactive physically realistic virtual world🌎? 📢Introducing AdaVoMP (ICML 26): generates volumetric physics fields at high spatial resolution making objects interactive and deformable🦾 🦣16^3x higher res (1024^3) ⚡️more accurate

code, models, datasets, and a @hf.co demo for our ICLR 2026 paper VoMP is out!

Masha Sh.@shumash.bsky.social · 4mo ago

🚀 𝗖𝗼𝗱𝗲, 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗱𝗮𝘁𝗮 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲! Convert meshes, Gaussian Splats and more to 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗮𝘀𝘀𝗲𝘁𝘀 with 𝗩𝗼𝗠𝗣 (ICLR2026) - the first feed-forward model to predict fine mechanical properties throughout 3D object volume. Kudos @rishit-dagli.bsky.social, @diwlevin.bsky.social, and team! Links👇

@rishit-dagli.bsky.social's amazing VoMP model is now available for to the people, including a fun demo on @hf.co. Check it out. research.nvidia.com/labs/sil/pro...

VoMP: Predicting Volumetric Mechanical Property Fields

Feed-forward fine-grained physically-based volumetric material properties from Splats, Meshes, NeRFs, etc. which can be used to produce realistic worlds.

research.nvidia.com

Masha Sh.@shumash.bsky.social · 4mo ago

🚀 𝗖𝗼𝗱𝗲, 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗱𝗮𝘁𝗮 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲! Convert meshes, Gaussian Splats and more to 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗮𝘀𝘀𝗲𝘁𝘀 with 𝗩𝗼𝗠𝗣 (ICLR2026) - the first feed-forward model to predict fine mechanical properties throughout 3D object volume. Kudos @rishit-dagli.bsky.social, @diwlevin.bsky.social, and team! Links👇

🚀 𝗖𝗼𝗱𝗲, 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗱𝗮𝘁𝗮 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲! Convert meshes, Gaussian Splats and more to 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗮𝘀𝘀𝗲𝘁𝘀 with 𝗩𝗼𝗠𝗣 (ICLR2026) - the first feed-forward model to predict fine mechanical properties throughout 3D object volume. Kudos @rishit-dagli.bsky.social, @diwlevin.bsky.social, and team! Links👇

just wrote: Deriving a Generalized Kaiming Initialization rishit-dagli.github.io/2026/02/07/g... i know everyone uses normalization, but thought to write down some things i was thinking of

📢want to create realistic dynamic 3D worlds (>100 splats)? my NVIDIA internship project, VoMP, is the first feed-forward approach turning surface geometry into volumetric sim-ready assets with real-world materials. 🌐Project: research.nvidia.com/labs/sil/pro... 📜Paper: arxiv.org/abs/2510.22975

hello world