Zichen "Charles" Zhang @ZCCZHANG
PYI @allen_ai | Specialist can generalize and Generalist can specialize zcczhang.github.io Joined August 2021-
Tweets59
-
Followers168
-
Following267
-
Likes604
So you want to do robotics tasks requiring dynamics information in the real world, but you don’t want the pain of real-world RL? In our work to be presented as an oral at ICLR 2024, @memmelma showed how we can do this via a real-to-sim-to-real policy learning approach. A 🧵 (1/7)
Join us at the **5th** Embodied AI Workshop in Seattle on June 18 #CVPR2024 🔊 Exciting invited speakers, 🥷 6+ challenges (with cash prizes), 📋 poster session, and 👽 lots more! 📜Workshop paper submission details coming soon Website: embodied-ai.org
Join us at the **5th** Embodied AI Workshop in Seattle on June 18 #CVPR2024 🔊 Exciting invited speakers, 🥷 6+ challenges (with cash prizes), 📋 poster session, and 👽 lots more! 📜Workshop paper submission details coming soon Website: embodied-ai.org
(1/2) 📢 Introducing LL3M: Large Language, Multimodal, and Moe Model Open Research Plan 👉github.com/jiasenlu/LL3M With the following goals: - Build an open-sourced codebase in Jax / Flax that supports large-scale training in LLM, LMM, and MoE models. - Record and share the…
How can we train robust policies with minimal human effort?🤖 We propose RialTo, a system that robustifies imitation learning policies from 15 real-world demonstrations using on-the-fly reconstructed simulations of the real world. (1/9)🧵 Project website: real-to-sim-to-real.github.io/RialTo/
OLMo is here! And it’s 100% open. It’s a state-of-the-art LLM and we are releasing it with all pre-training data and code. Let’s get to work on understanding the science behind LLMs. Learn more about the framework and how to access it here: blog.allenai.org/olmo-open-lang…
In the last two years, large foundation models have proven capable of perceiving and reasoning about the world around us unlocking a key possibility for scaling robotics. We introduce a AutoRT, a framework for orchestrating robotic agents in the wild using foundation models!
Excited to release Unified-IO 2 -- a multimodal model to not just parse but also produce images, text, audio and actions for robotics. This was a very challenging and demanding multi year effort. One of the largest projects to come out of PRIOR @allen_ai. Very proud of the team!
Excited to release Unified-IO 2 -- a multimodal model to not just parse but also produce images, text, audio and actions for robotics. This was a very challenging and demanding multi year effort. One of the largest projects to come out of PRIOR @allen_ai. Very proud of the team!
Joint work with @jiasenlu*, Christopher Clark, Sangho Lee*, @ZCCZHANG*, Savya Khosla, Ryan Marten, @DerekHoiem_UofI, @anikembhavi (* Leading authors)
6/ UnifiedIO 2 is state-of-the-art of the GRIT and SEED benchmarks, performs as well as other recent vision/language generate models on vision/language benchmarks despite supporting many additional modalities, achieves strong image generation results, and achieves good scores on…
5/ Our model is pre-trained from scratch on an extensive variety of multimodal data -- 1 billion image-text pairs, 1 trillion text tokens, 180 million video clips, 130 million interleaved image & text, 3 million 3D assets, and 1 million agent trajectories. We further…
4/ We develop a training sample construction pipeline from heterogeneous data sources. We trained the model with a multimodal mixture of denoisers (MoD) objective. The video shows how to construct input and output samples from video.
3/ Training on massive modality from scratch is very challenging. We include various architectural changes that significantly stabilize multimodal training. Left-top: Introducing a combination of image and text tasks (orange curve) slightly increases the gradient norm. However,…
2/ Our model architecture: a 7 billion parameter encoder-decoder transformer. The encoder processes a sequence of multimodal tokens, including text, images, audio, or image/audio history. The decoder outputs discrete tokens that can be decoded into text, an image, or an audio…
Wondering how to train a multimodal AI Model with massive input and output modalities from scratch? Introducing Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. Our model, inference code, and…
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action Presents the first autoregressive multimodal model that is capable of understanding and generating images, text, audio, and action proj: unified-io-2.allenai.org abs:…
Allen AI releases Unified-IO 2 Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action paper page: huggingface.co/papers/2312.17… the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action
Holodeck: Language Guided Generation of 3D Embodied AI Environments paper page: huggingface.co/papers/2312.09… 3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To…
Annalee Neang @AnnaleeNea13814
14 Followers 3K FollowingSophie-leigh Lemos @LemosLeigh33131
67 Followers 5K FollowingEkue @ekpodar
1K Followers 2K Following I am interested in Tech/AI, Marketing, and complex systems, I will posts random stuff in those categories_FUTURE_ 🍊🍊🍊.. @FUTURE_000_NFT
375 Followers 3K Following USAF 🦅🇺🇸 | Web3 Deployment and Analysis 💻 | 100x Gem Invester 📈🐂🎯Wang Jianming @jianming_w87187
17 Followers 327 Following Early Stage Investor focusing on AI+RoboticsYixin Chen @_yixinchen
64 Followers 114 FollowingEvolvableNFT @EvolvableN
14 Followers 101 Following As an unique digital ID, NFT could be evolvable by depositing crypto currencies, accepting attributes, skills, equipment, events or badges.MLEMONVR @MLemonVR
310 Followers 6K Following Design good VR accessories for Meta Quest2 Quest3 #AppleVisionPro #VR #vraccessories #QueestKrypton M. @kristywhim_
14 Followers 33 Following 专注自我|梦想很多的修行人|满绩和颜值是最害人和荒谬的优势| Biostatistics @UNC, Therapist, Dancer, Poet, Writer | Geek out on Digital Marketing, #Healthcare, #Web3, #GenAIStephen James @stepjamUK
4K Followers 177 Following Leading the @Dyson Robot Learning Lab. Postdoc @UCBerkeley w/ @pabbeel. PhD Imperial College London w/ @ajdDavison. AI, Robotics, Machine Learning 🤖Haoyi Zhu @HaoyiZhu
118 Followers 157 Following Ph.D. student @ Shanghai AI Lab & USTC. Interested in 3D vision & robot learning. PonderV2: https://t.co/C7XF871DXl RH20T: https://t.co/rlWsvZ75dFJamey Montella @JameyMontel
30 Followers 5K FollowingAnish Madan @anishmadan23
345 Followers 2K Following MS @CMU_Robotics | Prev: Associate ML Scientist @WadhwaniAI | @IIITDelhi '20Yongyuan Liang @cheryyun_l
440 Followers 114 Following @umdcs #RL #TrustworthyAI Prev. @Uber AI/@MSFTResearch AsiaHanxiao Jiang @jiang_hanxiao
267 Followers 321 Following Ph.D. student @IllinoisCS. Research interest: Robot Learning, Robot Vision, 3D VisionYuncong Yang @yyupsong
26 Followers 56 Following Incoming CS PhD student at UMass Amherst, advised by @gan_chuang | Foundation Models/Robotics/Embodied AI | Previously @Columbia and @nvidiaCharis Outzen @OutzeChar
44 Followers 5K FollowingViacheslav Sinii @ummagumm_a
49 Followers 260 FollowingAbdessamad LOIS @Abdessamad71099
2 Followers 184 FollowingJayaram Reddy @Jayaram_Robot10
72 Followers 999 Following Masters Student at Robotics research centre @iiit_hyderabad. Interested in robot learning, long horizon planning and RL. Previously undergrad @iitmadrasEricka Sutyak @eric_suty
53 Followers 5K FollowingMila-rose Cachola @mila_cacho
57 Followers 5K FollowingKumarmoto @kuwelz
202 Followers 3K FollowingYunsheng Tian @YunshengTian
228 Followers 273 Following PhD Candidate @MIT_CSAIL working on robotics/ML/graphicsWeiyu Liu @Weiyu_Liu_
719 Followers 435 Following Postdoc @Stanford. I work on semantic representations for robots. Previously PhD @GTroboticsKaryl Bazinet @kar_bazi
34 Followers 5K FollowingWilliam Sun @williamsun2020
116 Followers 1K FollowingMaggie @mtauranga
0 Followers 390 FollowingJiaxun Cui @cuijiaxun
365 Followers 514 Following Ph.D. candidate @UTAustin 🤘 | Multi-agent Learning | SJTU @sjtu1896 | Research Intern FAIR Labs @AIatMeta, Tencent AI LabsCharles Zhang @__xiaohao__
0 Followers 1 FollowingYue Wang @yuewang314
5K Followers 933 Following Assistant Professor @ USC CS and part-time Research Scientist @ Nvidia Research. Previous: EECS PhD @ MIT CSAIL. Opinions are mine.Andre Ye @andreiskiii
106 Followers 207 Following @UWPhilosophy and @UWCSE ugrad. Current research interest: interrogating political/social structures and paradigmatic assumptions in data and models.Stone Tao @Stone_Tao
2K Followers 870 Following PhD @UCSanDiego @HaoSuLabUCSD working on scalable robot learning and embodied AI. Co-founded @LuxAIChallenge to build AI competitions. @NSF GRFP fellowNicklas Hansen @ncklashansen
2K Followers 591 Following PhD student @UCSanDiego. @nvidia fellow. Prev: @MetaAI, @UCBerkeley, @DTU_Compute, @NTUsg. Interested in reinforcement learning, representations, and robots.Chong Harry @ChongHarry1
90 Followers 570 FollowingBo Zhang (Tony) @zhangboknight
364 Followers 156 Following Senior Researcher at Microsoft Research AsiaMuhammad Aamir Gulzar @m_aamir_gulzar
10 Followers 318 Following Student | Tech Innovator | AI & Data Enthusiastalex rubinsteyn @iskander
5K Followers 4K Following Genomics + immunology + ML = personalized cancer immunotherapy. @CompMedUNC @UNC_Lineberger @OpenVax https://t.co/8DWibdgbLIDaniel Lawson @danielblawson9
87 Followers 362 Following Student, Purdue CS. Interested in ML, RL, and roboticsMarketIn @MarketIn_1
4K Followers 100 Following MarketIn is designed to forecast market trends by analyzing User Behaviors and Price Action.Arthur Allshire @arthurallshire
1K Followers 380 Following robotics & simulation. incoming PhD @Berkeley_AI. intern @NvidiaAI. prev EngSci @UofT 🇮🇪 🇨🇦 🇦🇺🇨🇭🇨🇿Shenlong Wang @ShenlongWang
1K Followers 407 Following Assistant Professor at @IllinoisCS; 3D Computer Vision and Robot Perception.RL_Conference @RL_Conference
2K Followers 240 Following Home of the first annual reinforcement learning conference. Stay tuned up for updates!Zhiwen(Aaron) Fan @WayneINR
642 Followers 176 Following PhD@UT Austin | QIF 2022 Fellowship | Intern@NV/Meta/Google | Previous Senior Algorithm Engineer @Alibaba | 3D Modeling/Understanding/Generation, AI4SpaceStephen James @stepjamUK
4K Followers 177 Following Leading the @Dyson Robot Learning Lab. Postdoc @UCBerkeley w/ @pabbeel. PhD Imperial College London w/ @ajdDavison. AI, Robotics, Machine Learning 🤖Carlo Sferrazza @carlo_sferrazza
474 Followers 202 Following Postdoc at @berkeley_ai. PhD from @eth_en. Robotics, Artificial Intelligence, Tactile Sensing.Physical Intelligence @physical_int
4K Followers 8 Following Physical Intelligence (Pi), bringing AI into the physical world.Marcel Torné @marceltornev
219 Followers 209 Following Researcher at the Improbable AI Lab @MIT CSAIL | MEng @Harvard | BSc @EPFLJerome Revaud @JeromeRevaud
1K Followers 95 Following AI researcher :: Computer vision :: 3D vision :: Team Lead :: Project Lead :: Naver Labs EuropeAnish Madan @anishmadan23
345 Followers 2K Following MS @CMU_Robotics | Prev: Associate ML Scientist @WadhwaniAI | @IIITDelhi '20Yongyuan Liang @cheryyun_l
440 Followers 114 Following @umdcs #RL #TrustworthyAI Prev. @Uber AI/@MSFTResearch AsiaNishanth Kumar @nishanthkumar23
1K Followers 685 Following Robotics + AI PhD Student @MIT_LISLab @MIT_CSAIL, and the Boston Dynamics AI Institute. Formerly @brownbigai, @vicariousai and @uber. S.B @BrownUniversity.Hanxiao Jiang @jiang_hanxiao
267 Followers 321 Following Ph.D. student @IllinoisCS. Research interest: Robot Learning, Robot Vision, 3D VisionXingyu Lin @Xingyu2017
1K Followers 338 Following Postdoc at @berkeley_ai. PhD from @SCSatCMU. #Learning #RoboticsHao Liu @haoliuhl
4K Followers 155 Following phd student @berkeley_ai https://t.co/ZNJawlrerS machine learning, neural networks.1X @1x_tech
9K Followers 2 Following Androids built to benefit society and meet the world's labor demand.Saining Xie @sainingxie
14K Followers 1K Following researcher in #deeplearning #computervision | assistant professor at @NYU_Courant @nyuniversity | previous: research scientist @metaai (FAIR) @UCSanDiegoLirui Wang (Leroy) @LiruiWang1
563 Followers 266 Following Ph.D. Student @MIT_CSAIL. Previously @uwcse and @nvidia. Robotics, Fleet Learning, Foundation Model 🤖Hanna Hajishirzi @HannaHajishirzi
6K Followers 328 Following Associate professor at @uw_cse; senior director at @allen_ai co-leading @allenNLP; AI/NLP researcher at @uw_nlpYuki Mitsufuji @mittu1204
3K Followers 99 Following PhD, Distinguished Engineer @Sony, Lead Research Scientist @SonyAI_global, Head of Creative AI Lab, Specially Appointed Associate Prof. @tokyotech_jpCongyue Deng @CongyueD
2K Followers 288 Following CS PhD student @Stanford | Previous: math undergrad @Tsinghua_Uni | ❤️ 3D vision, geometry, and artHuazhe Harry Xu @HarryXu12
2K Followers 895 Following Hi, I like reinforcement learning, robots, and video games:) I am an amateur pianist. Assistant Prof at Tsinghua; Postdoc at Stanford; Ph.D. at BerkeleyYunsheng Tian @YunshengTian
228 Followers 273 Following PhD Candidate @MIT_CSAIL working on robotics/ML/graphicsWeiyu Liu @Weiyu_Liu_
719 Followers 435 Following Postdoc @Stanford. I work on semantic representations for robots. Previously PhD @GTroboticsBoyuan Chen @BoyuanChen0
2K Followers 277 Following PhD student @MIT_CSAIL @MITEECS, Ex @GoogleDeepMind, @berkeley_ai; Doing AI & Robotics. Foundational model for decision making. World models and robotics.Jiaxun Cui @cuijiaxun
365 Followers 514 Following Ph.D. candidate @UTAustin 🤘 | Multi-agent Learning | SJTU @sjtu1896 | Research Intern FAIR Labs @AIatMeta, Tencent AI LabsYue Wang @yuewang314
5K Followers 933 Following Assistant Professor @ USC CS and part-time Research Scientist @ Nvidia Research. Previous: EECS PhD @ MIT CSAIL. Opinions are mine.Andre Ye @andreiskiii
106 Followers 207 Following @UWPhilosophy and @UWCSE ugrad. Current research interest: interrogating political/social structures and paradigmatic assumptions in data and models.Stone Tao @Stone_Tao
2K Followers 870 Following PhD @UCSanDiego @HaoSuLabUCSD working on scalable robot learning and embodied AI. Co-founded @LuxAIChallenge to build AI competitions. @NSF GRFP fellowEras Tour Resell @ErasTourResell
240K Followers 23 Following fill out the form in our bio so we can get your tickets to another swiftie! ran by @ttwaswift @folklorewlw and @floellasversionMinyoung Hwang @robominyoung
243 Followers 214 Following Incoming Grad @MIT_CSAIL, Currently Research Intern @carnegiemellon, Previously @allen_ai, @SNU | Robotics | Preference-based RL | Human-Robot InteractionYue Yang @YueYangAI
307 Followers 240 Following PhD student @upennnlp, interested in vision and language.Vincent Sitzmann @vincesitzmann
13K Followers 296 Following Assistant Professor @ MIT, leading the Scene Representation Group (https://t.co/h5gvhLYrtw). Neural scene reps., neural rendering, inverse graphics.Chris Paxton @chris_j_paxton
8K Followers 2K Following Mostly posting about robots. Embodied AI @hellorobotinc, formerly @AIatMeta, @NVIDIAAI, @zoox. All views my own.Rafael Rafailov @rm_rafailov
3K Followers 640 Following Ph.D. Student at @StanfordAILab. I work on Foundation Models and Decision Making. Previously @GoogleDeepMind @UCBerkeleyYifeng Zhu 朱毅枫 @yifengzhu_ut
1K Followers 538 Following Ph.D. student at UT Austin. Research interest in robot learning and general-purpose robots. Opinions are my own.Manling Li @ManlingLi_
3K Followers 422 Following Postdoc @Stanford, Incoming Assistant Professor @Northwestern, PhD @UIUC. Working on Knowledge Foundation Models, especially for Multimodal data (Language + X).Haoyu Xiong @Haoyu_Xiong_
2K Followers 2K Following Student researcher @CMU_Robotics/ I work on robotic agents in the real world #robotlearningChenlin Meng @chenlin_meng
8K Followers 834 Following Co-founder & CTO @pika_labs | ex @StanfordAILab @StanfordDemi Guo @demi_guo_
22K Followers 695 Following Co-founder & CEO @pika_labs | ex @StanfordAILab @HarvardYejin Choi @YejinChoinka
19K Followers 330 Following professor at UW, director at AI2, adventurer at heartCheck out my labmate @sjoshi804’s work on data-efficient CLIP at #AISTATS2024!
Proud to be presenting Data-Efficient CLIP sjoshi804.github.io/data-efficient… at AISTATS 2024! We propose the first theoretically rigorous method to select the most useful data subset to train CLIP models. On CC3M and CC12M, our subsets are upto 2.5x better than the next best baseline! 🧵👇
Premier-TACO has been accepted by ICML 2024🎉
Imagine an AI that not only learns quickly but adapts to your daily tasks autonomously. Meet Premier-TACO 🌮, a multitask feature representation learning designed for few-shot adaptation in sequential decision-making. Project 🔗: PremierTACO.github.io #FoundationModel4RL A 🧵
Did anyone test this #DUSt3R + #3DGS implementation? github.com/nerlfield/wild…
I believe any PhD who cares quality more than quantity works in single thread mode.
Out of curiosity, do AI PhDs normally work (lead) on several projects simultaneously? I have never managed to work on more than one project during my PhD and I tried to convince my students not to do so. The paradigm might have already changed, so I am asking here.
🔥🔥🔥We're excited to introduce Metric3d v2, the most advanced monocular geometry foundation model for depth and normals estimation, ranking #1 on over 10 benchmarks. Training code, HF demo, and Arxiv preprints are all available now! Github:github.com/YvanYin/Metric… #3D #AIGC
So you want to do robotics tasks requiring dynamics information in the real world, but you don’t want the pain of real-world RL? In our work to be presented as an oral at ICLR 2024, @memmelma showed how we can do this via a real-to-sim-to-real policy learning approach. A 🧵 (1/7)
Dexterous manipulation transfer wishes to transfer human manipulations to dexterous robot hand simulations and is inherently difficult due to its intricate, highly-constrained, and discontinuous dynamics and the need to control a dexterous hand with a DoF to accurately replicate…
🚀Next step in 3D scene understanding beyond objects and parts, we now explore interactive elements and functionalities👇 Check out our @CVPR challenge and win2️⃣RTX4090🏅 (sponsored by @Matterport🙏) 🛠️Details: opensun3d.github.io/cvpr24-challen… 📄Paper: scenefun3d.github.io #CVPR2024
SAM + Optical Flow = FlowSAM FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥 robots.ox.ac.uk/~vgg/research/…
I'm thrilled to join Princeton's faculty as an assistant professor in the ECE department starting Fall 2025 🐯 Stay tuned for the launch of my lab. We will develop generally helpful robots that learn and plan 🤖
Thank you @_akhaliq for sharing our work! In this #CVPR2024 project, we introduce Video2Game to convert a video capture of a real-world scene into an interactive game. video2game.github.io
Video2Game Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video Creating high-quality and interactive virtual environments, such as games and simulators, often involves complex and costly manual modeling processes. In this paper, we present
🎤🎤CVPR24 Highlight🔥🔥: PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI Still worried about how to do physical interactions with these synthetic scenes, especially the object parts? With PhyScene, we could generate infinite interactive 3D scenes with…
SpaTracker can track any 2D pixels in 3D space, which allows for better handling of occlusions and out-of-plane rotations. Only seen this on the 2D plane until, looks pretty dope! Cool 3D examples + Links ⬇️
✨ Presenting MicKey (#CVPR2024, Oral) ✨ We regress and match 3D camera coordinates rather then 2D key points, all in metric space. Gives you a scaled relative pose between two RGB images. Paper: arxiv.org/abs/2404.06337 Page: nianticlabs.github.io/mickey
- Three training views on #DL3DV-10K datasets - Camera poses & intrinsics are unknown - Rendering by interpolation - Resolution: 1920x1080 I can tell, pseudo-views are needed to enhance the quality.
Speeding your view synthesis(<40s) with #InstantSplat! Our large-scale, pose-free method trains in just 37 seconds from sparse views—no #COLMAP, no intrinsics needed. Achieving nearly 30dB test PSNR with just 12 images, New standard in #NVS and new training efficiency.…
If you want to know more about DUSt3R and InstantSplat, the new rising stars on the #3DGS sky, bookmark @hupobuboo's stream or watch his recordings later. His paper readings are legendary and there is s lot to learn from! Highly recommend!
better faster stronger 3DGS, thanks @janusch_patas for the recommendation x.com/i/broadcasts/1…
I defended my PhD @MITEECS this week! Thanks to everyone who came out. And thanks especially to @nishanthkumar23 who not only managed the Zoom, but also got me this amazing gift…
Join us at the **5th** Embodied AI Workshop in Seattle on June 18 #CVPR2024 🔊 Exciting invited speakers, 🥷 6+ challenges (with cash prizes), 📋 poster session, and 👽 lots more! 📜Workshop paper submission details coming soon Website: embodied-ai.org
I'm happy to announce the fifth annual Embodied AI Workshop at CVPR! Our theme is open world embodied AI, and we'll have six speakers on how we can make that happen, and six challenges where approaches can prove that they can! #cvpr2024 #embodiedai embodied-ai.org