Research Scientist @Netflix | D.Phil. in Computer Science @UniofOxford
Joined October 2020
- Tweets55
- Following260
- Followers190
- Likes267
Ta-Ying Cheng retweeted
Netflix just released VOID on Hugging Face
A video inpainting model that removes objects and their physical interactions
Not just shadows, but things like objects falling when a person is removed
Ta-Ying Cheng retweeted
Netflix dropped some useful stuff. VOID -video object and interaction deletion.
- removes objects while realistically simulating physical consequences;
- beats Runway/ProPainter;
- CogVideoX-5B + SAM 2;
looks good, no smudges/artifacts
void-model.github.io/
Ta-Ying Cheng retweeted
VOID
Video Object and Interaction Deletion
paper: huggingface.co/papers/2604.0…
model: huggingface.co/netflix/void-…
app: huggingface.co/spaces/sam-mo…
🎞️✨ Have you ever imagined what happens if an object is NOT there?
Check out VOID, work led by our amazing intern @sammtmd to see how video diffusion models rewrite scenes after objects are removed!
🎥🪄 What should happen when you remove an object from a video?
Example 1:
A domino chain is falling → remove the middle blocks → the last block should remain standing
Example 2:
Two cars are about to crash → remove one car → the other should drive away 🚙
Current video object removal models fail at these dynamic scenarios.
We introduce VOID: a model that removes objects and updates the scene as if they were never there.
🏆 Preferred 64.8% of the time vs Runway Aleph, Gen-Omnimatte, ProPainter, and more.
🌐 Project page: void-model.github.io
💻 GitHub: github.com/Netflix/void-mode…
🤗 Demo: huggingface.co/spaces/sam-mo…
📄 arXiv: arxiv.org/abs/2604.02296
w/ @willarvey @ZhuoningYuan @ChengTim0708 and collaborators at @NetflixResearch and @INSAITinstitute
Ta-Ying Cheng retweeted
Slides from my talk on "Language as a Visual Format" at the Visual Generative Modeling workshop at CVPR (mostly derived from slides made by @hyojinbahng and @carolinemchan): dropbox.com/scl/fi/5ok46ted0…
Thanks @_akhaliq ‼️
Be sure to checkout our Hugging Face Demo 🤗:
huggingface.co/spaces/stabil…
Check out more about MARBLE 👇
🌐 Project Page: marblecontrol.github.io/
📝 Paper: arxiv.org/abs/2506.05313
🧑💻 Code: github.com/Stability-AI/marb…
🤗 HF demo: huggingface.co/spaces/stabil…
Dial roughness down, crank metallic up, stack multiple attributes at once all in a single forward pass!
Need parametric control sliders? A tiny 2-layer MLP trained on synthetic objects can learn CLIP directions for different material properties for real-world images 🖼️
By traversing through CLIP embeddings of two material exemplars, we notice the effect of a smooth blending in the generated image 🖌️
Inspired by InstantStyle, we begin by injecting CLIP embeddings only into the Denoising UNet’s “material block”, which keeps geometry much more intact compared to previous methods.
Imagine a Van Gogh-style teapot turning into glass with one simple slider🎨
Introducing MARBLE, material edits by simply changing CLIP embedding!
🔗 marblecontrol.github.io/
👏 Internship project with @prafull7, @markb_boss , @jampani_varun at @StabilityAI
Ta-Ying Cheng retweeted
🚀 Glad to see our All-Angles Bench (github.com/Chenyu-Wang567/Al…) being adopted to evaluate 3D spatial understanding in Seed-1.5-VL-thinking along with OpenAI (o1) and Gemini 2.5 Pro..!
Introducing Seed-1.5-VL-thinking, the model achieves SOTA on 38 out of 60 VLM benchmarks🥳🥳🥳
github.com/ByteDance-Seed/Se…
Ta-Ying Cheng retweeted
It seems there is still a long way to go for multi-modal large models to truly understand space and scene.
❗️❗️ Can MLLMs understand scenes from multiple camera viewpoints — like humans?
🧭 We introduce All-Angles Bench — 2,100+ QA pairs on multi-view scenes.
📊 We evaluate 27 top MLLMs, including Gemini-2.0-Flash, Claude-3.7-Sonnet, and GPT-4o.
🌐 Project: danielchyeh.github.io/All-An…
Ta-Ying Cheng retweeted
❗️❗️ Can MLLMs understand scenes from multiple camera viewpoints — like humans?
🧭 We introduce All-Angles Bench — 2,100+ QA pairs on multi-view scenes.
📊 We evaluate 27 top MLLMs, including Gemini-2.0-Flash, Claude-3.7-Sonnet, and GPT-4o.
🌐 Project: danielchyeh.github.io/All-An…