All Jesus ! |Research Assistant| 3D Vision @VisualAI4Humans | |Ex @KPMG_NG|T.A @DataScienceNIG|Co-Founder @lautechdatasci|Eph 2:10| - Open for internships
Lagos
Joined April 2011
- Tweets2.8K
- Following2K
- Followers1.1K
- Likes6.8K
Pinned Tweet
I am excited to announce that our work on "Mirror-Aware Neural Humans" 🤩 received the best paper award at the weakly supervised computer vision workshop at @deepindaba and a poster prize 🏆 at the main event. #DLI2023 #Indaba2023
(wscv-indaba.github.io/2023#a…)
Thread 🧵 1/n
#SirDaniel retweeted
Applying for a PhD in ML/CV this cycle?
Sharing my application tracker from last cycle programs, faculty I shortlisted. I mostly applied in Efficient ML and vision. Please reverify deadlines for current cycle.
docs.google.com/spreadsheets…
#SirDaniel retweeted
I'll be in SF next week for #COLM2026 to present our paper at the tokenization workshop!
I'd love to chat about *token-efficient language models*, long-horizon training, and ofc, language modeling beyond English!
#SirDaniel retweeted
Balancing background and foreground is the key to better AI video generation. ⚖️
In this talk, @danielajisafe discuss an optimized framework that enhances model control adherence.
Watch the session recording: youtu.be/SjjOPiV5tDI
#SirDaniel retweeted
Applications are open for the Cohere Labs Community ML Summer School.
• Free online ML summer school with live sessions
• Learn from researchers and engineers at Google DeepMind, Meta, Cohere, Liquid AI, Arize and more
• Topics include Agentic AI, LLMs, World Models, Computer Vision, ML Math, Evaluations, Edge AI and AI Careers
• Interactive sessions with leading ML researchers and practitioners
• Open to students, developers, researchers and AI enthusiasts worldwide
• Digital certificate of participation
If you're serious about building a career in AI, this is one of the best free learning opportunities this summer.
Register: events.zoom.us/ev/AqU4vnBuHB…
#SirDaniel retweeted
📢 Live in a few minutes — join us!
@Cohere_Labs' Computer Vision community leads, Mayank Bhaskar (@cataluna84) and Benedict (@Arkhymadhe), are hosting a special session with Daniel Ajisafe on a topic every video-AI practitioner should care about: how to make video generation models faithfully follow user intent — with minimal edits, not full re-renders.
This matters because current video diffusion pipelines are expensive and brittle to fine-grained edits. @danielajisafe's work tackles that head-on.
📄 Paper: "Making Video Models Adhere to User Intent with Minor Adjustments"
arxiv.org/abs/2603.19672
📅 Today, 14th July 2026
⏰ 11:00 AM EDT
🔗 Join here: luma.com/syz5r5pg?tk=LCDIEq
If you work in generative video, diffusion models, or multimodal AI — this is worth 60 minutes of your time. Tag a colleague who'd want in.
#ComputerVision #GenerativeAI #VideoGeneration #MachineLearning
📌Our work on controllable video generation is being presented at the @CVPR 2026 AI for Creative Visual Content Workshop!
💡TLDR: ironically, minor deviations from control signals allow for better control adherence.
🧵(1/n)
#CVPR2026 @cveu_workshop @RBCBorealis @UBC_CS
#SirDaniel retweeted
We’re thrilled to share our latest work: FLEXITOKENS!
In this work, we introduce language models with learnable tokenizers for making tokenization truly flexible during adaptation. See example below ↓
1/n
Our paper at @cveu_workshop @CVPRConf 😊
✨ TDLR: Small deviations matter, and can improve control adherence for video models
#SirDaniel retweeted
I like simple solutions!
📌Our work on controllable video generation is being presented at the @CVPR 2026 AI for Creative Visual Content Workshop!
💡TLDR: ironically, minor deviations from control signals allow for better control adherence.
🧵(1/n)
#CVPR2026 @cveu_workshop @RBCBorealis @UBC_CS
📌Our work on controllable video generation is being presented at the @CVPR 2026 AI for Creative Visual Content Workshop!
💡TLDR: ironically, minor deviations from control signals allow for better control adherence.
🧵(1/n)
#CVPR2026 @cveu_workshop @RBCBorealis @UBC_CS
🧵(3/n)
If you are working on conditional inputs or controllable generation, I would be happy to chat 🥳
Project page: ubc-vision.github.io/MinorAd…
🧵(2/n)
✅ Better trajectory faithfulness
✅ Strong preference in controlled generation quality
✅ Outperforms existing baselines on AnimalKingdom
#SirDaniel retweeted
Less than 4% of PhD candidates in CS-related fields are people of African descent.
The 2026 Emerging Leaders in AI (ELAI) program is helping change that through mentorship, grad school prep, mock interviews, and community.
Apply by June 21st:
bit.ly/4tR0cTf
#SirDaniel retweeted
Introducing the 2026-27 Vector Scholarship in AI recipients! 🌟
We're thrilled to announce 100 exceptional graduate students across Ontario have each received a $17,500 scholarship – $1.75 million invested in Canada's AI future.
This year's cohort comes from 13 universities, spanning computer science, engineering, health informatics, data science, and business. Now in its ninth year, the program has supported more than 900 students at Ontario universities since 2018.
"We're proud to support 100 exceptional students this year with $17,500 scholarships, but the real value of the Vector Scholarship in AI is the powerful ecosystem they join. From day one, recipients are connected to mentors, peers and industry leaders who help transform them from graduate students into the researchers, entrepreneurs and practitioners who will define the next decade of AI in this province." – Melissa Judd, VP, Research Operations and Academic Partnerships, Vector Institute
Congratulations to all of this year’s recipients and all the best in your incredible journeys ahead.
Learn more at na3.hubs.ly/y0sQm80
#SirDaniel retweeted
Say hello to Gemini 3.1 Flash Live. 🗣️
Our latest audio model delivers more natural conversations with improved function calling – making it more useful and informed. Here’s what’s new 🧵
#SirDaniel retweeted
We’re looking to attract the world’s brightest and best students!
Canada is home to world-class institutions and offers clear pathways for international students to pursue master’s and doctoral degrees.
Top reasons to get your graduate degree in Canada
• Simpler processing for most graduate degree students
• Faster timeline - 2 weeks for doctoral student applications
• Family members can apply to come with you
• Work in Canada after you graduate
Learn more: bit.ly/4k2hsBx
ALT Get your graduate degree in Canada
#SirDaniel retweeted
🌍 Get Involved in AFRICHI 2027!
AFRICHI 2027 will take place in Lagos, Nigeria in April 2027, & we are inviting members of the community to join the Organizing Committee.
Interested in contributing to the conference?
Apply here: forms.gle/PU5QLoo6x6cscG3o8
#AFRICHI #AFRICHI2027
#SirDaniel retweeted
We’re looking to attract the world’s brightest and best students!
Canada is home to world-class institutions and offers clear pathways for international students to pursue master’s and doctoral degrees.
Top reasons to get your graduate degree in Canada
• Simpler processing for most graduate degree students
• Faster timeline - 2 weeks for doctoral student applications
• Family members can apply to come with you
• Work in Canada after you graduate
Learn more: bit.ly/4k2hsBx
ALT Get your graduate degree in Canada
#SirDaniel retweeted
Thrilled to announce the 3rd African Computer Vision Summer School (ACVSS)
👉acvss.ai
🎓Learn computer vision from the best scientists
🌍Google, Accra, Ghana
📆July 19-29, 2026
🎓Apply before March 1st (full grants available)
❤️ Follow us
#ACVSS #computervision #ai
#SirDaniel retweeted
🚨 Announcing our #CVPR2026 the 2nd Workshop on Multi-Modal Reasoning for Agentic Intelligence @CVPR @CVPRConf.
🚀 Call for Papers!!!
We accept regular papers limited to eight pages in the CVPR style.
Timeline:
📅 Submission open: February 1th 2026, 23:59 AoE Time
📣 Submission deadline: March 15th 2026, 23:59 AoE Time
Submit now: openreview.net/group?id=thec…
🌐 Learn more at our Website: mmragi.github.io/mmragi/
Kudos to our amazing co-organizers @9LdROhjZE56jSh9 , @zixianma02 , Anda Epure, @kamath_amita , @MahtabBg , @alexttoshev , @RanjayKrishna , @lucy_x_shi , @_anniechen_ , @philiptorr
#SirDaniel retweeted
We trained diffusion models on a billion LLM activations, and we want you to use them!
New preprint: Learning a Generative Meta-Model of LLM Activations
Joint work with @feng_jiahai, @trevordarrell, @AlecRad, @JacobSteinhardt.
More in thread 🧵