Feiyang (Vance) Chen

Founding Research Engineer @Creatify_AI
Past: @Apple, @SFResearch, @CoupangInc, @SenseTime_AI
Interested in Generative AI/LLMs/Multimodal

[Creatify AI @Creatify_AI]

Creatify Agent, Wave 2. You watched it make the ad. Now watch it run the whole campaign. It learns your brand. Directs a cinematic spot — no slop. Connects to Meta, TikTok, and Google, and launches on the date you pick. The agent didn't get an update. It got promoted. Drop your product below.

[Ledell Wu @LedellWu]

Excited to share Creatify Agent: our step toward AI-native ad orchestration.

Creatify Agent is a multi-agent system for ad video and image production. A central producer orchestrates six stages — brief understanding, web research, parallel scene generation, scored audio, layered assembly, and per-scene QA — with a vision-capable critic feeding verdicts back into the loop.

Alongside the system, we're releasing VideoAdAgent Bench — the first public benchmark for AI ad-video production. Creatify Agent ranks first on the composite, hallucination, and pairwise-preference metrics that govern whether a finished ad is shippable, outperforming general-purpose video agents and frontier T2V models.

The design choices we think matter:

→ Reference-anchored generation. The producer can pull 8–10 high-performing ads from TikTok / Instagram in the brand's category before any scene is rendered. URLs and competitor reels enter the same typed asset graph as uploaded assets.

→ Persistent per-brand memory across sessions. Every T2V model and general-purpose video agent we benchmarked starts from zero on every call.

→ In-the-loop hallucination control. The critic runs inside production, not as a post-hoc filter. Each scene is judged against an explicit rubric (product fidelity, object hallucination, text quality, physical violations, anatomy), and failures route back with a structured verdict — which dimension, by how much, on which frame — for surgical per-scene regen.

Try it for free: https://t.co/GtXEm8fGG3
Full tech report: https://t.co/8YFW3srbD8
VideoAdAgentBench: https://t.co/J7aK6Hlgl4

[Creatify AI @Creatify_AI]

Introducing Creatify Agent.

The world’s first multi-agent orchestrator that makes viral ads without AI slop.

Drop an ad idea below, and we’ll build it for you.

[Ledell Wu @LedellWu]

Super Excited to introduce Aurora (Audio-driven Ultra-Realistic Rendering of Reactive Avatars) – our latest technical breakthrough: a new state-of-the-art AI foundation model for avatar video generation.

From a single image + an audio clip, Aurora produces a photorealistic video of a person speaking or singing — with full-body expressiveness, not just lip sync.

Aurora is a diffusion-based multimodal model that fuses audio, image, and optional text inputs to generate temporally coherent, emotionally aligned motion across the face, eyes, hands, and overall posture.

See demos + full detailed blog post here: 🔗 https://t.co/pYeQOShCXp

What makes this powerful:
- Zero-shot generation with highest visual fidelity
Identity consistency over long videos
- Natural gestures, facial nuance, and subtle motion
- Robust performance across diverse scenarios

It’s one of the most natural, expressive and controllable avatar models we’ve seen — and I’m incredibly proud of my team for making it happen.

[Creatify AI @Creatify_AI]

🆕 Today we’re introducing Aurora - the state-of-the-art image to avatar model.

From a single image and a voice, it generates ultra-realistic avatars that move, speak, and feel real.

With Aurora, you can scale your most creative marketing ideas. Aurora avatars don’t just say lines, they express them, making your ideas come alive on screen.

Comment "Aurora" & RT to get early access today.

[Ledell Wu @LedellWu]

We just announced our $15.5M Series A @creatify_ai , co-lead by @WndrCoLLC and @KindredVentures.

Today, we’re unveiling the next chapter of Creatify: AdMax—an autonomous AI agent for full-funnel advertising. 🚀

It’s not just gen AI for creatives. It’s a decision-making system that closes the loop between creative generation, testing, and performance optimization.

AdMax:
🧠 Ingests competitive ad data
🎨 Uses LLMs + VLMs to generate 100s of tailored video variants
📊 Runs live multi-variate tests (ROAS, CPA)
🔁 Analyzes performance feedback to generate smarter creatives & refine targeting
A full-stack agent that learns, adapts, and scales—autonomously.
The future of performance marketing is here → https://t.co/lMj9DjxSr8

Huge thanks to our customers: we couldn't reach this far with all your support, feedback, and love!

More details on our blog: https://t.co/3TklXHRln5

#AdMax #AIagents #SeriesA #Creatify #growthtech #autonomousads

[Creatify AI @Creatify_AI]

THE FUTURE IS HERE!

For the first time ever, you can now create your own 100% AI avatar from scratch. Simply describe your ideal representative, from their appearance to their surroundings, and our technology will bring your vision to life!

Available now at: https://t.co/7blTmaobMj (examples in thread)

[No real people were filmed in the making of this video.]

[Feiyang (Vance) Chen @vfychen]

@beckylitv I prefer Creatify 🙌 it can write script for you

[Feiyang (Vance) Chen @vfychen]

@beckylitv It's from Creatify AI (https://t.co/WDQOXVB5ad), you are welcome

[Google AI @GoogleAI]

We’re kicking off 2023 with a series of blog posts that look back at some of the many new and exciting developments coming out of Google Research. Check out our first post from @JeffDean, about computer vision, language, multimodal, and generative models! https://t.co/fDbpQlCVt0

[Sebastian Ruder @seb_ruder]

ML and NLP Research Highlights of 2021

These are the research areas and papers I found most exciting & inspiring in 2021.

https://t.co/sH96E6ww9n

[MONTREAL.AI @Montreal_AI]

Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer

Ronghang Hu, Amanpreet Singh: https://t.co/5x4oMfDg8C

#ArtificialIntelligence #DeepLearning #Transformer

[OpenAI @OpenAI]

We’ve developed two neural networks which have learned by associating text and images. CLIP maps images into categories described in text, and DALL-E creates new images, like this, from text.

A step toward systems with deeper understanding of the world. https://t.co/rppy6u1zcn

[/MachineLearning @slashML]

The best AI papers of 2020 with a clear video demo, short read, paper, and code for each of them. https://t.co/aVJedbWCOD

[Google DeepMind @GoogleDeepMind]

In a major scientific breakthrough, the latest version of #AlphaFold has been recognised as a solution to one of biology's grand challenges - the “protein folding problem”. It was validated today at #CASP14, the biennial Critical Assessment of protein Structure Prediction (1/3)

[Christopher Manning @chrmanning]

Artificial Intelligence Definitions: This (northern) summer, I spent more time than I’d like to admit coming up with a handout defining key terms in AI in 1 page, trying to be informative and suitable for non-specialists – let me know if you like them! https://t.co/baISijEzGK

[The Night AI Research Collective @thenightaico]

Finally created an account! The Night AI Research Collective is a fully-remote, independent AI research group. Our goal is to connect people from all over the world that want to conduct research, explore ideas and publish papers. Drop us a line https://t.co/ZjiNCagKRY.

[Feiyang (Vance) Chen @vfychen]

@SimonShaoleiDu @UW @uwcse Congratulations!!!

[Papers with Code @paperswithcode]

ICLR is starting! See all ICLR-2020 papers with official code sorted by number of GitHub stars here: https://t.co/fCDdZ0xnRi

[GitHub @github]

Today we’re announcing free private repositories with unlimited collaborators for teams with GitHub Free, and reducing the price of our paid Team plan to $4 per user/month. All of the core GitHub features are now free for everyone.

Learn more: https://t.co/fQ3r2ABtTR