1/ World model research is fragmented: every paper reimplements its own data pipeline, baselines, and eval harness. Comparing two methods fairly is weeks of infra work.
๐๐๐ฎ๐ฏ๐น๐ฒ-๐๐ผ๐ฟ๐น๐ฑ๐บ๐ผ๐ฑ๐ฒ๐น is a new open-source platform that standardizes the whole thing: https://t.co/Gg3V3LhKJr
in case you missed it @lancedb and HF are partnering up to unlock the next generation of large dataset storage on the Hub ๐ฅ
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")
๐ฅ๐ฅ
Most video models are silent.
Most audio models donโt 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.
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 107.5ร speedup, making high-resolution video generation practical.
Weโll walk through how Ray enables large-scale processing across hundreds of GPUs, while LanceDBโs columnar design provides efficient, intelligent curation and sampling. Together, theyโre producing smaller, more diverse, and higher-quality datasets for cutting-edge text-to-image and video-to-text research.
Building and curating large-scale multimodal datasets has long been a complex, resource-heavy challenge. But thatโs changing fast. Lei Xu of LanceDB and Pablo Delgado of @netflix will be speaking at Ray Summit 2025 โ Scaling Multimodal Data Curation with Ray and LanceDB
Now this is a @lancedb feature to make @Noahpinion proud. Introducing RabitQ: better compression, better recall, faster index build, higher throughput.
https://t.co/46vSI8eq7n
๐ฅณ Welcome another #Lancelot at the Roundtable, Ethan Rosenthal ๐
On Ethanโs first day at @runwayml , he was tasked with building a multimodal ๐ฑ๐ฎ๐๐ฎ ๐๐๐๐๐ฒ๐บ ๐๐ต๐ฎ๐ ๐๐๐ฝ๐ฝ๐ผ๐ฟ๐๐ฒ๐ฑ ๐ฏ๐ผ๐๐ต ๐ฑ๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ฒ๐ฑ ๐ฑ๐ฎ๐๐ฎ๐น๐ผ๐ฎ๐ฑ๐ถ๐ป๐ด ๐ฎ๐ป๐ฑ ๐ฒ๐ ๐ฝ๐น๐ผ๐ฟ๐ฎ๐๐ผ๐ฟ๐ ๐ฑ๐ฎ๐๐ฎ ๐ฎ๐ป๐ฎ๐น๐๐๐ถ๐. He said, โ๐๐ฉ๐ข๐ตโ๐ด ๐ข ๐ต๐ฆ๐ณ๐ณ๐ช๐ฃ๐ญ๐ฆ ๐ช๐ฅ๐ฆ๐ข. ๐ ๐ฐ๐ถ ๐ด๐ฉ๐ฐ๐ถ๐ญ๐ฅ ๐ฏ๐ฆ๐ท๐ฆ๐ณ ๐ต๐ณ๐บ ๐ต๐ฐ ๐ฅ๐ฐ ๐ต๐ฉ๐ช๐ด ๐ธ๐ช๐ต๐ฉ ๐ฐ๐ฏ๐ฆ ๐ด๐บ๐ด๐ต๐ฆ๐ฎ!". He then found #Lance and did exactly what he said not to do. ๐
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
Video diffusion models struggle beyond training resolution โ artifacts & repetition.
๐ฅCineScale๐ฅ solves this with a novel inference paradigm:
โก Dedicated variants for video architectures
โก Extends T2I to T2V & I2V & V2V
โก 8K images & 4K video, tuning-free/minimal tuning
Expanding the frontier of generative video fidelity.
โ Kudos to the teamwork led by our intern
@qhnmoon at @eyelinestudios.
#AI #AIResearch #MachineLearning #AIGC #GenAI #videos #DiffusionModels #HighRes #fidelity #ComputerVision #internship
Iโve 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
https://t.co/AMmBOMISFR