Jonathan Lorraine
@jonlorraine.bsky.social
Research scientist @NVIDIA | PhD in machine learning @UofT. Previously @Google / @MetaAI. Opinions are my own. 🤖 💻 ☕️
Reposted by Jonathan Lorraine
From Tasks to Topology: Dorsal and Ventral Streams Emerge in Optimized Neural Networks https://www.biorxiv.org/content/10.1101/2025.11.16.688720v1
November 17, 2025 at 10:15 AM
From Tasks to Topology: Dorsal and Ventral Streams Emerge in Optimized Neural Networks https://www.biorxiv.org/content/10.1101/2025.11.16.688720v1
🔍 New NVIDIA Spatial Intelligence Lab internship postings for 2026.
Come work with us to advance foundational technologies that enable AI systems to model and interact meaningfully with the world!
Topics on our homepage: research.nvidia.com/labs/sil/
Application link below
Come work with us to advance foundational technologies that enable AI systems to model and interact meaningfully with the world!
Topics on our homepage: research.nvidia.com/labs/sil/
Application link below
NVIDIA Spatial Intelligence Lab (SIL)
Advancing foundational technologies enabling AI systems to perceive, model, and interact with the world.
research.nvidia.com
October 9, 2025 at 4:56 AM
🔍 New NVIDIA Spatial Intelligence Lab internship postings for 2026.
Come work with us to advance foundational technologies that enable AI systems to model and interact meaningfully with the world!
Topics on our homepage: research.nvidia.com/labs/sil/
Application link below
Come work with us to advance foundational technologies that enable AI systems to model and interact meaningfully with the world!
Topics on our homepage: research.nvidia.com/labs/sil/
Application link below
Reposted by Jonathan Lorraine
Join us at #CVPR2025 for a preview of this #NVIDIA tech during a live-coding session. A #GPU back end will be reserved for all attending – just don’t forget to bring your laptop for some hands-on fun!
Wed, Jun 11, 8am-noon, or join in at 10:20 after the break. tinyurl.com/nv-kaolin-cv...
Wed, Jun 11, 8am-noon, or join in at 10:20 after the break. tinyurl.com/nv-kaolin-cv...
June 6, 2025 at 9:20 PM
Join us at #CVPR2025 for a preview of this #NVIDIA tech during a live-coding session. A #GPU back end will be reserved for all attending – just don’t forget to bring your laptop for some hands-on fun!
Wed, Jun 11, 8am-noon, or join in at 10:20 after the break. tinyurl.com/nv-kaolin-cv...
Wed, Jun 11, 8am-noon, or join in at 10:20 after the break. tinyurl.com/nv-kaolin-cv...
🔊 New NVIDIA paper: Audio-SDS 🔊
We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more.
🎧 Demos, audio examples, paper: research.nvidia.com/labs/toronto...
🧵below
We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more.
🎧 Demos, audio examples, paper: research.nvidia.com/labs/toronto...
🧵below
May 9, 2025 at 4:06 PM
🔊 New NVIDIA paper: Audio-SDS 🔊
We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more.
🎧 Demos, audio examples, paper: research.nvidia.com/labs/toronto...
🧵below
We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more.
🎧 Demos, audio examples, paper: research.nvidia.com/labs/toronto...
🧵below
Reposted by Jonathan Lorraine
What if you could control the weather in any video — just like applying a filter?
Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.
Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.
May 2, 2025 at 2:19 PM
What if you could control the weather in any video — just like applying a filter?
Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.
Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.
Reposted by Jonathan Lorraine
🚀 Announcing meshgen (AI in Blender) Update 0.6
🤗 Now supports remote backend via litellm, e.g. Hugging Face, ollama
🎨 UI/UX overhaul
This lays the foundation for Blender agents and more advanced 3D AI models (coming this year)
🤗 Now supports remote backend via litellm, e.g. Hugging Face, ollama
🎨 UI/UX overhaul
This lays the foundation for Blender agents and more advanced 3D AI models (coming this year)
March 14, 2025 at 8:09 PM
🚀 Announcing meshgen (AI in Blender) Update 0.6
🤗 Now supports remote backend via litellm, e.g. Hugging Face, ollama
🎨 UI/UX overhaul
This lays the foundation for Blender agents and more advanced 3D AI models (coming this year)
🤗 Now supports remote backend via litellm, e.g. Hugging Face, ollama
🎨 UI/UX overhaul
This lays the foundation for Blender agents and more advanced 3D AI models (coming this year)
Reposted by Jonathan Lorraine
🧊 New dataset of 50k+ low poly obj meshes
🎢 objaverse subsampled to <500 poly models, converted to untextured objs
🔧 suitable for training autoregressive transformer-based 3D models, which have limited context length, such as LLaMA-Mesh
🎢 objaverse subsampled to <500 poly models, converted to untextured objs
🔧 suitable for training autoregressive transformer-based 3D models, which have limited context length, such as LLaMA-Mesh
March 4, 2025 at 10:28 PM
🧊 New dataset of 50k+ low poly obj meshes
🎢 objaverse subsampled to <500 poly models, converted to untextured objs
🔧 suitable for training autoregressive transformer-based 3D models, which have limited context length, such as LLaMA-Mesh
🎢 objaverse subsampled to <500 poly models, converted to untextured objs
🔧 suitable for training autoregressive transformer-based 3D models, which have limited context length, such as LLaMA-Mesh
Reposted by Jonathan Lorraine
Here's a recap of what happened in AI 3D in 2024
December 30, 2024 at 10:44 PM
Here's a recap of what happened in AI 3D in 2024
🦙New #NVIDIA paper: LLaMA-Mesh 🦙
We enable LLMs to generate 3D meshes by representing them as plain text and fine-tuning, unifying 3D and text modalities in a single model.
🔎 Webpage research.nvidia.com/labs/toronto...
🕹️ Interactive Demo huggingface.co/spaces/Zheng...
💾 Model checkpoint available
We enable LLMs to generate 3D meshes by representing them as plain text and fine-tuning, unifying 3D and text modalities in a single model.
🔎 Webpage research.nvidia.com/labs/toronto...
🕹️ Interactive Demo huggingface.co/spaces/Zheng...
💾 Model checkpoint available
December 12, 2024 at 7:11 PM
🦙New #NVIDIA paper: LLaMA-Mesh 🦙
We enable LLMs to generate 3D meshes by representing them as plain text and fine-tuning, unifying 3D and text modalities in a single model.
🔎 Webpage research.nvidia.com/labs/toronto...
🕹️ Interactive Demo huggingface.co/spaces/Zheng...
💾 Model checkpoint available
We enable LLMs to generate 3D meshes by representing them as plain text and fine-tuning, unifying 3D and text modalities in a single model.
🔎 Webpage research.nvidia.com/labs/toronto...
🕹️ Interactive Demo huggingface.co/spaces/Zheng...
💾 Model checkpoint available
Check out our new #NVIDIA paper: ⚡️Multi-student Diffusion Distillation ⚡️
We make single-step distilled generators better and faster using our new method, multi-student distillation (MSD)!
Explore the project page to learn more: research.nvidia.com/labs/toronto...
We make single-step distilled generators better and faster using our new method, multi-student distillation (MSD)!
Explore the project page to learn more: research.nvidia.com/labs/toronto...
December 4, 2024 at 11:15 PM
Check out our new #NVIDIA paper: ⚡️Multi-student Diffusion Distillation ⚡️
We make single-step distilled generators better and faster using our new method, multi-student distillation (MSD)!
Explore the project page to learn more: research.nvidia.com/labs/toronto...
We make single-step distilled generators better and faster using our new method, multi-student distillation (MSD)!
Explore the project page to learn more: research.nvidia.com/labs/toronto...
🚨 New #NeurIPS2025 paper “Training Data Attribution via Approximate Unrolling” 🚨
Introducing SOURCE: A method to understand how individual training examples influence neural net behavior, allowing us to make AI models more transparent and trustworthy!
📄 Full paper: openreview.net/pdf?id=3NaqG...
Introducing SOURCE: A method to understand how individual training examples influence neural net behavior, allowing us to make AI models more transparent and trustworthy!
📄 Full paper: openreview.net/pdf?id=3NaqG...
November 27, 2024 at 5:41 PM
🚨 New #NeurIPS2025 paper “Training Data Attribution via Approximate Unrolling” 🚨
Introducing SOURCE: A method to understand how individual training examples influence neural net behavior, allowing us to make AI models more transparent and trustworthy!
📄 Full paper: openreview.net/pdf?id=3NaqG...
Introducing SOURCE: A method to understand how individual training examples influence neural net behavior, allowing us to make AI models more transparent and trustworthy!
📄 Full paper: openreview.net/pdf?id=3NaqG...