Orest Kupyn @OKupyn
CV Researcher, Ukrainian 🇺🇦 | PhD Student at University of Oxford, Visual Geometry Group kupynorest.github.io Joined February 2022-
Tweets106
-
Followers151
-
Following56
-
Likes231
Can video generation models do for vision what LLMs did for language? Introducing GenCeption from @GoogleDeepMind: one feed-forward video model for various vision tasks — SOTA, data-efficient, and emerging behaviors (ECCV 2026) 🌐 genception.github.io (1/8)
📣New Paper: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation. 🌐 flat-splat.github.io 🤗: huggingface.co/papers/2606.24… A feedforward latent scene decoder for generating explicit triangle-based 3D scenes from video diffusion latents.
@sammtmd @ZhaochongAn We can also have a chat anytime if you want 🙂
Glad to see VGGRPO accepted to ECCV’26! Exciting times ahead🔥. See you all in Sweden!
🎥 Video diffusion models can create beautiful videos, but their worlds often fall apart. 🔥 Excited to share our latest work at @Google: 📢 VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward 📢 📄 arxiv.org/pdf/2603.26599 🌐 zhaochongan.github.io/projects/VGGRPO 🧵
@taiyasaki Sure, we really appreciate the feedback! I think the current window function is still one of the main bottlenecks, so this should be an interesting experiment
@janheld14 Thanks, wouldn’t be possible w/o Triangle and Mesh Splatting, thanks for your great work too!
The final step is what makes the representation especially practical. A lightweight test-time refinement turns the predicted triangle soup into a fully opaque, game-engine-ready asset that supports real-time rendering and direct physical interaction.
Another nice property is flexibility. FLAT is trained to decode video-model latents directly, so the same scene decoder can plug into Wan-2.1 style pipelines beyond a single mode, enabling text to 3D, image to 3D, real-time generation and others.
Excited to share our #SIGGRAPH2026 paper: Go-with-the-Track! We utilize point-tracks as spatiotemporal conditioning to precisely insert multiple reference images into generated videos. Paper: arxiv.org/pdf/2606.20891 Project page: eyeline-labs.github.io/Go-with-the-Tr…
📢 @eyelinestudios and @netflix latest research, 🌟Go-with-the-Track🌟, has been accepted to #SIGGRAPH2026. We propose a video generation framework that jointly conditions on multiple reference images and reference-anchored point tracks, enabling a range of content creation
Aggregated diffusion features also transfer beyond still images, including video-to-3D settings. We hope this helps push toward more efficient multi-modal generation, where one model produces not just pixels, but richer complex outputs.
The key idea is multi-timestep feature aggregation. Different denoising steps capture different parts of scene structure, so reading only the final latent leaves useful information behind. Aggregating across timesteps gives much stronger representations.
Excited to release new paper: MMDiff: Extending Diffusion Transformers for Multi-Modal Generation that was just accepted to #ECCV2026 and is finally out! 🎉 Project page 🌐: yagmurakarken.github.io/mmdiff/ Paper 📄: arxiv.org/abs/2606.16673 Code: github.com/yagmurakarken/…
Congratulations to @ChuhanZhang5 @LiliMomeni @JunyuXieArthur Andrew and the team!! 🥳🥳
Huge congrats to the team, D4RT is a team work and all the authors have been working very hard on this in the past one year. Very well deserved. 🍻 and thank you Award Committee Members for the recognition.
Finally the orgs, who work for Russian government and helping developing weapon in the war of aggression against Ukraine have their papers desk rejected. Thank you, @iclr_conf. openreview.net/forum?id=w2tnh…
Jack Parker-Holder @jparkerholder
15K Followers 922 Following Research Director scaling world models @GoogleDeepMind, Adjunct Faculty @bold_lab_ai. Dad (🧒👶🐶), CFC fan, BJJ. Views are my own :)
Ofir Press @OfirPress
19K Followers 9K Following I push the AI frontier by building tough benchmarks with amazing people. SWE-bench, SWE-agent, SciCode, AlgoTune. Postdoc @Princeton. PhD @nlpnoah @UW.
Selim Kuzucu @SelimKuzucu
120 Followers 301 Following PhD Student @cvml_mpiinf, formerly @Google, @BoschGlobal / @_FiveAI, @metu_imagelab & @AFAR_Cambridge
Olaf Dünkel @olaf_duenkel
54 Followers 197 Following ELLIS PhD student with MPI-INF & Uni Oxford https://t.co/sk0jPCW5XP
Ashish Asthana @aash_asth
5 Followers 2K Following
Wei Cao @vveicao
167 Followers 702 Following PhD student @UofIllinois | Intern @StabilityAI | Prev @TU_Muenchen
omelette catching up @omeletsroll
3 Followers 320 Following i don’t understand a lot of things. but i want to.
Stéphane Agullo @StephaneAgullo
210 Followers 423 Following Freelance 3D Artist · https://t.co/R1U2GQCMpR · SuperSplat & PlayCanvas · https://t.co/flCSvwM3Et · Drone Scanning · https://t.co/jzZpd4fZby · WebXR · 3DGS · 3D ✨
Itay Rosenbach @itay_ros
47 Followers 4K Following
王同学 @iMIuQDhptU7O4FD
6 Followers 883 Following
Jasleen Kaur Dhanoa @jasleeen_dhanoa
19 Followers 683 Following Perception Engineer @Mach9Robotics | Robotics @GRASPLab
Mike Dereviannykh @Mishok2000
916 Followers 1K Following Neural Rendering & World Models at Stability AI, PhD Student at KIT; ex: Meta-RL, Eagle Dynamics;
Dominik Engel @xeTaiz
21 Followers 468 Following PhD in Deep Learning fron Ulm University. Interests: Deep Learning, Computer Graphics, Computer Vision. Account exists for DL research related Tweets only :P
Mark Welton @realMPWuk
2K Followers 5K Following Interests include creating abstract art and minimalist music.
Sad Hacker @Sadhac151
12 Followers 1K Following
Anthony R. Risen @RisenAnthony
97 Followers 1K Following BEO | BlackBox Founder Writer | Director | 3D Generalist | Agentic Engineer
Stone Felt @ScanSavvyStone
123 Followers 928 Following Building ScanSavy: Omnichannel in a box for brick-and-mortar retailers. DM or reach out to [email protected]
Yizhak Ben-Shabat (It... @sitzikbs
2K Followers 988 Following 🇮🇱 Researcher / Educator / Father / Podcaster. Creator of 3D computer vision algorithms. Follow the podcast feed at @talking_papers.
Abhinav Kumar @abhinav1kumar
382 Followers 2K Following 3D / 4D Computer Vision: 3D / 4D Generation, Monocular 3D Detection @Adobe
Davide Cuttini @cuttini
2K Followers 2K Following CEO @ Over The Reality | World's largest 3D map fueling Physical AI & robotics, VPS navigation & generative AR
Kuntay Yilmaz @kunt4y
228 Followers 2K Following 20 | senior ai engineering undergrad @hacettepe1967 | 3D vision/graphics, generative models
Easson Kang @EassonKang
15 Followers 205 Following Url: https://t.co/ZYt8FRcRr1 3D Moment App, with a vision of 3D Earth Reconstruction.
Charlii @charliiai
48 Followers 3K Following Full-Stack | GenAI Researcher | Creator of Vibe Coding | Exploring AI, Multimodal Interaction & Practical Dev Hacks
map to (tomap) @PrismLuma
4 Followers 332 Following
blindmelon @blindmelon1
51 Followers 3K Following
Jan Held @janheld14
568 Followers 260 Following 💻 Building 3D worlds at @SpAItial_AI 🤖 Prev projects: Triangle Splatting & MeshSplatting & 3D Convex Splatting & more
Dennis Rotondi @DennisRotondi
10 Followers 90 Following
Young D. Kwon ✈️ ... @YoungDKwon1
519 Followers 2K Following AI Scientist @ Samsung AI | Shipped on-device GenAI to Galaxy flagships (S24 · S25 · S26) | Visiting Scholar & PhD @ Cambridge | ML & Systems Rising Star (2025)
やきとり @Am0_11mAr3
260 Followers 4K Following
danglingpointer @sunshotai
20 Followers 3K Following
gzamps @gzamps
289 Followers 4K Following A cynical remark every now and then. Huge sports fan. #MFFL
conan kinde @ConanKinde
0 Followers 6K Following
Mingfei Chen @lasiafly
113 Followers 201 Following PhD Student @UW | PhD Fellow @Google | Multi-Modal LLMs, Spatial AI, XR, Robotics | Previously @Meta & @NUSingapore
Xuanchi Ren @xuanchi13
1K Followers 590 Following Ex-Senior Research Scientist @NVIDIAAI. PhD @UofTCompSci. Working on GenAI and world models
ที่บ้าน... @4B68616D77616E
29 Followers 352 Following SSO Contributor | Research Enthusiast in Heuristic Algorithms & Machine Vision |
Philipp Henzler @philipphenzler
1K Followers 727 Following Research Scientist @ Google | Gemini Omni / Generative 3D. PhD from UCL
Anton Zubekhin @anton_zubekhin
26 Followers 160 Following PhD student at Visual Computing and Artificial Intelligence Department, Max Planck Institute for Informatics Opinions are my own
Leo @leoxqys
3 Followers 90 Following
Zhiang @ZhiangGo
1 Followers 145 Following
Saturday Robotics @saturdayrobotic
2K Followers 30 Following 🤖 Saturday Reading Club on Robotics & World Models for AI Researchers in SF Hosts: @junfanzhu98 @aurorafeng_01 @neuralmotion https://t.co/fLSL01KO9e
Vitaly @M0nstas
20K Followers 49 Following Military analysis / Modern war theory / Unmanned battlefield Operational trends, force balance, probability in conflict Dummy predictions.
Changan Chen @changanvr
954 Followers 246 Following Co-founder and Chief Research Officer @RhodaAI Scaling visual intelligence toward physical AGI. Prev: @Stanford @UTAustin @FAIR.
Jeannette Bohg @leto__jean
9K Followers 537 Following Associate Professor @StanfordAILab @StanfordIPRL. Perception, learning and control for autonomous robotic manipulation #BlackLivesMatter she/her 🌈
Jiahui Yu @jiahuiyu
28K Followers 1K Following Startup. Previously co-founded TBD @Meta Superintelligence Labs; led Perception @OpenAI; co-led Gemini Multimodal @GoogleDeepMind.
Kateryna Lisunova @KaterynaLis
33K Followers 1K Following Journalist & Media Advisor Razom for Ukraine, former Congressional and UN correspondent for VOA and BBC. EMAIL: [email protected]
Sam Motamed @sammtmd
599 Followers 1K Following @ELLISforEurope PhD student at @INSAITinstitute + @Oxford_VGG. Ex: @NetflixResearch / @GoogleDeepMind / @CMU_Robotics / @UofT.
Songyou Peng @songyoupeng
9K Followers 811 Following Teaching multimodality to Gemini, Nano Banana, and more @GoogleDeepMind. PhD from @ETH and @MPI_IS.
François Fleuret @francoisfleuret
54K Followers 479 Following Research Scientist @meta (FAIR), Prof. @Unige_en, co-founder @neural_concept_. I like reality.
Jan Held @janheld14
568 Followers 260 Following 💻 Building 3D worlds at @SpAItial_AI 🤖 Prev projects: Triangle Splatting & MeshSplatting & 3D Convex Splatting & more
Katie Lewis Grumman @KatieLewisMIT
1K Followers 397 Following Research @runwayml , previously PhD @MIT_CSAIL Computer vision, generative & creative AI research. Opinions are my own.
Marjan Ghazvininejad @gh_marjan
3K Followers 439 Following Research Scientist at Meta FAIR, #NLProc #LLM
Roman Bachmann @roman__bachmann
629 Followers 567 Following Multimodal @Apple, previously at @EPFL_en, @RIKEN_AIP
Dmytro Okhonko 🇺�... @DmytroOk
835 Followers 244 Following Robotics @OpenAI, previously @Samaya_ai and @MetaAI
Pritam Damania @PritamDamania
439 Followers 354 Following Member of Technical Staff @OpenAI. Previously Tesla AI, PyTorch (led PyTorch Distributed), Facebook. Opinions are my own.
Xingyu Lin @Xingyu2017
4K Followers 495 Following Robot learning @openai. Previously @berkeley_ai @SCSatCMU. #Learning #Robotics
Tairan He @TairanHe99
15K Followers 1K Following Researcher @OpenAI. Prev: PhD @CMU_Robotics @NVIDIA @MSFTResearch @sjtu1896 | All Opinions are My Own
Iain Dunning @iaindunning
12K Followers 563 Following Head of AI @ HRT (@WeAreHRT), Chairman @ New York Transit Museum, Friend of Riverside Park Conservancy
Nithish Kannen @NithishKannen
2K Followers 3K Following Research Scientist @GoogleDeepmind. RL for 🍌 and Gemini. Prev: AI Resident, @GoogleDeepMind
Xuanchi Ren @xuanchi13
1K Followers 590 Following Ex-Senior Research Scientist @NVIDIAAI. PhD @UofTCompSci. Working on GenAI and world models
Jack Parker-Holder @jparkerholder
15K Followers 922 Following Research Director scaling world models @GoogleDeepMind, Adjunct Faculty @bold_lab_ai. Dad (🧒👶🐶), CFC fan, BJJ. Views are my own :)
Philipp Henzler @philipphenzler
1K Followers 727 Following Research Scientist @ Google | Gemini Omni / Generative 3D. PhD from UCL
Theo Uscidda @theo_uscidda
256 Followers 277 Following phd @IP_Paris_ | intern @Google @Apple @Amazon @SimonsFdn @HelmholtzMunich
Federico Tombari @fedassa
3K Followers 192 Following 3D computer vision and ML for AR and robotics, @Google and TU Munich
Dumitru Erhan @doomie
19K Followers 2K Following Co-lead of Gemini Omni @GoogleDeepMind. Senior Research Director.
Thinking Machines @thinkymachines
182K Followers 1 Following Thinking, beeping, and booping. @tinkerapi
Eldar Insafutdinov @EldarIsTyping
418 Followers 921 Following Computer vision researcher at Frontier AI and Robotics Lab, Amazon Ex-Postdoc @Oxford_VGG. PhD at the Max Planck Institute for Informatics. Opinions are my own.
Maria Dobko 🇺🇦 @DobkoMaria
1K Followers 187 Following ML researcher | Cornell & UCU alum #GraphML #NLP #ComputerVision #Ukrainian
Chuanxia Zheng @ChuanxiaZ
948 Followers 745 Following Assistant Professor @NTUsg | Postdoc @Oxford_VGG | PhD @NTUsg
Felipe Nuti @NutiFelipe
235 Followers 2K Following Systematic FICC QR @ CitSec | Prev. MCS @ Uni of Oxford & Research @ VGG | Interested in Generative Modeling and Reinforcement Learning | Opinions my own
Visual Geometry Group... @Oxford_VGG
15K Followers 367 Following Computer Vision research group @UniofOxford led by Andrew Zisserman, Andrea Vedaldi, João Henriques, Christian Rupprecht, and Iro Laina
Guanqi Zhan @zgq1879
314 Followers 154 Following Ph.D. @Oxford_VGG with Prof. Andrew Zisserman; Research Scientist Intern @NVIDIA
RuiningLi @RayLi234
869 Followers 976 Following Ph.D. Student at Oxford VGG. Building scalable sim and representation for physical AI.
Yash Bhalgat @ysbhalgat
2K Followers 2K Following Gemini Omni @GoogleDeepMind PhD @Oxford_VGG. Past: Senior RS @Qualcomm AI Research, @UMich, @iitbombay All opinions are mine.
Shu Ishida, Ph.D. @shuishidaOx
345 Followers 175 Following Senior AI Research Scientist at Autodesk. Ex-Microsoft, Wayve, VGG (University of Oxford). Research: Computer Vision, Deep Reinforcement Learning and GenAI.
Suny Shtedritski @shtedritski
738 Followers 213 Following Member of Technical Staff https://t.co/PW2bCliK7K | Prev: intern @GoogleDeepMind, PhD @Oxford_VGG, lead @OxfordAI, Engineering @oxengsci, IPhO 🥉 | Pump x Hunter
Institute for the Stu... @TheStudyofWar
1.4M Followers 3K Following ISW is a policy research organization focused on U.S. national security. Email: [email protected]. https://t.co/FO1PVyOnYB
Т @TarasChmut
197K Followers 141 Following 🇺🇦 marine, director @backandalive, founder @militarnyi / @mil_in_ua
NOELREPORTS 🇪🇺 ... @NOELreports
529K Followers 408 Following Media platform covering global conflict zones. Focus on the Russian-Ukrainian war. If you'd like to support our voluntary work: https://t.co/PmM2wwDA1Y.You might like
