Yash Bhalgat
@ysbhalgat.bsky.social
PhD at VGG, Oxford w/ Andrew Zisserman, Andrea Vedaldi, Joao Henriques, Iro Laina. Past: Senior RS Qualcomm #AI #Research, UMich, IIT Bombay.
I occasionally post AI memes.
yashbhalgat.github.io
I occasionally post AI memes.
yashbhalgat.github.io
Pinned
Yash Bhalgat
@ysbhalgat.bsky.social
· Nov 28
from kindness import *
Excited to announce the 1st Workshop on 3D-LLM/VLA at #CVPR2025! 🚀 @cvprconference.bsky.social
Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language.
📢 Call for papers: Deadline – April 20, 2025
🌐 Details: 3d-llm-vla.github.io
#llm #3d #Robotics #ai
Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language.
📢 Call for papers: Deadline – April 20, 2025
🌐 Details: 3d-llm-vla.github.io
#llm #3d #Robotics #ai
March 23, 2025 at 9:35 PM
Excited to announce the 1st Workshop on 3D-LLM/VLA at #CVPR2025! 🚀 @cvprconference.bsky.social
Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language.
📢 Call for papers: Deadline – April 20, 2025
🌐 Details: 3d-llm-vla.github.io
#llm #3d #Robotics #ai
Topics: 3D-VLA models, LLM agents for 3D scene understanding, Robotic control with language.
📢 Call for papers: Deadline – April 20, 2025
🌐 Details: 3d-llm-vla.github.io
#llm #3d #Robotics #ai
Reposted by Yash Bhalgat
Our beginner's oriented accessible introduction to modern deep RL is now published in Foundations and Trends in Optimization. It is a great entry to the field if you want to jumpstart into RL!
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
February 22, 2025 at 7:32 PM
Our beginner's oriented accessible introduction to modern deep RL is now published in Foundations and Trends in Optimization. It is a great entry to the field if you want to jumpstart into RL!
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
Need to rig 3D models? 🦖
New work from UCSD and Adobe:
"RigAnything: Template-Free Autoregressive Rigging
for Diverse 3D Assets" Liu et al.
tl;dr: reduces rigging time from 2 mins to 2 secs, works on any shape category & doesn't need predefined templates! 🚀
New work from UCSD and Adobe:
"RigAnything: Template-Free Autoregressive Rigging
for Diverse 3D Assets" Liu et al.
tl;dr: reduces rigging time from 2 mins to 2 secs, works on any shape category & doesn't need predefined templates! 🚀
February 15, 2025 at 1:05 PM
Need to rig 3D models? 🦖
New work from UCSD and Adobe:
"RigAnything: Template-Free Autoregressive Rigging
for Diverse 3D Assets" Liu et al.
tl;dr: reduces rigging time from 2 mins to 2 secs, works on any shape category & doesn't need predefined templates! 🚀
New work from UCSD and Adobe:
"RigAnything: Template-Free Autoregressive Rigging
for Diverse 3D Assets" Liu et al.
tl;dr: reduces rigging time from 2 mins to 2 secs, works on any shape category & doesn't need predefined templates! 🚀
"Latent Radiance Fields with 3D-aware 2D Representations" Zhou et al., #ICLR2025
tl;dr: Novel framework that integrates 3D awareness into VAE latent space using correspondence-aware encoding, enabling high-quality rendered images with ~50% memory savings.
(1/n) 🧵
tl;dr: Novel framework that integrates 3D awareness into VAE latent space using correspondence-aware encoding, enabling high-quality rendered images with ~50% memory savings.
(1/n) 🧵
February 14, 2025 at 10:28 AM
"Latent Radiance Fields with 3D-aware 2D Representations" Zhou et al., #ICLR2025
tl;dr: Novel framework that integrates 3D awareness into VAE latent space using correspondence-aware encoding, enabling high-quality rendered images with ~50% memory savings.
(1/n) 🧵
tl;dr: Novel framework that integrates 3D awareness into VAE latent space using correspondence-aware encoding, enabling high-quality rendered images with ~50% memory savings.
(1/n) 🧵
"EdgeRunner" (#ICLR2025) from #Nvidia & PKU introduces an auto-regressive auto-encoder for mesh generation, supporting up to 4000 faces at 512³ resolution. 🤩
Their mesh tokenization algorithm (adapted from EdgeBreaker) achieves ~50% compression (4-5 tokens per face vs 9), making training efficient.
Their mesh tokenization algorithm (adapted from EdgeBreaker) achieves ~50% compression (4-5 tokens per face vs 9), making training efficient.
February 13, 2025 at 10:34 PM
"EdgeRunner" (#ICLR2025) from #Nvidia & PKU introduces an auto-regressive auto-encoder for mesh generation, supporting up to 4000 faces at 512³ resolution. 🤩
Their mesh tokenization algorithm (adapted from EdgeBreaker) achieves ~50% compression (4-5 tokens per face vs 9), making training efficient.
Their mesh tokenization algorithm (adapted from EdgeBreaker) achieves ~50% compression (4-5 tokens per face vs 9), making training efficient.
Just came across this fascinating paper "CraftsMan3D" - a practical approach to text/image-to-3D generation that mimics how artists actually work!
Code available (pretrained models too) 🤩: github.com/wyysf-98/Cra...
(1/n) 🧵
Code available (pretrained models too) 🤩: github.com/wyysf-98/Cra...
(1/n) 🧵
February 12, 2025 at 10:10 PM
Just came across this fascinating paper "CraftsMan3D" - a practical approach to text/image-to-3D generation that mimics how artists actually work!
Code available (pretrained models too) 🤩: github.com/wyysf-98/Cra...
(1/n) 🧵
Code available (pretrained models too) 🤩: github.com/wyysf-98/Cra...
(1/n) 🧵
Got me excited for a second here 🫠
February 10, 2025 at 12:12 PM
Got me excited for a second here 🫠
📢 Paper accepted to #ICLR2025 🎉
"GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting"
TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching.
🔗: arxiv.org/abs/2408.11085
"GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting"
TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching.
🔗: arxiv.org/abs/2408.11085
January 23, 2025 at 11:42 AM
📢 Paper accepted to #ICLR2025 🎉
"GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting"
TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching.
🔗: arxiv.org/abs/2408.11085
"GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting"
TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching.
🔗: arxiv.org/abs/2408.11085
Switzerland is rolling out solar panels... on railway tracks! 🇨🇭🚄
Swiss startup Sun-ways will run a pilot project turning train lines into clean energy highways.
#renewable #energy for the win 🤓
www.pv-magazine.com/2024/10/04/s...
Swiss startup Sun-ways will run a pilot project turning train lines into clean energy highways.
#renewable #energy for the win 🤓
www.pv-magazine.com/2024/10/04/s...
Switzerland authorizes removable PV plant on railway track
Swiss startup Sun-ways is planning to build a 18 kW pilot PV system between the racks of a 100-m linear section of a railway line in the Swiss canton of Neuchâtel.
www.pv-magazine.com
January 21, 2025 at 9:06 PM
Switzerland is rolling out solar panels... on railway tracks! 🇨🇭🚄
Swiss startup Sun-ways will run a pilot project turning train lines into clean energy highways.
#renewable #energy for the win 🤓
www.pv-magazine.com/2024/10/04/s...
Swiss startup Sun-ways will run a pilot project turning train lines into clean energy highways.
#renewable #energy for the win 🤓
www.pv-magazine.com/2024/10/04/s...
Reposted by Yash Bhalgat
Solar panels are becoming so cheap the Swiss are looking at installing them *between train tracks* !!!
www.pv-magazine.com/2024/10/04/s...
www.pv-magazine.com/2024/10/04/s...
January 13, 2025 at 8:09 AM
Solar panels are becoming so cheap the Swiss are looking at installing them *between train tracks* !!!
www.pv-magazine.com/2024/10/04/s...
www.pv-magazine.com/2024/10/04/s...
Reposted by Yash Bhalgat
🚨🚨🚨 Reminder: closing in 3 weeks time 🚨🚨🚨
Please re-post!
Note: Oxford recruits faculty at Associate Professor level - we have no Assistant Professor level.
Please re-post!
Note: Oxford recruits faculty at Associate Professor level - we have no Assistant Professor level.
Multiple faculty positions at University of Oxford in @oxengsci.bsky.social - Join Us!
Recruiting for 3 Information Engineering faculty - including Robotics, Computer Vision, Machine Learning. Please repost!
Faculty positions in Oxford are typically linked to a college.
⬇️ details in thread ⬇️
Recruiting for 3 Information Engineering faculty - including Robotics, Computer Vision, Machine Learning. Please repost!
Faculty positions in Oxford are typically linked to a college.
⬇️ details in thread ⬇️
January 11, 2025 at 7:28 PM
🚨🚨🚨 Reminder: closing in 3 weeks time 🚨🚨🚨
Please re-post!
Note: Oxford recruits faculty at Associate Professor level - we have no Assistant Professor level.
Please re-post!
Note: Oxford recruits faculty at Associate Professor level - we have no Assistant Professor level.
Came across this LLM visualisation tool today: bbycroft.net/llm
Cool stuff! Let's you visualize each operation or layer in different Transformer architectures, and also explains them on the side. 😍
#llm #visualisation #gpt #ai #transformers
Cool stuff! Let's you visualize each operation or layer in different Transformer architectures, and also explains them on the side. 😍
#llm #visualisation #gpt #ai #transformers
January 9, 2025 at 7:30 AM
Came across this LLM visualisation tool today: bbycroft.net/llm
Cool stuff! Let's you visualize each operation or layer in different Transformer architectures, and also explains them on the side. 😍
#llm #visualisation #gpt #ai #transformers
Cool stuff! Let's you visualize each operation or layer in different Transformer architectures, and also explains them on the side. 😍
#llm #visualisation #gpt #ai #transformers
Reposted by Yash Bhalgat
For other 3D vision newcomers to blue sky: I highly recommend joning @chrisoffner3d.bsky.social 's list to follow the right people ;): go.bsky.app/Cfm9XFe
January 8, 2025 at 2:28 PM
For other 3D vision newcomers to blue sky: I highly recommend joning @chrisoffner3d.bsky.social 's list to follow the right people ;): go.bsky.app/Cfm9XFe
"NeuralSVG: An Implicit Representation for Text-to-Vector Generation"
(1/2) Encodes SVGs as implicit neural representations using a small MLP trained with Score Distillation Sampling (SDS). Maps 2D coordinates to shape/color outputs. Dropout-like technique ensures ordered, layered structures.
(1/2) Encodes SVGs as implicit neural representations using a small MLP trained with Score Distillation Sampling (SDS). Maps 2D coordinates to shape/color outputs. Dropout-like technique ensures ordered, layered structures.
January 8, 2025 at 2:26 PM
"NeuralSVG: An Implicit Representation for Text-to-Vector Generation"
(1/2) Encodes SVGs as implicit neural representations using a small MLP trained with Score Distillation Sampling (SDS). Maps 2D coordinates to shape/color outputs. Dropout-like technique ensures ordered, layered structures.
(1/2) Encodes SVGs as implicit neural representations using a small MLP trained with Score Distillation Sampling (SDS). Maps 2D coordinates to shape/color outputs. Dropout-like technique ensures ordered, layered structures.
Another gem from Bill Freeman, Katie Bouman & team 🌌
A differentiable rendering framework for direct #exoplanet imaging, leveraging wavefront sensing to refine starlight subtraction. Tested on JWST, it approaches noise limits and reveals faint planets like never before! 🚀
#ai #astronomy
A differentiable rendering framework for direct #exoplanet imaging, leveraging wavefront sensing to refine starlight subtraction. Tested on JWST, it approaches noise limits and reveals faint planets like never before! 🚀
#ai #astronomy
January 6, 2025 at 7:13 AM
Another gem from Bill Freeman, Katie Bouman & team 🌌
A differentiable rendering framework for direct #exoplanet imaging, leveraging wavefront sensing to refine starlight subtraction. Tested on JWST, it approaches noise limits and reveals faint planets like never before! 🚀
#ai #astronomy
A differentiable rendering framework for direct #exoplanet imaging, leveraging wavefront sensing to refine starlight subtraction. Tested on JWST, it approaches noise limits and reveals faint planets like never before! 🚀
#ai #astronomy
from kindness import *
November 28, 2024 at 2:55 PM
from kindness import *
📢 Proud that my first-ever #opensource (grid-based) #NeRF implementation hit 100 forks on #github! Just 30 more ⭐️'s to cross 1000. 📈
🔗: github.com/yashbhalgat/...
#instantngp #neuralradiancefield #3d #computervision #research #python
🔗: github.com/yashbhalgat/...
#instantngp #neuralradiancefield #3d #computervision #research #python
GitHub - yashbhalgat/HashNeRF-pytorch: Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/ - yashbhalgat/HashNeRF-pytorch
github.com
November 20, 2024 at 7:58 PM
📢 Proud that my first-ever #opensource (grid-based) #NeRF implementation hit 100 forks on #github! Just 30 more ⭐️'s to cross 1000. 📈
🔗: github.com/yashbhalgat/...
#instantngp #neuralradiancefield #3d #computervision #research #python
🔗: github.com/yashbhalgat/...
#instantngp #neuralradiancefield #3d #computervision #research #python
Excited to share that our work with VAL, IISc on "Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections" has been accepted to #3DV2025
Project page: val.cds.iisc.ac.in/reflecting-r...
Project page: val.cds.iisc.ac.in/reflecting-r...
Reflecting Reality
Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections
val.cds.iisc.ac.in
November 17, 2024 at 1:44 PM
Excited to share that our work with VAL, IISc on "Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections" has been accepted to #3DV2025
Project page: val.cds.iisc.ac.in/reflecting-r...
Project page: val.cds.iisc.ac.in/reflecting-r...
November 17, 2024 at 1:41 PM
We are hosting the 2nd Workshop on Learning #3D with Multi-View Supervision (3DMV) AT #CVPR2024 in Seattle on June 17th!
We are accepting paper submissions on a range of topics. More details on the website: abdullahamdi.com/3dmv2024/
#computervision #ai
We are accepting paper submissions on a range of topics. More details on the website: abdullahamdi.com/3dmv2024/
#computervision #ai
February 13, 2024 at 12:08 PM
We are hosting the 2nd Workshop on Learning #3D with Multi-View Supervision (3DMV) AT #CVPR2024 in Seattle on June 17th!
We are accepting paper submissions on a range of topics. More details on the website: abdullahamdi.com/3dmv2024/
#computervision #ai
We are accepting paper submissions on a range of topics. More details on the website: abdullahamdi.com/3dmv2024/
#computervision #ai