Engineer, Mathematician, Computer Scientist
San Francisco, CA
Joined October 2007
- Tweets3K
- Following585
- Followers628
- Likes18.5K
Pablo Delgado retweeted
Today's AI models are a technical marvel. With enough expertise, you can steer them almost anywhere. But by default they have to serve many masters, and easy prompts give you bland results.
Magnific is not build for "anyone." We serve creatives, and the default mode on these models is not what our users want.
Months ago we started a project with these goals:
1) built on top of existing models. Leverage the existing AI models as the building block. Get better when models get better.
2) make the default generation by and for creatives. Easy to get great results.
3) trivial to stay on brand.
A new model from scratch will be something that will become obsolete in weeks / months. Our approach enhances them for our users, making a useful contribution that is long-lasting and differentiated.
After many false starts, we landed on a pre, post-processing, and routing layer on top of a few of today's state of the art models.
We tested the model first with our employees, and later with external users, on two tests: best image for a given prompt, and best image overall (blinding the prompt). The first checks prompt adherence, the last checks image aesthetics.
Magnific One came out first on both tests by a wide margin.
You can use it exclusively on @magnific, test it yourself and tells us what you think.
Pablo Delgado retweeted
Introducing Kardashev-0.7, the world’s first trained swarm made of 32 distinct models
Trained with RL for Population Scaling (RLPS), 32 models organically develop specialization & complementary capabilities, delivering frontier performance at:
- 0.007x ~ 0.02x of the inference cost
- 0.03x of the required memory
Civilization advances through different minds specializing and working together. We’re bringing that principle into AI
@BanburyRoadAI, we’re scaling intelligence by model count, toward civilizations of models that learn to build on one another
Pablo Delgado retweeted
@MicrosoftAI’s Suqiang (Jack) Song is speaking at #Reverie2026.
Hear how MAI is building the frontier AI data flywheel, from curation and deduplication to search and training, with different workloads running on the same underlying data.
Apply to attend → na2.hubs.ly/H084LFl0
Pablo Delgado retweeted
See you at Neurips! Let’s talk world models!
stable-worldmodel got into neurips 2026!
it's basically everything we keep rebuilding for world model research (data loading, baselines, planning, evals) in one place so nobody has to do it again
arxiv.org/abs/2605.21800
Pablo Delgado retweeted
🚀 Sol-Attn is here!
We present a training-free sparse attention method that accelerates video generation while better preserving quality.
Sol-Attn unifies dynamic routing, sparse computation, and approximate correction in a single online-softmax pass:
• On-the-fly block thresholding for dynamic yet controllable budgets
• Proxy-score reuse to approximate unselected blocks
Results (vs dense FlashAttention-3):
• Wan 2.1-14B: 2.02× end-to-end
• HunyuanVideo-13B: 2.12× end-to-end
• LTX 2.3: up to 2.4× end-to-end
When integrated into Sol-Engine (with kernel fusion + caching):
• Wan 2.1-14B: 3.48× end-to-end
• HunyuanVideo-13B: 5.08× end-to-end
Already available in Sol-Engine.
The B200 kernel is still under further optimization.
🎬 Project: nvlabs.github.io/Sana/Sol-At…
📄 Paper: arxiv.org/abs/2607.24027
🔗 Code: github.com/NVlabs/Sana/tree/…
Pablo Delgado retweeted
Very cool to see @netflix releasing video datasets and models on @huggingface. They have a strong video AI team and would be amazing to see them open-source more!
huggingface.co/netflix
Pablo Delgado retweeted
Data processing has become a GPU workload and is dominated by inference. A new architecture is required, and it is not Spark on GPUs. anyscale.com/blog/data-proce…
Pablo Delgado retweeted
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.
𝘀𝘁𝗮𝗯𝗹𝗲-𝘄𝗼𝗿𝗹𝗱𝗺𝗼𝗱𝗲𝗹 is a new open-source platform that standardizes the whole thing: arxiv.org/abs/2605.21800
Pablo Delgado retweeted
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")
🔥🔥
Pablo Delgado retweeted
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.
Pablo Delgado retweeted
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.
Pablo Delgado retweeted
Our session is on Day 2, Nov 5 at 4pm. Check out the agenda here: anyscale.com/ray-summit/2025…
Pablo Delgado retweeted
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.
Pablo Delgado retweeted
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
Pablo Delgado retweeted
Now this is a @lancedb feature to make @Noahpinion proud. Introducing RabitQ: better compression, better recall, faster index build, higher throughput.
lancedb.com/blog/feature-rab…
Pablo Delgado retweeted
🥳 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. 😆
Pablo Delgado retweeted
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
@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/CineS…
Code: github.com/Eyeline-Labs/Cine…
***This is part of the ongoing research and development at @eyelinestudios, and we hope to see adoption of these techniques and workflows soon.