Juan Carlos Niebles
@jcniebles.bsky.social
Computer Vision, MultiModal AI Agents, Video AI
Research Director at salesforceairesearch.com
Adjunct Professor at cs.stanford.edu & svl.stanford.edu
🔗 www.niebles.net
Research Director at salesforceairesearch.com
Adjunct Professor at cs.stanford.edu & svl.stanford.edu
🔗 www.niebles.net
Pinned
Exploring Diffusion Transformer Designs via Grafting
Exploring Diffusion Transformer Designs via Grafting
grafting.stanford.edu
📢📢 Exciting news!
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Our #NeurIPS2025 oral presentation is starting in a few minutes!
Join us:
⏰3:30 pm
📍 Ballroom 6AB
grafting.stanford.edu
arxiv.org/abs/2506.05340
Join us:
⏰3:30 pm
📍 Ballroom 6AB
grafting.stanford.edu
arxiv.org/abs/2506.05340
December 4, 2025 at 11:00 PM
Our #NeurIPS2025 oral presentation is starting in a few minutes!
Join us:
⏰3:30 pm
📍 Ballroom 6AB
grafting.stanford.edu
arxiv.org/abs/2506.05340
Join us:
⏰3:30 pm
📍 Ballroom 6AB
grafting.stanford.edu
arxiv.org/abs/2506.05340
Such a great two days of workshops! Fuelled by inspiring talks and excellent reconnections with friends and colleagues—definitely my favorite part of the conference.
Missed my talk on AI Agents: from Language to Multimodal Reasoning?
Summary and slides are here:
www.niebles.net/blog/2025/mm...
Missed my talk on AI Agents: from Language to Multimodal Reasoning?
Summary and slides are here:
www.niebles.net/blog/2025/mm...
October 21, 2025 at 5:27 PM
Such a great two days of workshops! Fuelled by inspiring talks and excellent reconnections with friends and colleagues—definitely my favorite part of the conference.
Missed my talk on AI Agents: from Language to Multimodal Reasoning?
Summary and slides are here:
www.niebles.net/blog/2025/mm...
Missed my talk on AI Agents: from Language to Multimodal Reasoning?
Summary and slides are here:
www.niebles.net/blog/2025/mm...
Talk is done!
Shared our work on Multimodal AI Agents at the #ICCV2025 Workshop on Multi-Modal Reasoning. 🤖
All the slides, key papers, and the research journey are consolidated in this new blog post:
📄https://www.niebles.net/blog/2025/mmagents/
@iccv.bsky.social
Shared our work on Multimodal AI Agents at the #ICCV2025 Workshop on Multi-Modal Reasoning. 🤖
All the slides, key papers, and the research journey are consolidated in this new blog post:
📄https://www.niebles.net/blog/2025/mmagents/
@iccv.bsky.social
October 21, 2025 at 12:49 AM
Talk is done!
Shared our work on Multimodal AI Agents at the #ICCV2025 Workshop on Multi-Modal Reasoning. 🤖
All the slides, key papers, and the research journey are consolidated in this new blog post:
📄https://www.niebles.net/blog/2025/mmagents/
@iccv.bsky.social
Shared our work on Multimodal AI Agents at the #ICCV2025 Workshop on Multi-Modal Reasoning. 🤖
All the slides, key papers, and the research journey are consolidated in this new blog post:
📄https://www.niebles.net/blog/2025/mmagents/
@iccv.bsky.social
We will be presenting Strefer today at Poster 52 9:30-10:30am, join us to learn more about our work on Video-Languange at @salesforce.com AI Research @iccv.bsky.social #ICCV2025
strefer.github.io
arxiv.org/abs/2509.03501
strefer.github.io
arxiv.org/abs/2509.03501
October 20, 2025 at 7:33 PM
We will be presenting Strefer today at Poster 52 9:30-10:30am, join us to learn more about our work on Video-Languange at @salesforce.com AI Research @iccv.bsky.social #ICCV2025
strefer.github.io
arxiv.org/abs/2509.03501
strefer.github.io
arxiv.org/abs/2509.03501
Check out the latest on Strefer: model & data are now available!
arxiv.org/abs/2509.03501
We will see you at #ICCV2025 🏖️
arxiv.org/abs/2509.03501
We will see you at #ICCV2025 🏖️
October 17, 2025 at 8:55 PM
Check out the latest on Strefer: model & data are now available!
arxiv.org/abs/2509.03501
We will see you at #ICCV2025 🏖️
arxiv.org/abs/2509.03501
We will see you at #ICCV2025 🏖️
📢📢 Exciting news!
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Exploring Diffusion Transformer Designs via Grafting
Exploring Diffusion Transformer Designs via Grafting
grafting.stanford.edu
September 22, 2025 at 9:54 PM
📢📢 Exciting news!
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Our paper, "Exploring Diffusion Transformer Designs via Grafting," has been accepted as an Oral at #NeurIPS2025, with only 77 out of 21k submissions receiving this honor.
📄Paper: arxiv.org/abs/2506.05340
🌎Website: grafting.stanford.edu
🧑🏻💻Code: github.com/keshik6/graf...
Strefer: our new work for auto-generating instruction data on space–time–focused video tasks: spatiotemporal reasoning, space-time reference understanding, etc. for Video LLMs
✅ Auto & scalable
✅ Fine-grained, space–time–grounded queries
✅ Effective
📄: arxiv.org/abs/2509.03501
🌐: strefer.github.io
✅ Auto & scalable
✅ Fine-grained, space–time–grounded queries
✅ Effective
📄: arxiv.org/abs/2509.03501
🌐: strefer.github.io
Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Language Models (Video LLM...
arxiv.org
September 4, 2025 at 6:36 PM
Strefer: our new work for auto-generating instruction data on space–time–focused video tasks: spatiotemporal reasoning, space-time reference understanding, etc. for Video LLMs
✅ Auto & scalable
✅ Fine-grained, space–time–grounded queries
✅ Effective
📄: arxiv.org/abs/2509.03501
🌐: strefer.github.io
✅ Auto & scalable
✅ Fine-grained, space–time–grounded queries
✅ Effective
📄: arxiv.org/abs/2509.03501
🌐: strefer.github.io
Check out a new episode of The AI Research Lab - Explained on Multimodal AI.
Had a blast creating this with the @salesforce.com team!
youtu.be/r98jGdLtO6Q
Had a blast creating this with the @salesforce.com team!
youtu.be/r98jGdLtO6Q
What is Multimodal AI? | The AI Research Lab - Explained
YouTube video by Salesforce
youtu.be
June 16, 2025 at 11:18 PM
Check out a new episode of The AI Research Lab - Explained on Multimodal AI.
Had a blast creating this with the @salesforce.com team!
youtu.be/r98jGdLtO6Q
Had a blast creating this with the @salesforce.com team!
youtu.be/r98jGdLtO6Q
Congrats Chaitanya on winning the BEST PAPER AWARD 🥇 🏆
Check out details of our work:
arxiv.org/abs/2504.12513
Check out details of our work:
arxiv.org/abs/2504.12513
June 12, 2025 at 9:07 PM
Congrats Chaitanya on winning the BEST PAPER AWARD 🥇 🏆
Check out details of our work:
arxiv.org/abs/2504.12513
Check out details of our work:
arxiv.org/abs/2504.12513
Our first #cvpr2025 poster is up!
🕐Come check it out right now until 13:00
“AdaVid: Adaptive Video-Language Pretraining”
🪧ExHall D Poster # 203
📝 arxiv.org/abs/2504.12513
🕐Come check it out right now until 13:00
“AdaVid: Adaptive Video-Language Pretraining”
🪧ExHall D Poster # 203
📝 arxiv.org/abs/2504.12513
June 12, 2025 at 5:01 PM
Our first #cvpr2025 poster is up!
🕐Come check it out right now until 13:00
“AdaVid: Adaptive Video-Language Pretraining”
🪧ExHall D Poster # 203
📝 arxiv.org/abs/2504.12513
🕐Come check it out right now until 13:00
“AdaVid: Adaptive Video-Language Pretraining”
🪧ExHall D Poster # 203
📝 arxiv.org/abs/2504.12513
Just finished a day at the #CVPR2025 Area Chair workshop. Lots of interesting discussions and ideas, reconnection with colleagues and friends.
Had the chance to present our ViUnit poster to fellow ACs. If you missed it, come to our Sunday poster session.
See details in the 🧵⬇️
Had the chance to present our ViUnit poster to fellow ACs. If you missed it, come to our Sunday poster session.
See details in the 🧵⬇️
June 11, 2025 at 2:17 AM
Just finished a day at the #CVPR2025 Area Chair workshop. Lots of interesting discussions and ideas, reconnection with colleagues and friends.
Had the chance to present our ViUnit poster to fellow ACs. If you missed it, come to our Sunday poster session.
See details in the 🧵⬇️
Had the chance to present our ViUnit poster to fellow ACs. If you missed it, come to our Sunday poster session.
See details in the 🧵⬇️
Excited to attend #CVPR2025 in Nashville! 🤠 Looking forward to a fantastic week of cutting-edge computer vision research and connecting with the community.
@cvprconference.bsky.social
@cvprconference.bsky.social
June 10, 2025 at 5:37 AM
Excited to attend #CVPR2025 in Nashville! 🤠 Looking forward to a fantastic week of cutting-edge computer vision research and connecting with the community.
@cvprconference.bsky.social
@cvprconference.bsky.social
Just dropped a new blog post: "Level up your Agents: Teaching Vision-Language Models to Play by the Rules"! We're exploring how to make Vision-Language Models (VLMs) even smarter at interactive tasks.
blog: www.niebles.net/blog/2025/vl...
arxiv: arxiv.org/abs/2505.03181
#multimodalAI #agents #VLM
blog: www.niebles.net/blog/2025/vl...
arxiv: arxiv.org/abs/2505.03181
#multimodalAI #agents #VLM
June 4, 2025 at 7:44 PM
Just dropped a new blog post: "Level up your Agents: Teaching Vision-Language Models to Play by the Rules"! We're exploring how to make Vision-Language Models (VLMs) even smarter at interactive tasks.
blog: www.niebles.net/blog/2025/vl...
arxiv: arxiv.org/abs/2505.03181
#multimodalAI #agents #VLM
blog: www.niebles.net/blog/2025/vl...
arxiv: arxiv.org/abs/2505.03181
#multimodalAI #agents #VLM
Check out this great intro to Large Action Models, the key engine powering the AI Agent revolution. 🤖
By @salesforce.com AI Research’s Shelby Heinecke.
See video here:
youtube.com/watch?v=vlvv...
By @salesforce.com AI Research’s Shelby Heinecke.
See video here:
youtube.com/watch?v=vlvv...
What Are Large Action Models? | The AI Research Lab - Explained
YouTube video by Salesforce
youtube.com
May 12, 2025 at 6:14 PM
Check out this great intro to Large Action Models, the key engine powering the AI Agent revolution. 🤖
By @salesforce.com AI Research’s Shelby Heinecke.
See video here:
youtube.com/watch?v=vlvv...
By @salesforce.com AI Research’s Shelby Heinecke.
See video here:
youtube.com/watch?v=vlvv...
Reposted by Juan Carlos Niebles
@salesforce.com #AI Research has a new series called "AI Explained."
🎬 "The AI Research Lab - Explained" debuts with our groundbreaking work on Large Action Models! Sr. Mgr Shelby Heinecke reveals how we're training these specialized models to generate precise, executable actions. t.co/XLhlN2EZyk
🎬 "The AI Research Lab - Explained" debuts with our groundbreaking work on Large Action Models! Sr. Mgr Shelby Heinecke reveals how we're training these specialized models to generate precise, executable actions. t.co/XLhlN2EZyk
https://bit.ly/4kfipp4
t.co
May 12, 2025 at 6:02 PM
@salesforce.com #AI Research has a new series called "AI Explained."
🎬 "The AI Research Lab - Explained" debuts with our groundbreaking work on Large Action Models! Sr. Mgr Shelby Heinecke reveals how we're training these specialized models to generate precise, executable actions. t.co/XLhlN2EZyk
🎬 "The AI Research Lab - Explained" debuts with our groundbreaking work on Large Action Models! Sr. Mgr Shelby Heinecke reveals how we're training these specialized models to generate precise, executable actions. t.co/XLhlN2EZyk
Reposted by Juan Carlos Niebles
Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!
cvpr.thecvf.com/Conferences/...
cvpr.thecvf.com/Conferences/...
May 10, 2025 at 1:59 PM
Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!
cvpr.thecvf.com/Conferences/...
cvpr.thecvf.com/Conferences/...
Will AI be a "bicycle for the mind" boosting our creativity, or could it overshadow our own abilities? 🤔
📝 My latest blog explores this fascinating question!
Read more here: www.niebles.net/blog/2025/cr...
#AI #creativity #artificialintelligence
📝 My latest blog explores this fascinating question!
Read more here: www.niebles.net/blog/2025/cr...
#AI #creativity #artificialintelligence
www.niebles
May 7, 2025 at 5:12 PM
Will AI be a "bicycle for the mind" boosting our creativity, or could it overshadow our own abilities? 🤔
📝 My latest blog explores this fascinating question!
Read more here: www.niebles.net/blog/2025/cr...
#AI #creativity #artificialintelligence
📝 My latest blog explores this fascinating question!
Read more here: www.niebles.net/blog/2025/cr...
#AI #creativity #artificialintelligence
With AI models trained in colossal datasets, does the traditional concept of “generalization” (performing well on *unseen* data) still hold?
My latest blog outlines this critical question. Join the discussion! #AI #MachineLearning #Generalization
www.niebles.net/blog/2025/ga...
My latest blog outlines this critical question. Join the discussion! #AI #MachineLearning #Generalization
www.niebles.net/blog/2025/ga...
April 22, 2025 at 5:21 PM
With AI models trained in colossal datasets, does the traditional concept of “generalization” (performing well on *unseen* data) still hold?
My latest blog outlines this critical question. Join the discussion! #AI #MachineLearning #Generalization
www.niebles.net/blog/2025/ga...
My latest blog outlines this critical question. Join the discussion! #AI #MachineLearning #Generalization
www.niebles.net/blog/2025/ga...
Reposted by Juan Carlos Niebles
Always love Juan Carlos's blogs! 😍 His latest dives into how our #CVPR2025 work, ViUniT, catches sneaky bugs in visual programs using synthetic visual unit tests.
Fewer lucky mistakes, better and more reliable results, and even small open models beating GPT-4o-mini. Super cool stuff 👇
Fewer lucky mistakes, better and more reliable results, and even small open models beating GPT-4o-mini. Super cool stuff 👇
New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
April 18, 2025 at 9:38 PM
Always love Juan Carlos's blogs! 😍 His latest dives into how our #CVPR2025 work, ViUniT, catches sneaky bugs in visual programs using synthetic visual unit tests.
Fewer lucky mistakes, better and more reliable results, and even small open models beating GPT-4o-mini. Super cool stuff 👇
Fewer lucky mistakes, better and more reliable results, and even small open models beating GPT-4o-mini. Super cool stuff 👇
New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
April 18, 2025 at 9:08 PM
New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
April 18, 2025 at 5:39 PM
New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!
📰 Blog: niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859
Work by Artemis P & Honglu Z
Just around the corner! 🥁
Stay tuned for the latest from the AI Index. ⬇️⬇️
Stay tuned for the latest from the AI Index. ⬇️⬇️
Want to join the conversation on AI—and be heard? Use trusted insights from the Stanford HAI #AIIndex2025 to spark smarter dialogue and back your ideas with data that matters.
Stay informed with the AI Index, coming April 7: hai.stanford.edu/ai-index
Stay informed with the AI Index, coming April 7: hai.stanford.edu/ai-index
AI Index | Stanford HAI
The mission of the AI Index is to provide unbiased, rigorously vetted, and globally sourced data for policymakers, researchers, journalists, executives, and the general public to develop a deeper unde...
hai.stanford.edu
March 27, 2025 at 4:11 PM
Just around the corner! 🥁
Stay tuned for the latest from the AI Index. ⬇️⬇️
Stay tuned for the latest from the AI Index. ⬇️⬇️
Honored to be named a top 100 AI leader in Colombia! 🇨🇴.
Proud to advance computer vision & multimodal AI at Salesforce AI Research & Stanford Vision and Learning lab.
www.linkedin.com/posts/observ...
#ArtificialIntelligence #ComputerVision #AIResearch #Colombia
Proud to advance computer vision & multimodal AI at Salesforce AI Research & Stanford Vision and Learning lab.
www.linkedin.com/posts/observ...
#ArtificialIntelligence #ComputerVision #AIResearch #Colombia
Los 100 líderes más destacados en Inteligencia Artificial en Colombia en… | Observatorio de la Inteligencia Artificial en Colombia | 15 comments
Los 100 líderes de la Inteligencia Artificial en Colombia!.
🧠💥 Colombia ya no es solo café… también está pariendo genios en Inteligencia Artificial.
En un… | 15 comments on LinkedIn
www.linkedin.com
March 24, 2025 at 4:02 PM
Honored to be named a top 100 AI leader in Colombia! 🇨🇴.
Proud to advance computer vision & multimodal AI at Salesforce AI Research & Stanford Vision and Learning lab.
www.linkedin.com/posts/observ...
#ArtificialIntelligence #ComputerVision #AIResearch #Colombia
Proud to advance computer vision & multimodal AI at Salesforce AI Research & Stanford Vision and Learning lab.
www.linkedin.com/posts/observ...
#ArtificialIntelligence #ComputerVision #AIResearch #Colombia
Exciting news! The 2025 AI Index is coming soon! 🚀 Get ready for a data-driven look at the latest trends and progress in AI. If you want to understand the field, this is your go-to resource. Stay tuned for the release! #AI #ArtificialIntelligence #AIIndex2025
The Stanford HAI #AIIndex2025 report launches April 7. Packed with rigorously vetted data, it provides an independent lens on AI’s progress, its adoption across various sectors, and its far-reaching impact. Be among the first to receive the report: hai.stanford.edu/ai-index
March 24, 2025 at 3:18 PM
Exciting news! The 2025 AI Index is coming soon! 🚀 Get ready for a data-driven look at the latest trends and progress in AI. If you want to understand the field, this is your go-to resource. Stay tuned for the release! #AI #ArtificialIntelligence #AIIndex2025