Stanford Vision and Learning Lab @StanfordSVL
SVL is led by @drfeifei @silviocinguetta @jcniebles @jiajunwu_cs and works on machine learning, computer vision, robotics and language svl.stanford.edu Stanford, CA Joined September 2014-
Tweets335
-
Followers14K
-
Following149
-
Likes301
Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced
spent some time this weekend reading some of the papers that people have been theorizing underly Sora -- first cool concept from them, joint image & video training from @agrimgupta92
Our research introduces a system that enables you to generate 3D environments from text prompts and train embodied AI agents within them! Website: yueyang1996.github.io/holodeck/ Code: github.com/allenai/Holode… How did we leverage Objaverse assets to create interactive 3D environments? 👇
Can we give LLMs access to a visual scratchpad with diagrammatic abstractions and improve reasoning on text-based tasks? Come to the (spoiler) I Can't Believe It's Not Better workshop at @NeurIPSConf on Saturday to find out!
3D Copy-Paste: seamlessly copy virtual objects and paste them into real scenes, maintaining physically plausible integration. This generated data enhances monocular 3D detection models, achieving State-of-the-Art performance. #NeurIPS2023 🌐 gyhandy.github.io/3D-Copy-Paste/
We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇
Color, material, category… —visual concepts characterize different aspects of visual entities. We introduce a framework to recognize these language-informed concepts from images and recompose them to generate new images, e.g., “a blue 🟦 metallic 🪙 Teddy Bear 🧸”.
Can generative AI imagine what Alice saw in her journey in the Wonderland 🏞️🚶♀️? Introducing WonderJourney: Create a journey (a long sequence of diverse yet connected 3D scenes) from a single image or text! 🧵1/N Web: kovenyu.com/wonderjourney/ arxiv: arxiv.org/abs/2312.03884
Excited to talk about Logic-Enhanced Foundation Models (LEFT) @NeurIPSConf next week! Come chat with us on Tuesday morning at #203. Try out our Colab notebook to train your own LEFT and learn concepts on a new dataset in ~100 lines of code. 🔗Colab: colab.research.google.com/drive/1PHHvjIm…
Excited to talk about Logic-Enhanced Foundation Models (LEFT) @NeurIPSConf next week! Come chat with us on Tuesday morning at #203. Try out our Colab notebook to train your own LEFT and learn concepts on a new dataset in ~100 lines of code. 🔗Colab: colab.research.google.com/drive/1PHHvjIm…
Does GPT-4V understand geometric concepts as humans do? We revisit Geoclidean, and ask GPT-4V to learn geometric concepts from few examples. We see that GPT-4V's performance in classifying geometric abstractions differs significantly from that of humans.
Text-to-image models like DALL-E create stunning images. Their widespread use urges transparent evaluation of their capabilities and risks. 📣 We introduce HEIM: a benchmark for holistic evaluation of text-to-image models arxiv.org/abs/2311.04287 (in #NeurIPS2023 Datasets) [1/n]
Evaluation of modern generative models is challenging. Check out HEIM: amazing work led by @tonyh_lee @michiyasunaga @chenlin_meng. A new benchmark for evaluating text to image generation models 🧵👇
Evaluation of modern generative models is challenging. Check out HEIM: amazing work led by @tonyh_lee @michiyasunaga @chenlin_meng. A new benchmark for evaluating text to image generation models 🧵👇
Kosta Derpanis @CSProfKGD
48K Followers 197 Following #CS Associate Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, #CVPR2024/#ECCV2024 Publicity Co-chairMichael Black @Michael_J_Black
59K Followers 643 Following Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.Jia-Bin Huang @jbhuang0604
51K Followers 285 Following Associate Professor @umdcs; Part-time Research Scientist @Meta. I like pixels.Animesh Garg @animesh_garg
21K Followers 1K Following Foundation Models for Generalizable Autonomy. Assistant Professor in AI Robotics @GeorgiaTech + @NvidiaAI. prev @Stanford @berkeley_ai @UofTCompSciAutonomous Vision Gro.. @AutoVisionGroup
12K Followers 371 Following Awesome Vision Group of Andreas Geiger at the University of Tübingen. We are excited about Computer Vision, Machine Learning and Robotics.Michael Bronstein @mmbronstein
43K Followers 4K Following #DeepMind Professor of #AI @UniofOxford / Fellow @ExeterCollegeOx / ML Lead @ProjectCETI / https://t.co/kZpGpDzYeVAngjoo Kanazawa @akanazawa
14K Followers 627 Following Assist. Professor at @Berkeley_EECS, @berkeley_ai. KAIR, @nerfstudioteam, advising @WonderDynamics and @LumaLabsAI. she/her.Andrea Tagliasacchi �.. @taiyasaki
12K Followers 165 Following Associate Professor @ SFU (Research Chair), Research Scientist @ Google DeepMind, Associate Professor (status only) @ UofT. Opinions are my own.Dima Damen @dimadamen
8K Followers 644 Following Professor of Computer Vision, University of Bristol - passionate about the temporal stream in our lives.F. Güney @ftm_guney
7K Followers 1K Following research on computer vision, teaching, and movies. asst. prof. @KuisAICenter @kocuniversity tweets in TR, ENFrank Dellaert @fdellaert
11K Followers 1K Following CTO at Verdant Robotics, Robotics & Computer Vision Professor at Georgia Tech (on leave). Before: sabbatical at KUL, stints at Skydio, Facebook B*8, Google AI.Shane Gu @shaneguML
28K Followers 1K Following Research Scientist & Manager @GoogleDeepMind Tokyo/MTV. ex: @GoogleAI Brain, @OpenAI. (JP: @shanegJP)Yuke Zhu @yukez
15K Followers 464 Following Assistant Professor @UTCompSci | Co-Leading GEAR @NVIDIAAI | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my ownElliott / Shangzhe Wu @elliottszwu
5K Followers 768 Following Postdoc @StanfordSVL working on unsupervised 3D perception and inverse rendering, PhD from @Oxford_VGG. Public office hours: https://t.co/iSSemSi1NQChristian Wolf @chriswolfvision
7K Followers 1K Following Principal Scientist at @NaverLabsEurope, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. IEEE-PAMI area editor.Andrew Davison @AjdDavison
16K Followers 2K Following From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.Ben Poole @poolio
17K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.Stanford HAI @StanfordHAI
86K Followers 558 Following The official account of the @Stanford Institute for Human-Centered AI, advancing AI research, education, policy, and practice to improve the human condition.Luca Carlone @lucacarlone1
8K Followers 508 Following Associate Professor at MIT, SPARK Lab Director, Roboticist, interested in how machines see and understand the world (he/his/him)Patrick Witt @PatPwi
2K Followers 4K Following @meta Fellow @bmwi_bund & @Work4Germany_ Alumnus @hpi_de @DrexelUniv @unibogazici_enOpen @OpenXuu
0 Followers 150 FollowingGene @_francis_lewis
76 Followers 233 Following its working | droids @anduriltech | prev @stanfordsvlEzekiel A. Mitchell @ezekielmcv
38 Followers 182 Following Computer Engineering @SeattleU • building @EndrCompany computer vision for robotics • @USMCあき先生 / Aki @cumulo_autumn
15K Followers 6K Following AITuberの『しずく』@Shizuku_AItuber開発中。Ph.D. Student @UCBerkeley /東工大18M機械系卒/FOS2020/ ヘッダー→天狼さん(@094WPdx9ZrfYJnS) しずくのYoutube: https://t.co/4qvPWqVbakYafei Ding @YafeiD40717
9 Followers 50 FollowingFederico Borchardt @fedefan32
52 Followers 140 FollowingChinmaya @ChinmayaSaxena
977 Followers 2K Following Partner, Community Strategy, VC @ BEENEXT, Startup Enthusiast | ex- Facebook | ex- Microsoft |Believer in the India Entrepreneur Agenda. Stubborn Optimist.Zhe Jia @JiazheJ
20 Followers 91 FollowingDương Xuân @duongxuan2007
7 Followers 950 Following #AI #Python #Data #Robot #IoT #AGI #AutoGPT | #DigitalMarketing #ContentCreator #Youtuber | #Bitcoin #NFT #Web3 #Blockchain #XRP #ETHmetavalent stigmergy @metavalent
456 Followers 4K Following The process by which novel insights, intuitions, understandings, ideas, or concepts originate, germinate, blossom, propagate, and instantiate DCNs and DCNRs.Jason Phong @jasonkphong
132 Followers 315 Following PhD Student @MIT_DMSE @johnsonchem @EELabMIT | Bao Lab @Stanford ‘23 | he/himSerhan Yilmaz @srhnylmz14
67 Followers 771 Following current junior cs undergrad @sabanciu & president/founder @kaisabanci // prev @EPFL @YapiKredi @BU_Tweets @kocuniversity // contact: dmChristie Cordes @Ad_Recruiter
7K Followers 4K Following https://t.co/L3LqIIWkr0 | Founder, CEO Est. 2003 | Global Talent Strategy Creative + Technology + Brand | Consiglieré Talent Advisory 🤍 Board @ AdArtShowMoritz Knolle @moritzknolle
65 Followers 300 Following PhD Student in Privacy-preserving and Trustworthy ML for MedicineJonathan Wilhelm @J0nathanWilhelm
139 Followers 598 Following Entrepreneur ❤️ Innovation | Angel Investor | Real Estate Pro | Product | Committed to Growth | Automation | Girl Dad #AI #NoCode #CryptoSamuel Youssef @SamuelMYoussef
63 Followers 508 FollowingFernando Berrospi @fberrosp
5 Followers 86 Following I am Fernando Berrospi, a growth-minded Software Engineer who is passionate about all things related to machine learning, data science and Formula 1.Elgce @BenQingwei
66 Followers 220 Following Hey, everyone! I am a junior student of Tsinghua University & incoming Ph.D of MMLAB@CUHK. I am interested in Reinforcement Learning and Robotics.ROSguy @roboot_mobile
9 Followers 222 FollowingNahida @Nahida271
1 Followers 0 FollowingNao Yukawa @nyneurotech
957 Followers 925 Following CEO @LifestackAI, the only calendar with energy in mind / Cohort 7 @FounderUni / 🇯🇵: @NaoYukawaSamira @SameeraBe
4 Followers 34 FollowingKingDingus (code is s.. @KingDingus1776
102 Followers 942 Following The Kingus Dingus | raised in California, crafted in NYC | this never happenedFan Feng @ffeng01
148 Followers 1K FollowingNeuralNetNinja @DeepLearnQuest
10 Followers 161 Following curious. documenting my deep learning journey.Gianluca Iaccarino @GianlucaStnfd44
4 Followers 27 Following R3tarded Stanford admissions dean for ICME. I suk dick all day every day with lil undergrads at Stanford where all the kuntz and sletz congegrate AHHH yummy!Garuda @Garuda22878326
26 Followers 328 FollowingSeable @SeableHolidays
2K Followers 4K Following An award-winning social enterprise providing #accessible tailored and group holidays to the visually impaired community. Inclusive trips with trained assistanceceretor @ceretor3rd
50 Followers 308 Following It is basically an account for information. But I will occasionally post ... https://t.co/phSbef4sEiZhanke Zhou @zhankezhou
37 Followers 293 Following PhD student at HKBU. Focus on trustworthy machine reasoning for scientific discoveries.Mene Precious @MenePrecious3
26 Followers 80 FollowingMustafa A. Elghrib @maelghrib
2 Followers 186 FollowingSunghwan Kim @sssssshwan
8 Followers 96 FollowingJunwei Huang @dr_junwei
3 Followers 66 Following Senior Data Scientist @RBC helping multiple business lines Earn Trust 🤝and Grow Revenue 💲Francesco @Frances27168078
14 Followers 86 Followingchenchen @chenchen1229028
0 Followers 6 FollowingSoumith Chintala @soumithchintala
186K Followers 883 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Animesh Garg @animesh_garg
21K Followers 1K Following Foundation Models for Generalizable Autonomy. Assistant Professor in AI Robotics @GeorgiaTech + @NvidiaAI. prev @Stanford @berkeley_ai @UofTCompSciEric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pSergey Levine @svlevine
80K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceKyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Andrea Tagliasacchi �.. @taiyasaki
12K Followers 165 Following Associate Professor @ SFU (Research Chair), Research Scientist @ Google DeepMind, Associate Professor (status only) @ UofT. Opinions are my own.Dima Damen @dimadamen
8K Followers 644 Following Professor of Computer Vision, University of Bristol - passionate about the temporal stream in our lives.Laura Leal-Taixe @lealtaixe
10K Followers 118 Following Senior Research Manager at @NVIDIA. Prev Professor at @TU_Muenchen. Computer Vision mostly. Views are my own.Devi Parikh @deviparikh
23K Followers 151 Following Former Sr. Director, GenAI @Meta. Prof @GeorgiaTech. Generative artist https://t.co/z4n9IRQ3s5. Co-founded Caliper. @CarnegieMellon @RowanUniversity alum.Yuke Zhu @yukez
15K Followers 464 Following Assistant Professor @UTCompSci | Co-Leading GEAR @NVIDIAAI | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my ownZachary Lipton @zacharylipton
59K Followers 2K Following Professor: CMU/@acmi_lab, CTO / CSO: @AbridgeHQ, Creator: @d2l_ai & https://t.co/QQt98VNLUp, Relapsing 🎷Thomas G. Dietterich @tdietterich
50K Followers 505 Following Distinguished Professor (Emeritus), Oregon State Univ.; Former President, Assoc. for the Adv. of Artificial Intelligence; Robust AI & Comput. SustainabilityDhruv Batra @DhruvBatraDB
14K Followers 324 Following Senior Director (FAIR @MetaAI). Professor (@GeorgiaTech). Co-founded CaliperAI. Researcher in AI. @CarnegieMellon alum.Andrew Davison @AjdDavison
16K Followers 2K Following From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.Danfei Xu @danfei_xu
6K Followers 1K Following Assistant Prof. at Georgia Tech @ICatGT, researcher at @NVIDIAAI | Ph.D. @StanfordAILab | Making robots smarterFan-Yun Sun @sunfanyun
384 Followers 569 Following cs phd student @StanfordAILab @stanfordsvl generative simulation, (3D) computer vision, graph machine learningMark Endo @mark_endo1
107 Followers 60 Following Computer Science PhD student @Stanford | AI + HealthYunzhu Li @YunzhuLiYZ
4K Followers 451 Following Assistant Professor of Computer Science @ UIUC @UofIllinois @IllinoisCS, Postdoc from @Stanford @StanfordSVL, PhD from @MIT_CSAIL. #Vision #Robotics #LearningChen Wang @chenwang_j
2K Followers 674 Following PhD student @StanfordSVL @StanfordAILab. Prev @NVIDIA @MIT_CSAIL. Robotics/ManipulationWeiyu Liu @Weiyu_Liu_
716 Followers 433 Following Postdoc @Stanford. I work on semantic representations for robots. Previously PhD @GTroboticsJosiah Wong @josiah_is_wong
231 Followers 68 Following PhD Candidate at @Stanford @StanfordSVL | Teaching robots to do everyday tasksSumith Kulal @sumith1896
833 Followers 392 FollowingJoy Hsu @joycjhsu
1K Followers 280 Following cs phd-ing @stanford & @knighthennessy. studying visual reasoning and neuro-symbolic learning @stanfordailab & @stanfordsvl.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Carnegie Mellon Unive.. @CarnegieMellon
78K Followers 2K Following United by curiosity and driven by passion, we reach across disciplines, forge new ground and deploy our expertise to make real change that benefits humankind.Dorsa Sadigh @DorsaSadigh
8K Followers 390 Following CS Faculty @Stanford, @StanfordAILab 20% Research scientist @GoogleDeepMind PhD and BS from @Berkeley_EECSOren Etzioni @etzioni
28K Followers 2K Following Founder, https://t.co/IQ6xAlnKcR. Professor Emeritus, UW. Technical Director, AI2 Incubator. Venture Partner, Madrona. Founding CEO, AIlen Institute for AI (AI2).David Duvenaud @DavidDuvenaud
28K Followers 3K Following Machine learning prof @UofT. Working on generative models, inference, & latent structure.Michelle Lee @michellearning
3K Followers 944 Following PhD Candidate @StanfordAILab. Michelle Learning model currently training on robotics, AI, and wholesome dad jokes. ChemE🧪→ MechE 🔨→ AI research🤖Kuan Fang @KuanFang
2K Followers 663 Following Incoming Assistant Professor at Cornell CS (Fall 2024) | Postdoc at UC Berkeley & Researcher at Boston Dynamics AI Institute | Previously PhD at StanfordSanja Fidler @FidlerSanja
14K Followers 483 Following Associate Professor @UofT, Vice President of AI Research @nvidia, founding member of @VectorInst. Computer vision, deep learning, 3D. Opinions are my own.MIT CSAIL @MIT_CSAIL
298K Followers 22K Following MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: [email protected]Stanford IPRL Lab @StanfordIPRL
1K Followers 38 Following Stanford Interactive Perception and Robot Learning Lab directed by Jeannette Bohg @leto__jean. @StanfordAILabDurk Kingma @dpkingma
35K Followers 348 Following Deep learning, mostly generative models. Prev. Google Brain/DeepMind, founding team @OpenAI. Inventor of the VAE, Adam optimizer, among other things. ML PhD.Andrew Fitzgibbon @Awfidius
4K Followers 910 Following Technical Fellow, Graphcore. Love beautiful code, and beautiful hardware to run it on.Yee Whye Teh @yeewhye
24K Followers 1K Following Find me @[email protected] Professor at @OxCSML, @oxfordstats and Research Director at @GoogleDeepMind. All opinions are my own.Roberto @RobobertoMM
2K Followers 249 Following Assistant CS Professor at UT Austin. Former Stanford and TUBerlin. Researching at the intersection of vision, learning and robotics 🏳️🌈Tobias Gerstenberg @tobigerstenberg
4K Followers 866 Following Tea drinking assistant professor in cognitive psychology @Stanford.Stanford AI Lab @StanfordAILab
137K Followers 318 Following The Stanford Artificial Intelligence Laboratory (SAIL), a leading #AI lab since 1963. ⛵️🤖 Emmy-winning video: https://t.co/lV9smZTC1mThomas Kipf @tkipf
25K Followers 1K Following AI Research at @GoogleDeepMind. Ex-Physicist. Graph Neural Networks & Controllable Generative Models (e.g. GCNs, Structured World Models, Slot Attention).Chelsea Finn @chelseabfinn
69K Followers 384 Following Asst Prof of CS & EE @Stanford. PhD from @Berkeley_EECS, EECS BS from @MITVisual Geometry Group.. @Oxford_VGG
11K Followers 357 Following Computer Vision research group @UniofOxford led by Andrew Zisserman, Andrea Vedaldi, João Henriques and Christian Rupprecht.Emma Brunskill @EmmaBrunskill
7K Followers 91 Following Associate professor, Computer Science. Stanford. Stanford's Human Centered AI (HAI) Institute. Opinions expressed are my own.Ferenc Huszár @fhuszar
40K Followers 1K Following Secular Bayesian. Associate Professor in Machine Learning @Cambridge_CL. Talent aficionado at https://t.co/RbJkoLguey Alum of @Twitter, Magic Pony and @BaldertonBen Recht @beenwrekt
26K Followers 365 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.Surya Ganguli @SuryaGanguli
15K Followers 457 Following Associate Prof of Applied Physics @Stanford, and departments of Computer Science, Electrical Engineering and Neurobiology. Venture Partner @a16zLuis von Ahn @LuisvonAhn
159K Followers 123 Following CEO & co-founder of @duolingo. Invented reCAPTCHA. MacArthur Fellow. Former computer science professor at Carnegie Mellon. Proud Guatemalan. @LvA_Foundation.We especially thank @kenny__shaw @anag004 @pathak2206 for open-sourcing the LEAP Hand project. Having a customizable and low-cost dexterous hand benefits our project a lot!
We hope DexCap paves the path for future research on scaling up robot data with wearable devices. The code, data, and hardware are open-sourced at 🌐dex-cap.github.io Work done w/ @HaochenShi74 @KenWangWeizhuo @RuohanZhang76 @drfeifei Karen Liu @StanfordAILab @StanfordSVL
Also check out the fun failure modes of our robot. 8/
However, DexCap is not yet ready for tasks that require applying force, as positional data alone is insufficient. Therefore, we introduce DexCap for human-in-the-loop correction during rollouts. Within 30 trials of corrections, our robot can prepare tea🍵 and use scissors✂️. 7/
DexCap enables fast data collection, approximating the speed of natural human motion. Moreover, the collection process does not require costly robot hardware. 6/
DexCap is fully portable and can scale up data collection in the wild. By collecting data with multiple objects in diverse environments, the learned policy can generalize to unseen objects for the same task. 5/
We train a point cloud-based Diffusion Policy with retargeted human mocap data only. The robot controls both hands (46-dim action space) to perform tasks including collecting tennis balls🎾 and packaging objects🎁. All the policies are learned without any teleoperation data. 4/
We then retarget the mocap data to the robot embodiment. This includes (1) Observation retargeting by switching the camera system from human to robot. (2) Action retargeting by matching fingertip positions with IK. (3) Bridging the visual gap by including robot point clouds. 3/
Motion capture gloves, unlike vision-based tracking, are not affected by occlusions during hand-object interactions, perfect for mocap in daily activities. With an RGB-D camera, DexCap reconstructs 3D scenes and aligns motion data, all powered by a mini-PC in the backpack. 2/
Can we use wearable devices to collect robot data without actual robots? Yes! With a pair of gloves🧤! Introducing DexCap, a portable hand motion capture system that collects 3D data (point cloud + finger motion) for training robots with dexterous hands Everything open-sourced
Our research introduces a system that enables you to generate 3D environments from text prompts and train embodied AI agents within them! Website: yueyang1996.github.io/holodeck/ Code: github.com/allenai/Holode… How did we leverage Objaverse assets to create interactive 3D environments? 👇
Can we give LLMs access to a visual scratchpad with diagrammatic abstractions and improve reasoning on text-based tasks? Come to the (spoiler) I Can't Believe It's Not Better workshop at @NeurIPSConf on Saturday to find out!
3D Copy-Paste: seamlessly copy virtual objects and paste them into real scenes, maintaining physically plausible integration. This generated data enhances monocular 3D detection models, achieving State-of-the-Art performance. #NeurIPS2023 🌐 gyhandy.github.io/3D-Copy-Paste/
We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇
Color, material, category… —visual concepts characterize different aspects of visual entities. We introduce a framework to recognize these language-informed concepts from images and recompose them to generate new images, e.g., “a blue 🟦 metallic 🪙 Teddy Bear 🧸”.
Can generative AI imagine what Alice saw in her journey in the Wonderland 🏞️🚶♀️? Introducing WonderJourney: Create a journey (a long sequence of diverse yet connected 3D scenes) from a single image or text! 🧵1/N Web: kovenyu.com/wonderjourney/ arxiv: arxiv.org/abs/2312.03884
@NeurIPSConf And also check out our Colab demo to evaluate a trained LEFT on a human motion domain! 🔗Colab: colab.research.google.com/drive/1b0Bzlyr…
Excited to talk about Logic-Enhanced Foundation Models (LEFT) @NeurIPSConf next week! Come chat with us on Tuesday morning at #203. Try out our Colab notebook to train your own LEFT and learn concepts on a new dataset in ~100 lines of code. 🔗Colab: colab.research.google.com/drive/1PHHvjIm…
What’s left w/ foundation models? We found that they still can't ground modular concepts across domains. We present Logic-Enhanced FMs:🤝FMs & neuro-symbolic concept learners. We learn abstractions of concepts like “left” across domains & do domain-independent reasoning w/ LLMs.
Does GPT-4V understand geometric concepts as humans do? We revisit Geoclidean, and ask GPT-4V to learn geometric concepts from few examples. We see that GPT-4V's performance in classifying geometric abstractions differs significantly from that of humans.
A robot may be unable to complete a task when limited by its morphology. Remarkably, people and some animals can get around this by not only using but also *designing* tools. We explore whether robots can also do this in our latest work! 🌐robotic-tool-design.github.io 🧵👇