Avirup Dey @avideypi
3d vision / head avatars CS PhD @UniofBath United Kingdom Joined June 2022-
Tweets134
-
Followers18
-
Following224
-
Likes277
Good news: Soham Parekh, a PhD student in our group, will finally have the bandwidth to focus on his academic career! We just awarded him another scholarship that allows him to work remote.
doing god's work 🙏
Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)
Ashamed of Mr. Tharoor for speaking up for his country instead of pandering his "fans". No progressive liberal should condemn terrorists and their enablers.
Ashamed of Mr. Tharoor for speaking up for his country instead of pandering his "fans". No progressive liberal should condemn terrorists and their enablers.
easy fix: invoke a specialized model (some variant of instant-id) instead of DALLE when working with faces.
easy fix: invoke a specialized model (some variant of instant-id) instead of DALLE when working with faces.
IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos TLDR: A diffusion-based method is used to generate 3D renderable talking heads from a single image, using a single denoising step for real-time. The model can learn from…
It's over. Meta just announced MoCha, a new model that turns text or voice into super realistic talking characters. There is no way to tell anymore... 10 examples: (please unmute)
One hell of a thread!
After hacking GPT-4o's frontend, I made amazing discoveries: 💡The line-by-line image generation effect users see is just a browser-side animation (pure frontend trick) 🔦OpenAI's server sends only 5 intermediate images per generation, captured at different stages 🎾Patch size=8
No... the fear isn't irrelevance, but that's a comforting thing for us technologists to tell ourselves. The fear is degradation. You can sense where this leads even if you can't put your finger on it, which is why so many feel vaguely uneasy. They say they hate it but they…
No... the fear isn't irrelevance, but that's a comforting thing for us technologists to tell ourselves. The fear is degradation. You can sense where this leads even if you can't put your finger on it, which is why so many feel vaguely uneasy. They say they hate it but they… https://t.co/FNM6qL0B2D
DisentTalk: Cross-lingual Talking Face Generation via Semantic Disentangled Diffusion Model TLDR: A hierarchical diffusion-based speech-to-3DMM generator that decomposes FLAME parameters into lip, eye and global regions for better quality. It uses PiRender to get the final…
Pippo: High-Resolution Multi-View Humans from a Single Image TLDR: High-resolution and Multi-View but static human Generation from one image. Uses a DiT to generate the images directly (e.g. no 3D representation), with a control MLP. Imagine this distilled onto one of Meta's…
Decentralized Diffusion Models power stronger models trained on more accessible infrastructure. DDMs mitigate the networking bottleneck that locks training into expensive and power-hungry centralized clusters. They scale gracefully to billions of parameters and generate…
📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. radfoam.github.io arxiv.org/abs/2502.01157 Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ @kwangmoo_yi
Exciting opportunity for those working on avatars. Do sign up!
POV: A chinese company drops a powerful open source reasoning AI model competitive with o1 that neither of your companies have released yet as products while you're attending an inauguration
I'm excited to share what I've been working on during my summer internship at @Microsoft . GASP creates photorealistic, real-time Avatars from an image or short video. Project page: microsoft.github.io/GASP/ Arxiv paper: arxiv.org/abs/2412.07739… Demo Video: youtube.com/watch?v=3oWB7-…

MaudJasper @9P5VlTg6oS5622P
51 Followers 964 Following
Dimitris Tzionas @dimtzionas
2K Followers 955 Following Assistant Professor for Comp. Vision @UvA_Amsterdam 3D human bodies+hands from images. Past: Res. Scientist at @MPI_IS, PhD at @UniBonn, Diploma @Aristoteleio.
Sware @SwarenXiueHs
131 Followers 3K Following
Anushka CVPR 25✈️ @_anushkaagarwal
725 Followers 5K Following Research Engineer Intern @ Flawless|Machine learning Engineer @Neuralgarage| Research Intern @Airlab CMU| 3D Vision
Ian Bach ☯︎ @lan8ach
3K Followers 7K Following 🎨📱 🎹 I build tools that help people create. Product Designer/Director @aiatmeta (prev @spotify @cashapp) @univ_basic • 🇬🇧 in 🇺🇸
Mr Paul bet⚽ @isabel48599
293 Followers 7K Following home of all betting specialized in fixed matchs with 100% winning assurance
Jundan Luo @JundanLuo
70 Followers 273 Following CS Phd student at University of Bath. Interested in intrinsic image decomposition and material reconstruction. Graduation in 2025, open to PostDoc positions
Hmrishav @bandy_hmrishav
216 Followers 752 Following PhD candidate in Computer Vision @SketchXlab @cvssp_research Research @StabilityAI
Syeda Gulnoor Zahra @SyedaZahra95
64 Followers 144 Following PhD student exploring Algorithmic Auditing at ART-AI - University of Bath. MSc Data Science - University of Sheffield.
Davide Moltisanti @davmoltisanti
486 Followers 349 Following Prize Fellow at the University of Bath (tenure track to lecturer/assistant professor)
Jack Saunders @jack_r_saunders
685 Followers 349 Following Talking about everything to do with Facial Avatars | PhD Student | Founder of @realsyncai
Soumitri Chattopadhya... @soumitri2001
197 Followers 702 Following CS PhD student at UNC Chapel Hill @unccs Computer Vision Researcher
ART-AI at Bath @ARTAIBath
707 Followers 291 Following UKRI-funded research programme in Accountable, Responsible and Transparent Artificial Intelligence (ART-AI) @UniofBath
Sayan Deb Sarkar @debsarkar_sayan
520 Followers 638 Following Currently @Microsoft Spatial AI | PhDing @Stanford | MS @CSatETH | Prev - @Qualcomm, @MercedesBenz
Sarosij Bose @SarosijB
49 Followers 370 Following Ph.D. student @UCRiverside @VCG_UCR #ARCS; Research interests: 3D Perception and Robotics
Deedy @deedydas
205K Followers 5K Following VC at @MenloVentures. Formerly founding team @glean, @Google Search. @Cornell CS. Tweets about tech, immigration, India, fitness and search.
#ICCV2025 @ICCVConference
11K Followers 63 Following Official account for the IEEE/CVF International Conference on Computer Vision. #ICCV2025 Honolulu 🇺🇸 Hosted by @natanielruizg @anfurnari @YVinker @CSProfKGD
Abhijit Iyer-Mitra @Iyervval
294K Followers 2K Following 🔸HRH The ArchBitchess of Mylapore🔸Class Oppressor🔸I make Genghis Khan look like a humanitarian🔸My cigars cost more than your education🔸Pronouns 🖕🏾/🤛🏾
Felix Taubner @taubnerfelix
289 Followers 142 Following Intern @ Meta | PhD Student at University of Toronto, working on generative 3D animation and digital humans
Higgsfield AI 🧩 @higgsfield_ai
70K Followers 9 Following The ultimate AI-powered platform for creators
George Kopanas @gkopanas
3K Followers 414 Following @runwayml fiddling with video models and 3d -- inventor of Gaussian Splatting -- a climbing gym owner back at home -- previously @Google @Adobe @Inria @Arm
David @DavidSHolz
92K Followers 8K Following founder @midjourney, prev founder leap motion, nasa, max planck - random vibeposting @davidvibesonly
Lilian Weng @lilianweng
163K Followers 166 Following Co-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
Rodrigo Mira @RodrigomiraA
320 Followers 568 Following Postdoc @MetaAI, PhD grad @imperialcollege, ex-research intern 2x @MetaAI 1x @sony_jpn. Audio-visual speech + SSL + generative modelling.
Tavus @heytavus
4K Followers 423 Following We’re a research lab building AI humans: real-time, perceptive agents that close the gap between us & machines. Get emotional intelligence at machine scale.
Lucky Iyinbor @Luckyballa
4K Followers 927 Following Physics Simulation | Geometry Processing | Computer Graphics | AR/VR
Yulia Gryaditskaya @ygryaditskaya
447 Followers 207 Following Creative and controllable AI Researcher @ Adobe
Speech Graphics @speechgraphics
803 Followers 307 Following Award-winning facial animation from audio alone. Empowers developers to make the games they want. Check out our enterprise proposition, @RapportCloud
Tobias Kirschstein @TobiasKirschst1
570 Followers 92 Following PhD Student at the Visual Computing & Artificial Intelligence Lab @ TUM
Ruiqi Gao @RuiqiGao
9K Followers 779 Following Research scientist @GoogleDeepmind | Generative models. Veo3, Veo2, CAT3D, Imagen Video, etc. | Mom of Mochi.
Jia-Bin Huang @jbhuang0604
65K Followers 284 Following
Mirela Ostrek @MirelaOstrek
9 Followers 18 Following CS PhD @ Max Planck Institute for Intelligent systems. #MPI_IS
neoknowstic @neoknowstic
59 Followers 2 Following An unfiction and educational channel explaining AI scientific research and AI Safety. YouTube channel: https://t.co/uM8Uj6dwuF
Jonathon Luiten @JonathonLuiten
3K Followers 2K Following Research Scientist at Meta Reality Labs in Boston Prev PhD at RWTH Aachen + Carnegie Mellon + Uni Oxford Dynamic 3D Gaussians + SplaTAM + HOTA + more From NZ
Jack Morris @jxmnop
45K Followers 975 Following research @cornell @meta // language models, information theory, science of AI
Kai Zhang @KaiZhang9546
1K Followers 453 Following Training image/video GenAI foundation models at Adobe. Opinions are my own.
Anushka CVPR 25✈️ @_anushkaagarwal
725 Followers 5K Following Research Engineer Intern @ Flawless|Machine learning Engineer @Neuralgarage| Research Intern @Airlab CMU| 3D Vision
Flawless @Flawlessai
9K Followers 69 Following Cinema-grade, ethical AI-powered editing tools designed by filmmakers, for filmmakers. Refine dialogue, enhance performances and reduce shoot time.
Pierre Ablin @PierreAblin
6K Followers 361 Following https://t.co/sNXqNTO0Vm Machine learning research @Apple
Ishan Misra @imisra_
7K Followers 245 Following Director, GenAI Research @Meta. Tech Lead of Movie Gen Meta. Past: MIT TR35, Llama3, Emu Video, ImageBind, DINO. Tweets and opinions are my own.
Amir Habibian @amir_habibian
1K Followers 163 Following Research Scientist (Director) @Qualcomm AI Research
Thiemo Alldieck @thiemoall
1K Followers 499 Following Research Scientist @GoogleDeepMind | 3D Computer Vision & Machine Learning
Berkeley AI Research @berkeley_ai
225K Followers 367 Following We're graduate students, postdocs, faculty and scientists at the cutting edge of artificial intelligence research.
Tali Dekel @talidekel
2K Followers 302 Following Associate Professor @ Weizmann Institute Research Scientist @ Google DeepMind
Peter Wonka @peter_wonka
985 Followers 102 Following Prof. of Computer Science at KAUST | Computer Vision, Machine Learning, Computer Graphics, Deep Learning
Simon Giebenhain @SGiebenhain
470 Followers 217 Following PhD Student at TUM. Interested in virtual Avatars and Neural Scene Representations.
Yawar Siddiqui @yawarnihal
1K Followers 568 Following Researcher in 3D Computer Vision at Meta. Views expressed are my own.
Ashkan Mirzaei @ashmrz10
878 Followers 312 Following Research Scientist @Snap Previously @UofT, @NVIDIAAI, @samsungresearch Opinions are mine.
Ayan Das @dasayan05
997 Followers 1K Following Research Scientist @Huawei R&D UK | PhD | Generative Models | Theory & Applied | Diffusion is ❤️ | Blogs @ https://t.co/wlzHeUFhk2 | 🇬🇧 🇮🇳
Dr. Deblina Bhattacha... @deblinaforAI
232 Followers 168 Following Assistant Professor of CS @UniofBath 🇬🇧| Ph.D. @EPFL🇨🇭| Publicity Co-Chair @CVPR 2025| Co-chair WiCV @CVPR| General Chair- AI for Visual Arts
Neel Nanda @NeelNanda5
30K Followers 123 Following Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Stella Bounareli @sbounareli
17 Followers 137 Following
julieta @yoknapathawa
779 Followers 0 Following Currently @RealityLabs. Prev researcher @Waabi_ai, @UberATG. PhD @UBC_CS. Now at https://t.co/tJBTiKrEXU
Lea Müller @LeaMue27
791 Followers 281 Following Working on virtual humans - pose/shape/touch to understand human behavior. PostDoc @UCBerkley and PhD @MPI_IS.
David Pfau @pfau
29K Followers 2K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own https://t.co/xqtVHHVI17 on 🦋
Hedra @hedra_labs
45K Followers 71 Following The generative media creation platform, featuring Character-3, Veo 3, Kling, and more. Join our discord: https://t.co/GLXAU7QJHZ
Davide Moltisanti @davmoltisanti
486 Followers 349 Following Prize Fellow at the University of Bath (tenure track to lecturer/assistant professor)