X / Twitter
Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction.
Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop.
Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost. https://t.co/rAwCafjS4T
GIMM is a new video interpolation method that uses motion modelling to predict motion between frames!
Links ⬇️ https://t.co/jpSkUGZWEs
If you want to become a better software engineer, there are 6 famous books you should read
They cover the 20% of reading you need to do to for 80% of the benefit:
Gnight! Let's celebrate the end of Wednesday! ⚡️🤘 https://t.co/dp5KPni52I
shading.fluid.motion.005
#vidgenmodels #vfx #shading #fluid #motion #technical #ML #generative #neural https://t.co/mzlA6C92Em
Dang, consistent-character has hit 100k runs on Replicate.
https://t.co/Kbp11CKdeS https://t.co/fN3AMTBswf
Animate3D
Animating Any 3D Model with Multi-view Video Diffusion
Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image-conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view attributes, and their results suffer from spatiotemporal inconsistency owing to the inherent ambiguity in the supervision signals. In this work, we present Animate3D, a novel framework for animating any static 3D model. The core idea is two-fold: 1) We propose a novel multi-view video diffusion model (MV-VDM) conditioned on multi-view renderings of the static 3D object, which is trained on our presented large-scale multi-view video dataset (MV-Video). 2) Based on MV-VDM, we introduce a framework combining reconstruction and 4D Score Distillation Sampling (4D-SDS) to leverage the multi-view video diffusion priors for animating 3D objects. Specifically, for MV-VDM, we design a new spatiotemporal attention module to enhance spatial and temporal consistency by integrating 3D and video diffusion models. Additionally, we leverage the static 3D model's multi-view renderings as conditions to preserve its identity. For animating 3D models, an effective two-stage pipeline is proposed: we first reconstruct motions directly from generated multi-view videos, followed by the introduced 4D-SDS to refine both appearance and motion. Qualitative and quantitative experiments demonstrate that Animate3D significantly outperforms previous approaches. Data, code, and models will be open-released.
I had a couple of people in my DM's asking for advice on how to become a ML Engineer.
My answer has been more or less the same each time.
So i put in some effort, did a proper write-up on my blog, and links to some great actionable resources
Link below & in bio https://t.co/3BTK09Fmay