Siddharth Choudhary @siddharth0708
Sr. Applied Scientist @Amazon AGI and AWS AI labs | Ex @amazon halo | Previously @magicleap | Georgia Tech CS PhD | IIIT-H Alum itzsid.github.io Dublin, CA Joined November 2013-
Tweets52
-
Followers260
-
Following736
-
Likes876
We present SplatArmor, a fully articulated Gaussian splatting model for human avatars. Our model includes both rigid and non-rigid skinning components, and a Neural Color Field for implicit color regularization. Project page: jenaroh.it/splatarmor
rebuttal.pdf uploaded ✅ rebuttal.mp3 uploaded ✅ Whats more fun than writing a rebuttal? Making an AI-generated diss track for the #iccv2023 reviewers (ft. @atemyipod ) it's amazing how effortless this is to make #iccv soundcloud.com/rohit-kumar-je…
My Ph.D advisor's startup @hellorobotinc comes out of stealth mode :-)
My Ph.D advisor's startup @hellorobotinc comes out of stealth mode :-)
🎉 Introducing... Methods! We are now tracking 730+ building blocks of machine learning: optimizers, activations, attention layers, convolutions and much more! Compare usage over time and explore papers from a new perspective. Browse the catalogue here: paperswithcode.com/methods
This graph is really eye-opening.
A new experimental feature in the @magicleap OS 0.98.10 update; Found Objects. Developers can access this information which makes me want to make a bridge-building game across my living room. #magicleapdevs.
@tokufxug thanks for sharing this exciting experimental platform feature! a team of engineers and designers did a lot of work to bring it to light in the latest release. here’s another video of it in action.
Excited about releasing a 3d object recognition feature with the latest update. The algorithm is designed with scalability, multi-user and persistence scenarios in mind.
Excited about releasing a 3d object recognition feature with the latest update. The algorithm is designed with scalability, multi-user and persistence scenarios in mind.
𝟯𝗗 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗦𝗰𝗲𝗻𝗲 𝗚𝗿𝗮𝗽𝗵𝘀: 𝗔𝗰𝘁𝗶𝗼𝗻𝗮𝗯𝗹𝗲 𝗦𝗽𝗮𝘁𝗶𝗮𝗹 𝗣𝗲𝗿𝗰𝗲𝗽𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗣𝗹𝗮𝗰𝗲𝘀, 𝗢𝗯𝗷𝗲𝗰𝘁𝘀, 𝗮𝗻𝗱 𝗛𝘂𝗺𝗮𝗻𝘀 #mitSparkLab Video: youtu.be/SWbofjhyPzI Paper: arxiv.org/abs/2002.06289
great guest lecture by John Leonard for MIT 16.485 Visual Navigation for Autonomous Vehicles youtu.be/rm23cEvQNvE
I think every graphics engineer should work on a computer vision team for a while, and vice versa.
Seems troubling: Many of the images in the CXR-14 chest x-ray data set are post treatment and have chest drains in the images. Once these examples are removed, machine learning performs worse than a first year resident. h/t @DrLukeOR arxiv.org/abs/1909.12475
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.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)Mustafa Mukadam @mukadammh
1K Followers 270 Following Research Scientist @AIatMeta (FAIR). PhD from @GTrobotics (Georgia Tech). Robotics and Machine Learning.Varun Agrawal @varagrawal
936 Followers 455 Following PhD padawan @GeorgiaTech | Robotics | CS https://t.co/QzLezFDRkBVassilis Choutas @vchoutas1
2K Followers 2K Following Research Scientist @Google, Ph.D. from @PerceivingSys and @ETH, prev. intern @Microsoft and @RealityLabs, ECE @Aristoteleio, trying to capture 3D humansGiovanni Beltrame @jumpjoe78
483 Followers 377 Following Computer engineer, academic. Mastodon @[email protected]Yuliang Xiu @yuliangxiu
5K Followers 4K Following Ph.D. in Vision & Graphics @MPI_IS, previously @USC_ICT. Focusing on democratizing human-centric digitization. Intern at @RealityLabs @UbisoftRosalina Thom @rosal_tho
0 Followers 77 FollowingJoyceRobin @0pvu1syQcGV1i
0 Followers 210 FollowingOtelia Faville @FaviOteli
43 Followers 5K FollowingBlewflo @Blewflo4dI
1 Followers 177 FollowingJack FitzGerald @jgmfitz
10 Followers 197 Following Principal, Applied Scientist at Amazon AGI org | AI model and system builder | LLM and multimodal research | Views my ownMildredReed @ZyWukYbGeC1h8
0 Followers 211 FollowingKarlene Maiava @KarleMaiav
54 Followers 5K FollowingAlessandro Favero @alesfav
282 Followers 571 Following Physics/ML PhD candidate @EPFL working on the foundations of deep learning. Former applied scientist intern @AWSCloud AI Labs.Denis A. @den_run_ai
603 Followers 971 Following AI Scientist @ServiceNow | LLM Code Gen | Marathon Runner | Founder @aikynetixSlesesl @slesesl44665
1 Followers 367 FollowingTeknium (e/λ) @Teknium1
29K Followers 3K Following Cofounder @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE Support me on Github SponsorsGeorgia Pesola @GeorgiaPes54889
74 Followers 5K FollowingSimran Morta @sim_morta
78 Followers 5K FollowingEloise Ferri @EloiseFerr86779
35 Followers 5K FollowingEverley Lausen @EverleyLau37028
91 Followers 5K Followingshubman gill 208(149).. @ItsPrannay
171 Followers 383 Following I like cricket | Always hungry for mum’s keema | Turning lemonade into lemons since 1996 | PhD in Machine Learning | 🇮🇳🇬🇧Sandra Linda @KamalRakes2627
5 Followers 197 FollowingShikun Liu @liu_shikun
992 Followers 738 Following Ph.D. student at the Dyson Robotics Lab at Imperial College.Prasanna S @myprasanna
10K Followers 7K Following Co-Founder @Rippling @0xPPL_; Angel Investor: https://t.co/pjiWi4E1BlLong Le @int64_le
46 Followers 185 Following Assistant (ᴛᴏ ᴛʜᴇ) Professor @GRASPLab @Penn. Previously @Google, @CarnegieMellon, @Meta, @UMassAmherstHamid Naderi Yeganeh @naderi_yeganeh
35K Followers 32K Following Research Student @UCL Maths. Mathematical artist. Email: naderiyeganeh at gmail dot comAli K @alihkw_
277 Followers 1K Following DMs Open! AI & Robotics MSc at @Mila_Quebec/@UMontreal. Prev: nlp at @amazonscience, compsci at @UofT. Slowly figuring out how to make robots learn.Chethan Parameshwara @cmparam
346 Followers 542 Following AI Researcher @AmazonScience | Multimodal AI | PhD @UofMarylandleonidk @leo_nid_k
454 Followers 361 Following Vision, Graphics, Learning & Robotics. berkeley + stanford + cmu (bs + ms + phd). notable: intel realsense & diff. rendering w/ 3d gaussiansNikhil Varma Keetha @Nik__V__
870 Followers 918 Following PhD in Robotics @CMU_Robotics @airlabcmu | Making Robots Temporally See the World🤖🌍👀 | Cook👨🍳 Gamer🎮 Movie Buff🎥Stephanie Chan @scychan_brains
3K Followers 2K Following Senior Research Scientist at DeepMind. Artificial and biological brains 🤖 🧠 Views are my ownBarbara @barbara44carpen
117 Followers 3K 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.S.K.MAHLA @SKMAHLA2
8 Followers 810 FollowingFree Delivery @and_blogge52384
1K Followers 4K FollowingRan Cheng @RanCheng10
198 Followers 1K Following Head of AI at Eureka Robotics & Midea Group MCA, formerly a research engineer at Huawei Noah's Ark Lab, Canada.Chen Feng @simbaforrest
348 Followers 134 Following Assistant Professor at NYU (robotics, computer vision, construction automation)Shital Shah @sytelus
10K Followers 8K Following Deep learning research and code. If universe is an optimizer, what is the loss function? All opinions are my own.npj Digital Medicine @npjDigitalMed
3K Followers 1K Following Open access @NaturePortfolio journal for the #DigitalHealth community, publishing research, reviews & comments. Tag us & tweet your work with #npjDigitalMed.Arsh Verma @imarshverma
283 Followers 699 Following Associate ML Scientist @WadhwaniAI | CSE @ IIITD'21advocate debchand agr.. @debchand92
28 Followers 70 Following I am an advocate practicing in taxation lawsJiefeng Chen @jiefengchen1
335 Followers 528 Following Research Scientist at Google | Working on LLM Research.Makarand Tapaswi @MakarandTapaswi
1K Followers 530 Following Senior ML Scientist @WadhwaniAI | Assistant Professor @IIIT_Hyderabad | Opinions my ownJames Morrison Rubin @import_jmr
6K Followers 6K Following Product Lead | Bringing Gemini to life @Google Tweets are my own. Retweets are not endorsements. Joyful Learning MachinesShashank Tripathi @sha2nk_t
824 Followers 751 Following PhD student at Max Planck Institute for Intelligent Systems. Meta Research Fellow, 2023. prev: @amazon, @CarnegieMellonTarun Raheja @atemyipod
430 Followers 1K Following grad student @penn | machine learning etc | @bitspilaniindia gradIgor Napolskikh @igornaps
7 Followers 91 FollowingYang Chen @ychenNLP
663 Followers 438 FollowingMuhammad Waseem H @hwaseem04
99 Followers 788 Following Research Intern @CVC_UAB | Prev @ CVIT @iiit_hyderabad | Computer Vision | Anything techMohamed El Banani @_mbanani
576 Followers 905 Following PhD student @UMichCSE. Prev: @MetaAI, @GoogleAI, @GeorgiaTech. I am interested in computer vision, machine learning, and cognitive science. 🇪🇬Animesh Garg @animesh_garg
21K Followers 1K Following Foundation Models for Generalizable Autonomy. Assistant Professor in AI Robotics @GeorgiaTech + @NvidiaAI. prev @Stanford @berkeley_ai @UofTCompSciMichael Black @Michael_J_Black
59K Followers 646 Following Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.AK @_akhaliq
311K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxMatthias Niessner @MattNiessner
32K Followers 163 Following Professor for Visual Computing & Artificial Intelligence @TU_Muenchen Co-Founder @synthesiaIOFrank 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.Kosta Derpanis @CSProfKGD
48K Followers 197 Following #CS Associate Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, #CVPR2024/#ECCV2024 Publicity Co-chairAutonomous Vision Gro.. @AutoVisionGroup
12K Followers 371 Following Autonomous Vision Group of Andreas Geiger at the University of Tübingen. We are excited about Computer Vision, Machine Learning and Robotics.Andrej Karpathy @karpathy
981K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Dmytro Mishkin 🇺�.. @ducha_aiki
18K Followers 593 Following Marrying classical CV and Deep Learning. I do things, which work, rather than being novel, but not working.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.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)Kostas Daniilidis @KostasPenn
4K Followers 1K Following Ruth Yalom Stone Professor @Penn @PennEngineers @PennCIS @GRASPlabAntoni Rosinol @RosinolToni
2K Followers 735 Following Co-Founder @StackAI_HQ (YC W23) | PhD @MIT | LLMs & Computer Vision | https://t.co/5irrHUYiJmJeannette Bohg @leto__jean
7K Followers 490 Following Assistant Professor @StanfordAILab @StanfordIPRL. Perception, learning and control for autonomous robotic manipulation #BlackLivesMatter she/her 🌈Yann LeCun @ylecun
713K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Peyman Milanfar @docmilanfar
67K Followers 264 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.Mark Riedl @mark_riedl
32K Followers 1K Following AI for storytelling, games, explainability, safety, ethics. Professor @GeorgiaTech. Associate Director @MLatGT. Time travel expert. Geek. Dad. he/himSong Han @songhan_mit
6K Followers 145 Following Assoc. Prof. @MIT, Distinguished Scientist @NVIDIA, cofounder of DeePhi (now part of AMD) and OmniML (now part of NVIDIA). PhD @Stanford. Efficient AI computingRohan Paul @rohanpaul_ai
13K Followers 1K Following ML Engineer (e/acc) 📌 https://t.co/x0IIWfnOt8 🚀 https://t.co/QEO4CKRl1b Open LLMs is Happiness 💡 Ex Deutsche & HSBC. DM for collaboration.Alessandro Favero @alesfav
282 Followers 571 Following Physics/ML PhD candidate @EPFL working on the foundations of deep learning. Former applied scientist intern @AWSCloud AI Labs.Lina Colucci, PhD @lina_colucci
6K Followers 1K Following Co-Founder @toinfinityai (YC W24). Try it here: https://t.co/U3BKdJLVqN. 2x Founder. Alum: @MIT @Harvard @DukeU 🇧🇷→🇨🇦→🇺🇸Alexandr Wang @alexandr_wang
143K Followers 703 Following ceo at @scale_ai. rational in the fullness of timefloating point @yar_vol
590 Followers 1K FollowingDenis A. @den_run_ai
603 Followers 971 Following AI Scientist @ServiceNow | LLM Code Gen | Marathon Runner | Founder @aikynetixAnjney Midha @AnjneyMidha
7K Followers 2K Following general partner @a16z • board @MistralAI @LumaAI • past: ceo/founder @ubiquity6 (acquired by @discord), bioinformatics @StanfordMedSara Hooker @sarahookr
39K Followers 8K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.Saurabh Dash @TheyCallMeMr_
251 Followers 461 Following ML @CohereAI , PhD Student @GeorgiaTech. Previously, ML Research @Apple, @IITkgp. https://t.co/yZLkUsiZ7P. Learning why my machines don’t learn.Nils Reimers @Nils_Reimers
10K Followers 434 Following Director of Machine Learning @Cohere | ex-huggingface | Creator of SBERT (https://t.co/MKKOMfuQ4C)Ahmad Al-Dahle @Ahmad_Al_Dahle
4K Followers 53 Following #Girldad of twins. Leading GenAI @ Meta (llama, imagine, meta ai and more)Sergey Edunov @edunov
993 Followers 103 Following Director of Engineering @ GenAI, Meta. I work on LlamasAston Zhang @astonzhangAZ
5K Followers 92 Following Research Scientist at the #llama team of Meta Generative AI, designing and training large language models. Opinions are my own.Teknium (e/λ) @Teknium1
29K Followers 3K Following Cofounder @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE Support me on Github SponsorsJeremy Howard @jeremyphoward
222K Followers 5K Following 🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Hon Professor: @UQSchoolITEE ; Digital Fellow: @StanfordBrett Adcock @adcock_brett
172K Followers 14 Following Founder @Figure_robot (AI Robotics) & Archer Aviation (NYSE: ACHR)Trenton Bricken @TrentonBricken
7K Followers 2K Following Trying to figure out what makes minds and machines go "Beep Bop!" @AnthropicAISholto Douglas @_sholtodouglas
15K Followers 861 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meterPhysical Intelligence @physical_int
4K Followers 8 Following Physical Intelligence (Pi), bringing AI into the physical world.Ted Xiao @xiao_ted
11K Followers 682 Following I teach robots to be smarter @GoogleDeepMind. Tweets about robot learning, scaling, and large models. Opinions my own.shubman gill 208(149).. @ItsPrannay
171 Followers 383 Following I like cricket | Always hungry for mum’s keema | Turning lemonade into lemons since 1996 | PhD in Machine Learning | 🇮🇳🇬🇧lmsys.org @lmsysorg
39K Followers 173 Following Large Model Systems Organization. We created Vicuna and Chatbot Arena! Compare 30+ LLMs (GPT-4/Claude/Llamas) side-by-side at https://t.co/IDFeIDIOtmShikun Liu @liu_shikun
992 Followers 738 Following Ph.D. student at the Dyson Robotics Lab at Imperial College.Angel Villar @angelvillar96
391 Followers 2K Following PhD Student @ AIS Uni-Bonn Doing at reaserch at the intersection between deep learning, computer vision and robotics.Suhail @Suhail
295K Followers 464 Following Founder: @playground_ai, @mixpanel Pizzatarian, programmer, music makerJason Weston @jaseweston
9K Followers 569 Following Research @MetaAI+NYU. Pretrain+SFT: NLP from Scratch (2011). Multilayer attention+position encode+LLM: MemNet (2015). Recent (2024): Self-Rewarding LLMs & more!Hemant Mohapatra @MohapatraHemant
47K Followers 119 Following investing @lightspeedindia, past: @a16z prod/engg @Google @AMD; @supabase @pixxelspace @gorattle @sarvamai @solana @pintuID. Poetry, physics & 🎹Linjie (Lindsey) Li @LINJIEFUN
2K Followers 297 Following researching @Microsoft, @UW, contributing to https://t.co/a3zper7NJGHyung Won Chung @hwchung27
18K Followers 231 Following Research Scientist @OpenAI. Past: @Google Brain / PhD @MITDeedy @deedydas
69K Followers 4K Following Investing at @MenloVentures. Formerly founding team @glean, @Google Search. @Cornell CS. Tweets about tech, immigration, India, fitness and search.Nathan Lambert @natolambert
25K Followers 693 Following Figuring out AI @allen_ai, "rl boi" DM me papers. Writes @interconnectsai, talks @retortai Has phd and some credentialsHamid Naderi Yeganeh @naderi_yeganeh
35K Followers 32K Following Research Student @UCL Maths. Mathematical artist. Email: naderiyeganeh at gmail dot comPrasanna S @myprasanna
10K Followers 7K Following Co-Founder @Rippling @0xPPL_; Angel Investor: https://t.co/pjiWi4E1BlYasantha Rajakarunana.. @yasantha62
6K Followers 445 Following Technologist, Scientist, Engineer. Plain living, high thinking..Irina Rish @irinarish
9K Followers 994 Following prof UdeM/Mila; Canada Excellence Research Chair; AAI Lab head https://t.co/UzlrC7ZrGF; INCITE project PI https://t.co/0rV7szd7rH; CSO https://t.co/XDhj6MEtUjVipul Ved Prakash @vipulved
5K Followers 841 Following Building an AI supercomputer out of spare internet parts. Founder, CEO @togethercomputeTim Zaman @tim_zaman
20K Followers 103 Following AI at Google DeepMind. callsign PD4TA. Previously Tesla, X/Twitter (head of AI Infra), NVIDIA.Ali K @alihkw_
277 Followers 1K Following DMs Open! AI & Robotics MSc at @Mila_Quebec/@UMontreal. Prev: nlp at @amazonscience, compsci at @UofT. Slowly figuring out how to make robots learn.Chethan Parameshwara @cmparam
346 Followers 542 Following AI Researcher @AmazonScience | Multimodal AI | PhD @UofMarylandMistral AI @MistralAI
91K Followers 0 Following Fast, open-source and secure language models. Join us https://t.co/INALdNGvCPSasha Rush @srush_nlp
52K Followers 465 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzZekun Jiang @zekun_jiang
252 Followers 626 Following I mainly focus on Trustworthy AI, Medical Imaging, BioMedical AI, and AI for Healthcare. Feel, learn, think, and express. Enjoy your life first.Nikhil Varma Keetha @Nik__V__
870 Followers 918 Following PhD in Robotics @CMU_Robotics @airlabcmu | Making Robots Temporally See the World🤖🌍👀 | Cook👨🍳 Gamer🎮 Movie Buff🎥Long Le @int64_le
46 Followers 185 Following Assistant (ᴛᴏ ᴛʜᴇ) Professor @GRASPLab @Penn. Previously @Google, @CarnegieMellon, @Meta, @UMassAmherstleonidk @leo_nid_k
454 Followers 361 Following Vision, Graphics, Learning & Robotics. berkeley + stanford + cmu (bs + ms + phd). notable: intel realsense & diff. rendering w/ 3d gaussiansShimon Whiteson @shimon8282
15K Followers 405 Following Professor of Computer Science at Oxford. Head of Research at Waymo UK.Jonathan Frankle @jefrankle
16K Followers 684 Following Chief Scientist, Neural Networks @Databricks via MosaicML. PhD @MIT_CSAIL. BS/MS @PrincetonCS. DC area native. Making AI efficient for everyone at @DbrxMosaicAIEnjoyed this paper that plots emergent abilities with pretraining loss on the x-axis, which is actually a suggestion that @OriolVinyalsML also made a few years back: arxiv.org/abs/2403.15796 The paper uses intermediate checkpoints to plot a variety of pretraining losses. For some…
with SegmentAnything+CLIP, we can build rich metric-semantic 3D maps for robotics. but what is the right granularity for objects & places in the map? is a backpack an object? or is the zipper on the backpack an object? youtu.be/m-HJO10qhSQ [1/n]
We release and open source Idefics2-8B, a foundation vision language model with SOTA results for its size on various benchmarks Architecture, data, pre-training, fine-tuning: most important things are in the thread 🧵
I have been working on vision+language models (VLMs) for a decade. And every few years, this community re-discovers the same lesson -- that on difficult tasks, VLMs regress to being nearly blind! Visual content provides minor improvement to a VLM over an LLM, even when these…
Today we’re releasing OpenEQA — the Open-Vocabulary Embodied Question Answering Benchmark. It measures an AI agent’s understanding of physical environments by probing it with open vocabulary questions like “Where did I leave my badge?” More details ➡️ go.fb.me/7vq6hm…
BRAVE Broadening the visual encoding of vision-language models Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress,
Schedule-Free Learning github.com/facebookresear… We have now open sourced the algorithm behind my series of mysterious plots. Each plot was either Schedule-free SGD or Adam, no other tricks!
[75min talk] i finally recorded this lecture I gave two weeks ago because people kept asking me for a video so here it is, enjoy "The Little guide to building Large Language Models in 2024" tried to keep it short and comprehensive – focusing on concepts that are crucial for…
One of the most imaginative LLM papers I've read in a while: use evolution to merge models from HuggingFace to unlock new capabilities, such as Japanese understanding. It's a form of sophisticated model surgery that requires much smaller compute than traditional LLM training. By…
nternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding Presents a new video foundation model that achieves SotA on over 60 tasks, including action recognition, video-text tasks, and video-centric dialogue arxiv.org/abs/2403.15377
In my mid 20's to early 30's I dealt with chronic low back pain. I went to a Chiropractor who told me I'd have to live with the pain & get adjustments for the rest of my life. I said screw that, searched for a solution, and fixed my back. Here's how I did it:
SV3D takes an image as input and outputs camera-controlled novel views that are highly consistent across the views. We also propose techniques to convert these novel views into quality 3D meshes. View synthesis models are publicly released. Project page: sv3d.github.io
Today, we are releasing Stable Video 3D, a generative model based on Stable Video Diffusion. This new model advances the field of 3D technology, delivering greatly improved quality and multi-view. The model is available now for commercial and non-commercial use with a Stability…
Apple presents MM1, a family of multimodal LLMs up to 30B parameters, that are SoTA in pre-training metrics and perform competitively after fine-tuning arxiv.org/abs/2403.09611
Language models scale reliably with over-training and on downstream tasks Explores gaps in LM scaling laws, providing insights into over-training and linking model perplexity to downstream performance repo: github.com/mlfoundations/… abs: arxiv.org/abs/2403.08540
The information bandwidth of the human visual system is *not* 20MB/s just because you have 1 million optic nerve fibers. It's exactly like saying that the information bandwidth of a 1280x720 video is 16MB/s, because you have 1280x720x3 channels with 256 possible values firing at…
01.AI just released the paper on Yi models arxiv.org/abs/2403.04652
Long overdue but here's a new blogpost on training LLMs in the wilderness from the ground up 😄🧐 In this blog post, I discuss: 1. Experiences in procuring compute & variance in different compute providers. Our biggest finding/surprise is that variance is super high and it's…
On India: I have had two decades of discussions with various people on what India needs to do. They fall roughly into two camps A) India has deep issues. Poverty, health, infrastructure. Fix that first. B) India has strengths. A thriving market. Build on those strengths and go…
Ever wondered how your LLM splits numbers into tokens? and how that might affect performance? Check out this cool project I did with @djstrouse: Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs. Read on 🔎⏬
Humanoid Locomotion as Next Token Prediction We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. To account for
great quote from karpathy most great organizations require leader(s) with a disproportionate amount of power when this is absent you end up with countless hierarchies of ineffective committees, e.g. many google products lack a Directly Responsible Individual with actual power