Ying Shan @yshan2u
Distinguished Scientist @TencentGlobal, Founder of PCG ARC Lab, Director of AI Lab Visual Computing. Formerly @Microsoft, @MSFTResearch. Views are my own. Joined June 2014-
Tweets719
-
Followers1K
-
Following570
-
Likes3K
A tiny bee-shaped robot that flies in swarms autonomously, using an ultra-wideband indoor positioning system.
A tiny bee-shaped robot that flies in swarms autonomously, using an ultra-wideband indoor positioning system. https://t.co/ZQNHqixPCT
Connecting U-Net and Belief Propagation!
Real world from the views of real "agents"!
Real world from the views of real "agents"! https://t.co/qKQpXipDBu
Text to Video is in GenAI arena! Collecting votes at: huggingface.co/spaces/TIGER-L…
Text to Video is in GenAI arena! Collecting votes at: huggingface.co/spaces/TIGER-L…
A benchmark of Multimodal Agents w/ 369 task-based evals. Humans can accomplish over 72.36% of the tasks, while the best current agent only 12.24%.
A benchmark of Multimodal Agents w/ 369 task-based evals. Humans can accomplish over 72.36% of the tasks, while the best current agent only 12.24%. https://t.co/4Giop9pSq8
Element level editing making progress!
Element level editing making progress!
Advice for young scientists: optimize fun😊
How a plant breathes🍃
How a plant breathes🍃 https://t.co/4jGn0TCBuf
[LG] A Survey on the Memory Mechanism of Large Language Model based Agents arxiv.org/abs/2404.13501 - The memory module is a key component that differentiates agents from original large language models (LLMs), enabling agent-environment interactions. - Memory serves…
[SIGGRAPH '24]: TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts Paper: arxiv.org/abs/2401.14828 Project: zjy526223908.github.io/TIP-Editor Code: github.com/zjy526223908/T…
In the era of #Sora, it’s important to detect whether a video is AIGC and who is the owner. Happy to introduce RingID, a diffusion-based watermark identification method that can not only identify whether an image/video is generated or not, but also by who: arxiv.org/abs/2404.14055
Thanks to @_akhaliq for sharing! 🔥 Check out our SEED-Bench-2-Plus, the most comprehensive benchmark for assessing MLLM's performance in text-rich image understanding. It consists of 2.3K questions spanning 63 different scenes. 🤗 - Project page: github.com/AILab-CVC/SEED…
Thanks to @_akhaliq for sharing! 🔥 Check out our SEED-Bench-2-Plus, the most comprehensive benchmark for assessing MLLM's performance in text-rich image understanding. It consists of 2.3K questions spanning 63 different scenes. 🤗 - Project page: github.com/AILab-CVC/SEED… https://t.co/RlJCWZDwQU
SEED-Bench-2-Plus Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension Comprehending text-rich visual content is paramount for the practical application of Multimodal Large Language Models (MLLMs), since text-rich scenarios are ubiquitous in the
A launchpad for product designs, with built-in Gen AI tools!
A launchpad for product designs, with built-in Gen AI tools! https://t.co/Y03eiHVTVR
Wearable MLLMs (Multimodal LLMs) has chance going mainstream this time! 🚀✨
Wearable MLLMs (Multimodal LLMs) has chance going mainstream this time! 🚀✨ https://t.co/SOmDEIqxae
Thanks @_akhaliq for featuring! SEED-X is a unified MLLM designed for both real world understanding and generation tasks, with competitive results. Feel free to try it out! Project page: github.com/AILab-CVC/SEED… CC: @tttoaster_ , Sijie Zhao, Jinguo Zhu, @ge_yixiao , Kun Yi, Lin…
Thanks @_akhaliq for featuring! SEED-X is a unified MLLM designed for both real world understanding and generation tasks, with competitive results. Feel free to try it out! Project page: github.com/AILab-CVC/SEED… CC: @tttoaster_ , Sijie Zhao, Jinguo Zhu, @ge_yixiao , Kun Yi, Lin…
Interstellar debugging (over 15 billion miles away) wakes up Voyager 1, resuming its engineering updates to Earth! 😊
Interstellar debugging (over 15 billion miles away) wakes up Voyager 1, resuming its engineering updates to Earth! 😊 https://t.co/NeXpyaMPUX
Successful editing of DNA in human cells with gene editors fully designed with AI!
Successful editing of DNA in human cells with gene editors fully designed with AI! https://t.co/Crxzw4npjc
Song Mei @Song__Mei
1K Followers 571 Following Assistant Professor at UC Berkeley, Department of Statistics and EECS. Researcher working on foundations of AI and deep learning.IAComunIA @IAcomunIA
398 Followers 1K Following Descubre todo el poder de la IA a tu alcance con ✨IAcomunIA. 🤖 IA Explorador 💬 Comparto IA 👉 Comparo IA ✨Explora las posibilidades ✨ https://t.co/8ITq0xaBiLSujith Joseph @sujithjoseph
107 Followers 1K FollowingJiteng Mu @JitengMu
391 Followers 628 Following Ph.D. student in ECE @UCSD ; previously M.S. in Robotics @JohnsHopkins ; Intern @Nvidia @AdobeDonglai Xiang @DonglaiXiang
1K Followers 727 Following Research Scientist at Nvidia. Previously Ph.D. from Carnegie Mellon University; visiting researcher at Meta Reality Labs.tennant @BingChenZhao2
2 Followers 3K FollowingYiming Shi @uestcshiym
17 Followers 207 Following Pursuing a PhD in multimodal modeling. Undergrad @UESTC1956 Think and Move forward. e/accArif Ahmad @arif_ahmad_py
274 Followers 7K Following All things AI, Computer Science and Circuits! Prev. @GoogleAIXu Cao @Xu_Cao_
220 Followers 627 Following Research scientist @ CyberAgent Inc. AI Lab | Ph.D. @ Osaka University | 3D Computer VisionQinghe Wang @HuaqiangLiu666
39 Followers 64 Following Ph.D Candidate, Dalian University of Technology.Timothée Coolamet @KaladinFree
15K Followers 767 Following Christian, husband, father. Independent. Cybertruck Enthusiast. Jack Smith fan club. Blocker of gnat accounts. #DoNotUnite🚫 #BreakTheCult #BurnItDownEkue @ekpodar
1K Followers 1K Following I am interested in Tech/AI, Marketing, and complex systems, I will posts random stuff in those categoriesNirvana.Viaje @NirViaje
702 Followers 4K Following Math, Complex System, Political Science, Circuit and HAM, Cycling, Piano.. .etczhao wei li @lizhaowei126
5 Followers 32 FollowingMonkey @a33668874586
45 Followers 394 FollowingStefano Perna @st3p_dot_io
27 Followers 101 Following Industrial PhD Student at @translation @UnivRoma3 | AI ResearcherKim wong @Kimwong379341
4 Followers 58 Following Like girls, women. I'm a cleanly boy, so I hope you are cleanly too.Andrea Bajcsy @andrea_bajcsy
1K Followers 183 Following Assistant Professor @SCSatCMU, @CMU_Robotics | PhD from @Berkeley_EECS | Robots, humans, learning, and safetymarsx @zxc011100
39 Followers 186 FollowingJoahakim @Joahakim2
46 Followers 276 FollowingWalid BOUSSELHAM @BousselhamWalid
80 Followers 192 Following PhD Student at Bonn University | Computer Vision, Multi-modal learning and Zero-shot adaptation. Prev. @NUSingapore & @ENSTAParisRuzcko @ruzcko
121 Followers 273 Following PhD in Artificial Intelligence Student 📍 UNIST, South Korea 🇰🇷 IG: @/ruzckoWeidi Xie @WeidiXie
2K Followers 577 Following Computer Vision Researcher. Associate Professor at SJTU, Previously @Oxford_VGG. 中文名:谢伟迪 Personal Webpage: https://t.co/sZoZ0AfKrXRan Ding @AlfredDing6
142 Followers 540 Following 📚 MSc Informatics student @TU_Muenchen 🔬 Student Researcher @tumcvg 🤖 Make robot intelligent and Accelerate human abundance #AI #Rob #ComputerVisionYolanda He @CrossingZebraAI
125 Followers 877 Following Founder of @ArtefactsAI & Co-Creator of @AEONLabs_xyzAaditya ; @Aaditya26082004
526 Followers 7K Following CS'26 • Machine Learning • Open-Source • Web Dev. • Algorithms • Jai Shree Krishna 🦚🪈Fan @Zhang_Fan_
7 Followers 64 FollowingHenry Carrillo @HenryCa58558303
54 Followers 1K FollowingZhaoyang Wang @wangwan83764204
309 Followers 4K Following CS PhD student at UoB in the United Kingdom. Research interests: Automated Machine Learning, Online Learning, and Reinforcement Learning 🏳️🌈永远满仓的Kevin @KevinWang676
0 Followers 28 Following 重度AI爱好者、开发者,业余up主,GitHub 3k stars,关注多模态AI,持续分享AI行业观察,欢迎交流~ bilibili: https://t.co/ouwzllDhgn GitHub: https://t.co/xaKOk6e7Rz 永远满仓,永远热泪盈眶!Makya @Makya12345678
6 Followers 962 FollowingBoying Li @BoyingLi_LBY
12 Followers 79 Following Research Fellow at @MonashUni, PhD from Shanghai Jiao Tong University @sjtu1896 | 3D computer Vision, Robotics, SLAM.Liangyu Chen @cliangyu_
523 Followers 1K FollowingWeitong ZHANG @WeitongZhang
1K Followers 3K Following Dissertation-year CS Ph.D. Candidate @UCLA | Ex-intern @nvidia |@amazon fellow | On 2024 academic job marketJinlu Zhang @JinluZhang1126
31 Followers 241 Following Ph.D student at CFCS, Peking University. focusing on 3D human-centric vision field.He Zhang @ZH28181
92 Followers 75 Following Researcher at Tencent Robotics X. Previously PhD at University of EdinburghMoises Sanabria.lens @moisesdsanabria
4K Followers 3K Following Chief Prompt Officer @lore_machine, Founder @AI24live, Resident Artist @BACMiami - also @moisesnotfoundNayan Saxena @SaxenaNayan
2K Followers 2K Following Brought artificial intelligence to @RBC, @Glowforge, @Wombo, @Bell & beyond.Michael Pyrcz🌻 @GeostatsGuy
23K Followers 342 Following #Professor @UTAustin @CockrellSchool @txgeosciences @daytum_io #Ukrainian #Canadian #geostatistics #DataAnalytics #DataScience #MachineLearning #author #fatherDonglai Xiang @DonglaiXiang
1K Followers 727 Following Research Scientist at Nvidia. Previously Ph.D. from Carnegie Mellon University; visiting researcher at Meta Reality Labs.Timothée Coolamet @KaladinFree
15K Followers 767 Following Christian, husband, father. Independent. Cybertruck Enthusiast. Jack Smith fan club. Blocker of gnat accounts. #DoNotUnite🚫 #BreakTheCult #BurnItDownAndrea Bajcsy @andrea_bajcsy
1K Followers 183 Following Assistant Professor @SCSatCMU, @CMU_Robotics | PhD from @Berkeley_EECS | Robots, humans, learning, and safetyWeidi Xie @WeidiXie
2K Followers 577 Following Computer Vision Researcher. Associate Professor at SJTU, Previously @Oxford_VGG. 中文名:谢伟迪 Personal Webpage: https://t.co/sZoZ0AfKrXNayan Saxena @SaxenaNayan
2K Followers 2K Following Brought artificial intelligence to @RBC, @Glowforge, @Wombo, @Bell & beyond.Moises Sanabria.lens @moisesdsanabria
4K Followers 3K Following Chief Prompt Officer @lore_machine, Founder @AI24live, Resident Artist @BACMiami - also @moisesnotfoundVivek Gupta @keviv9
2K Followers 5K Following PostDoc @cogcomp UPenn | Ph.D. CS @UUtah | @iitkanpur. @Bloomberg & @MSFTResearch Fellow | ex-@MetaAI, @IBM, @Verisk, @samsungresearch, @Synopsys #nlp #mlMarc Andreessen 🇺�.. @pmarca
1.4M Followers 24K Following Techno-optimist. E/acc. Technology brother. Move Fast and Make Things. p(Doom) = 0; p(“1984”) = not 0.zzachzhang @zzachzhang36427
5 Followers 7 FollowingNick Matarese @nmatares
1K Followers 1K Following Design Lead for @YouTube’s Generative AI and Advanced Capabilities teams | prev. Google ATAP, Google Home, and Google Wifi.Emm @emmanuel_2m
32K Followers 6K Following Co-founder & CEO at https://t.co/7ElrGjg10n 🚀 | Craft unique and style-consistent game assets with custom-trained AI models 👾 | #GenAI #Gaming @scenario_ggLingjie Liu @LingjieLiu1
3K Followers 642 Following Assistant Professor at UPenn. Research interests: Neural Scene Representation, Neural Rendering, Human Performance Modeling and Capture.proxima centauri b @proximasan
10K Followers 840 Following she/they 🌿 • kuudere at https://t.co/4ZLnfb7qXc • fine-tuning at @LeonardoAI_ • #aiart #posthumanism 🤖✨🌈 • opinions largely due to viral stowaways in my dnaKirito (e/acc) 🏴�.. @bronzeagepapi
3K Followers 5K Following engineer scientist artist –– moloch disrespectoor // qualia connoisseur // tensor whisperer // epistemology enjoyer // kardashev mechanic // bounty hunterWenhu Chen @WenhuChen
11K Followers 520 Following AI researcher @UWaterloo @GoogleAI @VectorInst. Interested in natural language processing, diffusion models. I direct TIGER-Lab at UWaterloo.khalid @k_saifullaah
3K Followers 1K Following cs phd student @umdcs. cinephile🎞️, mostly into ai research🧠, visualization🎨, photography📷. prev: ai research @adobe, @deltanalytics fellow 🇧🇩Haotian Zhang @HaotianZhang4AI
432 Followers 239 Following Research Scientist @ Apple. Ex-Research Intern @ MSR AI. Ph.D. @ UW. Be Borderless.Alara Dirik @alaradirik
1K Followers 242 Following PhD candidate and @GoogleDeepMind scholar at @imperialcollege, previously at @huggingface and @unibogaziciZhaoyang Lv @LvZhaoyang
1K Followers 518 Following Research Scientist @RealityLabs Research. Previously Ph.D. at @GeorgiaTech All the bullshit is my own.Mehdi (e/flλ) @BetterCallMedhi
15K Followers 2K Following Manufacturing the future at the intersection of DeepTech, AI & DeSci @joininteract @_buildspace ex @ens_ulmEthan @Ethan_smith_20
3K Followers 687 Following a boy and his gpu vs the world. directing research at @leonardoai_. learning as I go. uf psych. generative models and representation learningJavi Lopez ⛩️ @javilopen
83K Followers 1K Following I spend endless hours researching AI to bring you tuts, tools & news. Founder @Magnific_AI 🤖 Prompts: https://t.co/kd37b47f4n 🔥 Tuts: https://t.co/UeZrLtBIpnMichal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindIntellect2 @Intellect2ai
2K Followers 2K Following A software solutions company offering end-to-end advanced data solutions powered by modern #datascience and #AI technology.【𝕐o𝕦𝕤𝕖�.. @YosGPT
10K Followers 5K Following Programming Engineer & Linux+ | IT & Net+ | CCIE & CISSP | Azure Developer & Multi-Clouds Architect+ | Quantum AI Builder+ | #الحمدلله_على_نعمة_الامارات 🇦🇪 ❤️James Matthew Rehg @RehgJim
978 Followers 1K Following Founder Professor of CS & ISE @IllinoisCS @IllinoisISE and Director of @ILHealthEng at @UofIllinois. Researcher in computer vision, mobile health, & social AIJunyang Lin @JustinLin610
5K Followers 1K Following Chief Evangelist Officer of Qwen Team & OpenDevin, building LLM and LMM. Now @Alibaba_Qwen . Previously @PKU1898 LANCO group. ❤️ 🍵 ☕️ 🍷 🥃Peter Chen @peterxichen
3K Followers 1K Following Covariant CEO and Co-Founder. Previously @OpenAI, @UCBerkeley PhD.Pinar Yanardag @PINguAR
4K Followers 709 Following Assistant Prof. #VirginiaTech CS. Formerly #MIT #Purdue #Bogazici. #Emmy Nominated Creative Director, #Fulbright Fellow. Contact: [email protected].Prof. Chuixiang (Tree.. @cyi12
16K Followers 17K Following Earth resilience, tipping behavior, nonlinear thinking, stability analysis, climate change, photosynthesis, soil respiration, tree mortality, Fulbright ScholarHaihao Shen @HaihaoShen
3K Followers 3K Following Creator of Intel Neural Compressor/Speed/Coder, Intel Ext. for Transformers, AutoRound; HF Optimum-Intel Maintainer; Founding member of OPEA; Opinions my ownDeemos Tech @DeemosTech
5K Followers 269 Following Pioneering 3D Generative AI: https://t.co/uHgZ0XFSTy ChatAvatar: Text/Image to production-ready 3D avatars.I. Yosun Chang @Yosun
4K Followers 1K Following {wonder, innovation, elegance} ∈ I turn emerging technologies into award winning apps. Ex-Hackathon pro. #3D #AR #AI since forever. Mad science and artistry ❤️juju @juxuan_27
87 Followers 83 Following Ph.D. Candidate @cuhkcse, Research Intern @TencentGlobal ARC, Previous Intern @IDEA, @SenseTime_AIVR/AR Association (VR.. @thevrara
26K Followers 9K Following We are #VRARA We help you Grow, Learn, Connect! Join our virtual and in-person events! #augmentedreality #vr #ar #virtualreality #spatialcomputing #aiWannan (Winnie) Yang .. @winnieyangwn
538 Followers 220 Following Interested in how memory& learning works in brains 🧠 and machines 🤖|| geometry of memory 🌐 during learning and sleep 😴 || PhD student in the Buzsaki LabJihyun Lee @jyun_leee
182 Followers 139 Following PhD Student @ KAIST | Incoming Intern @RealityLabs | Digital Humans & 3D VisionEgo4D @ego4_d
1K Followers 440 Following Massive-scale (but accessible) datasets and benchmark suites for human activity understanding https://t.co/swnxuaCth1 & https://t.co/ajYTwb7yPbLewis Walker ➲ @lewiswalkerai
5K Followers 5K Following Follow for Generative AI insights shared daily | Deloitte AI | Ex-Goldman Sachs | LinkedIn Top AI VoiceBanghua Zhu @BanghuaZ
2K Followers 804 Following PhD @Berkeley_EECS, statistics, info theory, LLM, RL, Human-AI Interactions.Allen Z. Ren @allenzren
654 Followers 638 Following PhD student in robotics @Princeton with @Majumdar_Ani. Past intern at @GoogleDeepMind @ToyotaResearch.Nikolaos Sarafianos @sarafianosn
878 Followers 504 Following Research Scientist @RealityLabs working on 3D generative models約34g、長さ22cm、羽根幅24cmのハチ型ロボット youtu.be/UzRf9y9EWqM 超広帯域技術(UWB)を使用した屋内位置特定システムにより、群れをなして自律飛行することができる #robot #robotics #Biorobotics #biomimicry #バイオミミクリー #生物模倣 #ハチロボット #BionicBee #Festo
Why do diffusion models use the U-Net architecture? Fascinatingly, the U-Net's encoder-decoder structure with long skip connections naturally encodes the belief propagation algorithm for hierarchical models. Explore more in this paper! arxiv.org/abs/2404.18444. .
Ever wondered how to exploit unlabeled LiDAR data for 3D object detection? Check out #𝑺𝒆𝑴𝒐𝑳𝒊!! We use motion patterns to cluster points into objects and extract class-agnostic pseudo-labels even across datasets!! @CVPR @lealtaixe @AljosaOsep 👇🧵 research.nvidia.com/labs/dvl/proje…
i haven't logged into stackoverflow for months or years and suddenly i'm in the top 2% 🤣 - this is my secret account where i used to ask all of my dumb questions before LLMs could rtfm for me
Animals are intelligent agents that plan and act to accomplish complex goals. Can we try learning from them? We present EgoPet, a new ego centric video dataset of animals scraped from YouTube and TikTok.
Excited to share our latest research, "Multidimensional Interpolants," now available on #arXiv! Exploring new dimensions in flow and diffusion, we're planning further experiments to enrich our insights. Check it out: arxiv.org/abs/2404.14161 #ML #AI #GenerativeAI #Flow #Diffusion
I think this is a very interesting point, and I've spent some time working on the controllability aspect. E.g., can we use concepts from control theory to better guide AI models? Talk I've given (see 2nd half): yisongyue.com/talks/structur… 1/3
It strikes me that AI alignment/safety is like controllability, and AI interpretability is like observability. These are both classical concepts from system theory that seem to be largely unknown to AI researchers.
Delighted to see our AutoDAN project featured in @khulick's latest piece on AI jailbreaks! 🚀 Discover more about AI safety in the full article: snexplores.org/article/chatbo…. Thanks for the wonderful write-up, Kathryn! See our tweet: x.com/furongh/status… #AISafety #AutoDAN
🔐 #Jailbreaking #LLMs is an urgent concern that impacts more than just the tech world — it's a vulnerability that could affect systems integral to our daily lives. Manual attacks are troubling, but autonomous jailbreaks that transfer across different LLMs is a recipe for…
The most interesting design of image elemement is that it doesn't require any explicit editing supervision. The scaling and translating capabilities just emerge automatically.🪄
We introduce🌟Editable Image Elements🥳, a new disentangled and controllable latent space for diffusion models, that allows for various image editing operations (e.g., move, resize, de-occlusion, object removal, variations, composition) jitengmu.github.io/Editable_Image… More details🧵👇
Let's go!! Common Voice 17 - now on the Hub! 🔥 With 31,000 hours of audio (& transcriptions) across 124 languages. *sound on 🎶* 847 hours of data were added in CV 17, along with 493 hours of validated data. Four new languages have been added to this edition: Haitian…
“Control and predictability > easy entry point.” Yes 💯 The pros want consistency and control.
Design/UI confession - Last year I was a bit of a “chatbot maximalist”: “Screw the 300 buttons in Adobe — give me Jarvis! You don’t need to learn a new UI, just ask it for what you need!” But then, being in market, we quickly realized that, at least for most visual tasks:…
I just reached 5k Google scholar citations. Citations remind me that I’m part of a scientific community and that my students & I are helping others! Stoked! Don’t tell anyone, but I still can’t believe that I’m a professor. It is my greatest honor educate the next generation of…
Post a picture YOU took. Just a pic. No description
Fully local Video Summaries with llama3 on @ollama. Breaks up longer videos into chunks and provides a summary. Lots of questions on the last vid so here i am fixing errors real time. Open-source: git.new/local-vid-summ…
Thanks @_akhaliq for promoting our work. AdvPrompter finally passed the arXiv moderation and now have an arXiv link: arxiv.org/abs/2404.16873. For a brief review of the paper, please check x.com/tydsh/status/1…. @brandondamos has provided a more detailed explanation:…
Meta presents AdvPrompter Fast Adaptive Adversarial Prompting for LLMs While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful content.
We are happy to integrate "text-to-video" into GenAI arena huggingface.co/spaces/TIGER-L…. Currently, we support six open-source video generation models. Please help us vote to create the video leaderboard! For "text-to-image" arena, Playground V2 and V2.5 @playground_ai are leading…
Goodbye LoRA 👋 (Part 999) MultiBooth can generate images that include any number of concepts in various styles, contexts, and layout relationships as specified by given text prompts. multibooth.github.io
Explore immersive Mars footage with the #Perseverance rover from @NASA . We can recover the 3D from #Perseverance's stereo navigation cameras! Detailed 3D reconstructions can be done in just ~20 seconds from scratch, without using the calibration from @NASA_Technology .…
We introduce🌟Editable Image Elements🥳, a new disentangled and controllable latent space for diffusion models, that allows for various image editing operations (e.g., move, resize, de-occlusion, object removal, variations, composition) jitengmu.github.io/Editable_Image… More details🧵👇