Pablo Delgado

3K posts

Pablo Delgado banner
Pablo Delgado

Pablo Delgado

@pablete

Engineer, Mathematician, Computer Scientist

San Francisco, CA Присоединился Ekim 2007
545 Подписки621 Подписчики
Pablo Delgado ретвитнул
Julien Chaumond
Julien Chaumond@julien_c·
in case you missed it @lancedb and HF are partnering up to unlock the next generation of large dataset storage on the Hub 🔥 And it's fire! - Supports storing embeddings (and their indexes) directly alongside the data - Vector search / similarity search is built-in - Large multimodal datasets (text, images, video) just use the hf:// prefix: db = lancedb. connect("hf://datasets/julien-c/hub-stats-lance") 🔥🔥
Julien Chaumond tweet media
English
0
16
80
8.2K
Ale
Ale@gptcrosa·
Me regalaron esto, algo interesante para imprimir nerds?
Ale tweet media
Español
15
0
16
6.4K
Pablo Delgado ретвитнул
Yoav HaCohen
Yoav HaCohen@yoavhacohen·
Most video models are silent. Most audio models don’t see. LTX-2 learns the joint distribution of sound and vision, generating speech, foley, ambience, motion, and timing together not as a post-hoc pipeline.
Yoav HaCohen tweet media
English
1
1
48
4.7K
Pablo Delgado ретвитнул
DailyPapers
DailyPapers@HuggingPapers·
HiStream Meta AI researchers introduce an efficient autoregressive framework for 1080p video generation. By eliminating spatial, temporal, and timestep redundancy, HiStream achieves state-of-the-art quality with up to 107.5× speedup, making high-resolution video generation practical.
DailyPapers tweet media
English
3
14
129
10.7K
Pablo Delgado ретвитнул
LanceDB
LanceDB@lancedb·
Lei Xu and Pablo Delgado of @netflix took the stage on Wednesday at Ray Summit 2025!
LanceDB tweet mediaLanceDB tweet mediaLanceDB tweet mediaLanceDB tweet media
English
1
1
10
1.7K
Pablo Delgado ретвитнул
LanceDB
LanceDB@lancedb·
We’ll walk through how Ray enables large-scale processing across hundreds of GPUs, while LanceDB’s columnar design provides efficient, intelligent curation and sampling. Together, they’re producing smaller, more diverse, and higher-quality datasets for cutting-edge text-to-image and video-to-text research.
LanceDB tweet media
English
1
1
2
266
Pablo Delgado ретвитнул
LanceDB
LanceDB@lancedb·
Building and curating large-scale multimodal datasets has long been a complex, resource-heavy challenge. But that’s changing fast. Lei Xu of LanceDB and Pablo Delgado of @netflix will be speaking at Ray Summit 2025 — Scaling Multimodal Data Curation with Ray and LanceDB
LanceDB tweet media
English
1
3
9
760
Pablo Delgado ретвитнул
LanceDB
LanceDB@lancedb·
🥳 Welcome another #Lancelot at the Roundtable, Ethan Rosenthal 🎉 On Ethan’s first day at @runwayml , he was tasked with building a multimodal 𝗱𝗮𝘁𝗮 𝘀𝘆𝘀𝘁𝗲𝗺 𝘁𝗵𝗮𝘁 𝘀𝘂𝗽𝗽𝗼𝗿𝘁𝗲𝗱 𝗯𝗼𝘁𝗵 𝗱𝗶𝘀𝘁𝗿𝗶𝗯𝘂𝘁𝗲𝗱 𝗱𝗮𝘁𝗮𝗹𝗼𝗮𝗱𝗶𝗻𝗴 𝗮𝗻𝗱 𝗲𝘅𝗽𝗹𝗼𝗿𝗮𝘁𝗼𝗿𝘆 𝗱𝗮𝘁𝗮 𝗮𝗻𝗮𝗹𝘆𝘀𝗶𝘀. He said, “𝘛𝘩𝘢𝘵’𝘴 𝘢 𝘵𝘦𝘳𝘳𝘪𝘣𝘭𝘦 𝘪𝘥𝘦𝘢. 𝘠𝘰𝘶 𝘴𝘩𝘰𝘶𝘭𝘥 𝘯𝘦𝘷𝘦𝘳 𝘵𝘳𝘺 𝘵𝘰 𝘥𝘰 𝘵𝘩𝘪𝘴 𝘸𝘪𝘵𝘩 𝘰𝘯𝘦 𝘴𝘺𝘴𝘵𝘦𝘮!". He then found #Lance and did exactly what he said not to do. 😆
LanceDB tweet media
English
1
2
7
1.1K
Pablo Delgado ретвитнул
Freepik
Freepik@freepik·
Welcome to Freepik Spaces A single place where ideas live, connected through real-time workflows Our CEO and CPO are presenting the future of Freepik live from Upscale Studios NYC Join the waitlist below
Freepik tweet media
English
40
62
349
2M
Pablo Delgado ретвитнул
Ning Yu (hiring interns)
Ning Yu (hiring interns)@realNingYu·
Video diffusion models struggle beyond training resolution → artifacts & repetition. 🎥CineScale🎥 solves this with a novel inference paradigm: ⚡ Dedicated variants for video architectures ⚡ Extends T2I to T2V & I2V & V2V ⚡ 8K images & 4K video, tuning-free/minimal tuning Expanding the frontier of generative video fidelity. ✊ Kudos to the teamwork led by our intern @qhnmoon at @eyelinestudios. #AI #AIResearch #MachineLearning #AIGC #GenAI #videos #DiffusionModels #HighRes #fidelity #ComputerVision #internship
Ning Yu (hiring interns) tweet media
Eyeline@eyelinestudios

@eyelinestudios and @NTUsg's latest research paper, CineScale, showcases a new method for creating higher-resolution image and video content with novel adaptations for a variety of visual generative model architectures. Unleash the resolution of text-to-video, image-to-video, and video-to-video generative diffusion models with minimal tuning! Watch our 4k video generation demo below. #CineScale Kudos to the team: @qhnmoon, @realNingYu, @ziqi_huang_, @debfx, @liuziwei7 Paper: arxiv.org/pdf/2508.15774 Project: eyeline-labs.github.io/CineScale/ Code: github.com/Eyeline-Labs/C… ***This is part of the ongoing research and development at @eyelinestudios, and we hope to see adoption of these techniques and workflows soon.

English
0
11
47
5.4K
Pablo Delgado ретвитнул
changhiskhan
changhiskhan@changhiskhan·
I’ve been a huge fan of the Netflix engineering blog for a long time. So so excited for @lancedb to be an important part of the multimodal AI transformation in data engineering netflixtechblog.com/from-facts-met…
changhiskhan tweet media
English
3
16
123
13.3K
Ale
Ale@gptcrosa·
Pensé que me iba a pedir plata pero me dijo fíjate que estás arrastrando algo, me fijo y me dice la facha que tenes amigo lo que me hiciste reír
Español
7
0
120
18.7K
Pablo Delgado ретвитнул
ray
ray@raydistributed·
We had an incredible time at Netflix HQ for our latest Ray x AI Infra Meetup! Session highlights included: 🔹@Netflix's approach to scalable AI pipelines with Ray 🔹The latest in Ray Data for large-scale AI data processing 🔹A featured update from the LanceDB team on their newest developments Huge thanks to everyone who joined us!
ray tweet mediaray tweet mediaray tweet mediaray tweet media
English
2
3
14
753
Pablo Delgado ретвитнул
ray
ray@raydistributed·
Incredible meetup last night. Thank you to @netflix for hosting! Great talks from - Lingyi Liu on Netflix's ML platform - Pablo Delgado on multimodal data curation at Netflix - Lei Xu on LanceDB's multimodal lakehouse - Richard Liaw on Ray Data for AI data processing
ray tweet mediaray tweet media
English
0
6
22
4.4K
Pablo Delgado ретвитнул
ray
ray@raydistributed·
Multimodal AI is moving fast – and scaling it takes serious infrastructure. Join us June 25 at @netflix HQ to hear how teams at Netflix are using Ray in production for distributed AI workloads, from multimodal data curation to GenAI at scale. You'll also hear what's new in Ray Data and from the @lancedb team RSVP: lu.ma/qx5b418t
ray tweet media
English
1
4
11
943

Открыть

@lancedb @changhiskhan @gptcrosa @netflix @Noahpinion @runwayml @VLDBconf @qhnmoon