Mehmet Saygın Seyfioğlu @mehsaygin
Ph.D. candidate at @UW, working on medical AI at the intersection of vision and language. Previously 4x Research Intern @AmazonScience. mehmetsayginseyfioglu.github.io Seattle, WA Joined May 2013-
Tweets1K
-
Followers799
-
Following754
-
Likes10K
Excited to share that Quilt-LLaVA has been accepted at @CVPR! As promised, we are making our model, datasets, and training scripts available to the community: quilt-llava.github.io See you all in Seattle! @wizdom_dominic @fghezloo @RanjayKrishna @lindashapiro
Excited to share that Quilt-LLaVA has been accepted at @CVPR! As promised, we are making our model, datasets, and training scripts available to the community: quilt-llava.github.io See you all in Seattle! @wizdom_dominic @fghezloo @RanjayKrishna @lindashapiro
Thank you @_akhaliq for sharing our work! Check out Diffuse2Choose, a virtual try-all model that allows users to try on any e-commerce item in any setting! Arxiv: arxiv.org/abs/2401.13795 Website: diffuse2choose.github.io Thread: x.com/mehsaygin/stat… Stay tuned for more!
Thank you @_akhaliq for sharing our work! Check out Diffuse2Choose, a virtual try-all model that allows users to try on any e-commerce item in any setting! Arxiv: arxiv.org/abs/2401.13795 Website: diffuse2choose.github.io Thread: x.com/mehsaygin/stat… Stay tuned for more!
Thank you @Scobleizer, for covering our work! Check out Diffuse2Choose, a virtual try-all model that allows users to try on any e-commerce item in any setting! 📜: arxiv.org/abs/2401.13795 🌎: diffuse2choose.github.io Thread: x.com/mehsaygin/stat… Stay tuned for more!
Thank you @Scobleizer, for covering our work! Check out Diffuse2Choose, a virtual try-all model that allows users to try on any e-commerce item in any setting! 📜: arxiv.org/abs/2401.13795 🌎: diffuse2choose.github.io Thread: x.com/mehsaygin/stat… Stay tuned for more!
Thank you @thibaudz, for covering our work! Please see the following thread for more information! x.com/mehsaygin/stat…
Thank you @thibaudz, for covering our work! Please see the following thread for more information! x.com/mehsaygin/stat…
Becky Taira @bec_tai
74 Followers 5K FollowingClarinda Gumz @clarin_gu
44 Followers 5K FollowingVenusMalory @x264Jx7pz0X55
1 Followers 155 FollowingSytare @Sytare175439
3 Followers 275 FollowingSharyn Mcdonnel @SMcdonnel38259
70 Followers 5K FollowingLola-rose Asplin @AsplinLola31687
94 Followers 5K FollowingBernicePaul @3rOAk288CKOby9w
2 Followers 217 FollowingCoraline Tinklenberg @CoralineTi30843
73 Followers 5K FollowingKiersten Willingham @WillingKierst
65 Followers 5K FollowingBreagha Dautrich @DautricBrea
46 Followers 5K FollowingLove Devoy @devoy32821
32 Followers 5K Followingqi78qoz3j8lmh88r @7cvxdm5qnfh
6 Followers 270 Following 【coinsrw . com 】User**me:Rom88 , P*****rd:R 66888 Bal:4,289,287,11 U.S.D.TMikki Clower @ClowMikk
69 Followers 5K Followingad sil @Adrwitter_
1 Followers 130 FollowingLorri Catalli @cata_lorr
36 Followers 5K FollowingAlannah Gattison @AlannahGat13284
23 Followers 5K FollowingAria Conorich @a_conori
32 Followers 5K FollowingDodie Topete @DodieTopet48347
27 Followers 5K FollowingAaron Walsman @aaronwalsman
212 Followers 276 FollowingMelodie Sogge @MSogge23023
70 Followers 5K FollowingMenaal Fenstermaker @MenaalFens11555
72 Followers 5K FollowingApoorva Sheera @apoorva_sheera
28 Followers 101 Following Masters Data Science @UW, ex-McKinsey consultant, @IITKanpurSonya Lepez @lepez_lep
72 Followers 5K FollowingTabitha Crispino @TabithCrisp
33 Followers 5K FollowingAmee Schmierer @am_schmiere
53 Followers 5K FollowingAshlyn Mackey @AshlynMack93734
75 Followers 5K FollowingHarriette Fagley @HFagley63527
65 Followers 5K FollowingLeola Defrancisco @DefrancisLeo
85 Followers 5K FollowingAinsley Howell @AinsleHowel
68 Followers 5K FollowingTonia Tierce @TierceToni80387
61 Followers 5K FollowingAspen Tu @aspen_tu23492
65 Followers 5K FollowingIvelisse Feilbach @IvelisseFe80323
77 Followers 5K FollowingLeola Polivick @LeolaPoliv6313
76 Followers 5K FollowingTeagan Baucom @bauc_teag
22 Followers 5K FollowingAkmal Dogar @akmalmasud96
51 Followers 177 Following Experienced in AI model development, pipeline preparation, model optimization and large-scale deployment.Huang Qichag @HQichag48397
403 Followers 4K FollowingRonin Graphics @GraphicsRonin
2K Followers 2K Following Transforming your visions into stunning reality through the power of design and AI, Ignite your brand with our exceptional 2D and logo design, and 3D Modeling.Roy @RoyZiqi
1 Followers 27 FollowingAcbm @PascalsAcbm
0 Followers 183 FollowingAmalia Grussendorf @AmaliaGrus84558
39 Followers 5K FollowingNell Rebello @ne_rebell
12 Followers 3K FollowingAlan Karthikesalingam @alan_karthi
5K Followers 2K Following Health AI @GoogleHealth @GoogleAI @GoogleDeepMind: ✨Med-Gemini✨, AMIE, MedPaLM, MedPaLM-2, MedPaLM-M + CoDoC. Hon Lecturer Vasc Surgery @ImperialVascJascha Sohl-Dickstein @jaschasd
19K Followers 626 Following Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.Thomas Steinke @shortstein
9K Followers 457 Following Computer scientist interested in (differential) privacy & related topics, e.g., generalization. @GoogleDeepMind Opinions are mine ©. 🇳🇿Gautam Kamath @thegautamkamath
44K Followers 508 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.Sholto Douglas @_sholtodouglas
15K Followers 859 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meterJames Bradbury @jekbradbury
11K Followers 8K Following Compute at @AnthropicAI! Previously JAX, TPUs, and LLMs at Google, MetaMind/@SFResearch, @Stanford Linguistics, @Caixin.Apoorva Sheera @apoorva_sheera
28 Followers 101 Following Masters Data Science @UW, ex-McKinsey consultant, @IITKanpurDevi 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.Jülyana Asanj 🇹�.. @julyinasanj
15K Followers 91 Following Physicist | Software Developer | Philosopher | Aeronautics, Electronics & Space Enthusiast | Defence Industry Worker | PPL PilotJack Rae @drjwrae
9K Followers 356 Following Principal Scientist @ Google DeepMind Work on Gemini 💎♊ Compression is all you need LLMs (e.g. Gopher, Chinchilla, Gemini) 💼 Past: OpenAI, QuoraLysonOber @lyson_ober
4K Followers 639 Following 📺 Midjourney & 3D & Productivity / 🪄 MJ, 3D, UI, Framer, Dify etc / 🎨 Create Sth Interesting with AI / ✨ Unlocking the Potential of Productivity Toolslabml.ai @labmlai
12K Followers 8 Following 📝 Annotated paper implementations https://t.co/qeO4UTbrJ3Srikar Yellapragada @ymsrikar
68 Followers 138 Following PhD student @SBUcompsc | Previously @Bloomberg, @nyuniversity, @IITHyderabadAGI.Eth @ceobillionaire
155K Followers 4K Following Vincent Boucher, President of @Montreal_AI #MontrealAI | B. Sc. Physics, M. A. Govt. Policy Analysis and M. Sc. Aerospace Engineering | $AGI by AGI.Eth #AGIAlperen Keleş @Keleesssss
6K Followers 1K Following METU CENG 21' | PhD Student at @umdcs | Writing at https://t.co/JYlXbdcnTq | Contact: [email protected]Tuna Meral @tunahansalih
340 Followers 320 Following CV & GenAI | PhD in @VT_CS @virginia_tech MSc & BSc @Bogazici_CmpE @UniBogazici Prev. ML Engineer @LyrebirdStudio & @visperaco 🇹🇷/🇺🇸Barışcan KURTKAYA @bariskurtkaya
398 Followers 562 Following KUIS AI Fellow @kocuniversity / Interested in Computer Vision (Generative Models and 3D)Hıdır Yeşiltepe @d_yesiltepe
197 Followers 713 Following CS PhD Student at Virginia Tech | METU CENG'23Pinar Yanardag @PINguAR
4K Followers 709 Following Assistant Prof. #VirginiaTech CS. Formerly #MIT #Purdue #Bogazici. #Emmy Nominated Creative Director, #Fulbright Fellow. Contact: [email protected].Rong Ching Chang @AnnCC12
694 Followers 5K Following Fascinated by ML, LLMs, GNN, Multimodal models in social media. Ph.D. student @ucdavisAmita Kamath @kamath_amita
371 Followers 169 Following PhD student at @UCLANLP | Previously, Predoctoral Young Investigator at @Allen_AI and Stanford CS MS student @StanfordNLPBesmira Nushi 💙�.. @besanushi
2K Followers 739 Following Researcher @MSFTResearch artificial intelligence, human-machine collaboration, technology & society.Tal Hassner @THassner
530 Followers 115 Following Doing my best in Computer vision, machine learning, and deep learning. Still failing at stoicism.Stability AI @StabilityAI
190K Followers 31 Following We are building the foundation to activate humanity's potential.Oindrila Saha @oindy_saha
177 Followers 220 Following CS PhD student @UMassAmherst previously @RealityLabs @MSFTResearch @AdobeResearch @IITKgpMaria Zontak @MariaZontak
31 Followers 79 FollowingOreva Ahia @orevaahia
1K Followers 971 Following PhD student @uwcse | ex: AI/ML Research Intern @apple | Co-organizer @AISaturdayLagos | Researcher @MasakhaneNLPstephen balaban @stephenbalaban
9K Followers 1K Following Co-founder, CEO - Lambda. We’re hiring: https://t.co/n0yFaq0ZDnGül Varol @gulvarol
3K Followers 403 Following Research faculty @ImagineENPC. Also affiliated with @Oxford_VGG and @PerceivingSys. PhD from @inria_paris.Neel Das @Nilzkool
6K Followers 5K Following Gen AI expert in healthcare | Building https://t.co/Erkxvoh2hm to help tutors conduct CS & coding quizzes effortlessly | Opinions are mineira kemelmacher @kemelmi
3K Followers 33 FollowingPalmer Luckey @PalmerLuckey
219K Followers 2K Following I am a technology enthusiast, writer, and modder. Founder of ModRetro, @Oculus VR, and @Anduriltech. Keeping American superheroes safe with autonomous systems.Shambhu Yadav, PhD @Yadav5_
4K Followers 218 Following Postdoctoral Research Scientist, Harvard Medical School @harvardmed and @BrighamWomens| Science Editor | Science Educator & Communicator | @IISERMohali alumnus.Jaehong Yoon @jaeh0ng_yoon
537 Followers 678 Following Postdoc @unccs & @uncnlp, working w/ @mohitban47 | PhD @MLAI_KAIST | Interned @MSFTResearch | Video & Multimodal LLM, Efficiency, Compositionality, FaithfulnessTom Goldstein @tomgoldsteincs
23K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.Joshua Elkington @elkingtonxy
25K Followers 6K Following Founder and General Partner at Axial @axialxyzAshwin Lalendran @ashwinl
2K Followers 2K Following Positive sum Globalist | Engineered bomb detecting drones @AFResearchLab and mapped our world @Apple | AI's biggest impact will be on the physical world |⚡️Colin @colinfortuner
3K Followers 791 FollowingKevin Bishop @Kevin_W_Bishop
223 Followers 121 Following PhD student @UW working on microscopy & biomedical optics | Science communication with @EngageScience | @OregonState ECE alum | he/himYuxuan Sun @jamesja69137043
77 Followers 175 Following Currently working on pathology #LMM and #Medical image analysis.Bojan Tunguz @tunguz
187K Followers 8K Following Machine Learning ex Nvidia. Kaggle Quadruple Grandmaster. Data Scientist. Physicist. Catholic. Husband. Father. Stanford Alum. e/xgb. XGBoost.eth. AMDG.Gul Tahaoglu @thglu_gl
342 Followers 288 Following Postdoctoral researcher on multimedia forensics, Computer Engineer, Assist. Prof. Dr.Sabri Eyuboglu @EyubogluSabri
616 Followers 263 Following Computer Science PhD student @Stanford working with @HazyResearch and @james_y_zou 🪬Wei Qiu @weiqiu55
184 Followers 280 Following PhD student at @uwcse @suinleelab working on Machine learning for healthcare.Soham Gadgil @soham_gadgil
43 Followers 244 Following Ph.D. student @uwcse, previously @Microsoft @Stanford. Working on explainable AI for healthcare.Josh Ye @ByJoshYe
9K Followers 5K Following Tech correspondent @Reuters. 路透社中國科技組. Ex @SCMP. Gamer. University of Pittsburgh/HKU alum. joshye.eth. Views my own.Zijie Huang@Neurips20.. @HuangZi71008374
482 Followers 419 Following CS PhD @UCLA; Research Intern @Amazon @Netflix; Work on #AI4Science, #GNN, #KnowledgeGraph, #DynamicalSystem, #NeuralODE. I am on job market for year 2023-2024.Inexpensive token generation and agentic workflows for large language models (LLMs) open up intriguing new possibilities for training LLMs on synthetic data. Pretraining an LLM on its own directly generated responses to prompts doesn't help. But if an agentic workflow implemented…
A thread on the artwork by Japanese artist Hisao Kawada
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. .
Delighted to share ✨Med-Gemini✨ - our new family of multimodal models for medicine unlocking new possibilities for health - arxiv.org/pdf/2404.18416 More accurate multimodal conversations about medical images🩻, surgical videos📽️, genomics🧬, ultra-long health records📚, ECGs🫀…
Daniel Dennett’s death has made me reflect on the work I’m doing. For a few years, with the increased pace of things, I’ve felt it’s impossible for me to take the time to think clearly enough to make a point that will last more than two years. This seems like a bad thing.
A side note: We started this project about three years ago. I am really proud of how it has evolved over the years, and excited to share this with everyone!
1. 🧵🎉 Excited to share that our paper "Sequential Compositional Generalization in Multimodal Models" is accepted as a long paper at #NAACL2024! 🌟 We'll be presenting our findings in Mexico City this June (@naaclmeeting). Dive into the full details here 👇 - Paper:…
1. 🧵🎉 Excited to share that our paper "Sequential Compositional Generalization in Multimodal Models" is accepted as a long paper at #NAACL2024! 🌟 We'll be presenting our findings in Mexico City this June (@naaclmeeting). Dive into the full details here 👇 - Paper:…
Good work in mitigating the memorization risks of Diffusion models. It worth to examine the mitigation under stronger attacks. Our recent work, Shake to Leak (S2L, arxiv.org/abs/2403.09450), provides a simple yet effective way to red-team the privacy of Diffusion models: Can your…
Consistent Diffusion Meets Tweedie. Our latest paper introduces an exact framework to train/finetune diffusion models like Stable Diffusion XL solely with noisy data. A year's worth of work breakthrough in reducing memorization and its implications on copyright 🧵
This is the kind of things that gets both roboticist and everyone else excited about robotics and AI!
Boston Dynamics reveals its new, improved all-electric Atlas robot, and @bheater has all the details right here: tcrn.ch/3vKUeeN
Our computer vision textbook is released! Foundations of Computer Vision with Antonio Torralba and Bill Freeman mitpress.mit.edu/9780262048972/… It’s been in the works for >10 years. Covers everything from linear filters and camera optics to diffusion models and radiance fields. 1/4
I've spent the past ~2 weeks trying to make a chip from scratch with no prior experience. It's been an incredible source of learning so far. Progress tracker in thread (coolest stuff at the end)👇
Our latest study measures how persuasive language models like Claude are compared to humans. We find a general scaling trend: newer models tend to be more persuasive, with Claude 3 Opus generating arguments that don't differ statistically from human-written ones.
New Anthropic research: Measuring Model Persuasiveness We developed a way to test how persuasive language models (LMs) are, and analyzed how persuasiveness scales across different versions of Claude. Read our blog post here: anthropic.com/news/measuring…
🔥New Video🔥 Flow matching (not classic diffusion) is the basis for state-of-the-art text to image models, like Stable Diffusion 3. Here is how it works: youtu.be/7NNxK3CqaDk
Three is a magic number: Professor Su-In Lee earns trio of honors, including the “Korean Nobel Prize” in engineering, for advancing AI for biomedicine news.cs.washington.edu/2024/04/03/thr…
Update on 🔮Readout Guidance (readout-guidance.github.io)! We open sourced the code – check out our demos, model weights, and training code: github.com/google-researc…. Here’s a teaser of what you can do with our method:
Proof that you don't need Olympiad golds for building towards a better Devin if you have open source. (although at Princeton, Olympiad medalists are so commonplace that even if they exist, they don't bother to mention them) github.com/princeton-nlp/…
Updated list of diffusion model tutorial sources, from my lecture on diffusion.
I wrote a tutorial on diffusion models for undergrad and grad students. I tried my best to give intuitive explanations for complicated equations. Your feedback is much appreciated Thanks to those who suggested various reading materials to me arxiv.org/abs/2403.18103
we read "Learning by Reconstruction Produces Uninformative Features For Perception" in our reading group today. does anyone have any idea how to interpret this figure? how is this a loss curve? do we read it from right to left? paper: arxiv.org/abs/2402.11337
Check out our new work, "Health Equity LLM Toolbox", where we introduce a rigorous human evaluation framework for LLMs in healthcare, alongside the largest human evaluation to date. arxiv.org/abs/2403.12025
Jensen Huang effectively confirms GPT4 is 1.8 trillion parameters lol