Live portraits with detailed faces pushed to a new level 🧗🏼‍♂️

Another step for human head avatars #ECCV2022 - our work on head geometry and appearance reconstruction from a single photo is available. Welcome to try ROME! samsunglabs.github.io/rome

📢HumanRF at ACM SIGGRAPH 2023 synthesiaresearch.github.io/humanrf/ actors-hq.com We enable novel view synthesis of full-body humans in motion at 12MP resolution. HumanRF achieves per-frame Instant-NGP quality while being 20x more compact and temporally stable.

We have released the code for HumanRF on github.com/synthesiaresea…. Also, visit actors-hq.com to get access to our dataset, ActorsHQ.

👋 Hey there! I'm Nikita Drobyshev, a dedicated Generative AI researcher with a Global Talent UK visa. I've been in London for a year, and today, I'm opening up about my pursuit for knowledge. 📚 Imagine dreaming of a UK PhD, full of ambition and credentials, only to hit a wall

Next week I’ll be in Malta 🇲🇹 to present our work on Improving Generalization in Semantic Parsing by Increasing Natural Language Variation at #EACL2024! 1/3

How well do text-to-SQL parsers handle ambiguous questions? 🤔 Introducing 🌿𝔸𝕄𝔹ℝ𝕆𝕊𝕀𝔸, a new benchmark that tests the limits of text-to-SQL semantic parsers in interpreting ambiguous requests! ambrosia-benchmark.github.io 1/5

⚡️ Accepted to #NeurIPS2024 NeurIPS Conference D&B track as a Spotlight! See you in Vancouver!

🔥 New Preprint! 🔥 How should LLMs handle ambiguous questions in text-to-SQL semantic parsing? 👉🏼 Disambiguate First, Parse Later! We propose a plug-and-play approach that explicitly disambiguates the question 💬 Paper: arxiv.org/abs/2502.18448

Today we're introducing Gen-4, our new series of state-of-the-art AI models for media generation and world consistency. Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media. Gen-4 Image-to-Video is rolling out today to all paid

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise

Everyone's an actor now 🎬 I'm sooo proud 🚀

New, unreal possibilities for your imagination unlocked! 🎥✨ Who's ready to revolutionize storytelling?

Excited to share our paper "Asking a Language Model for Diverse Responses" accepted at #UncertaiNLP workshop at #EMNLP2025 When generating diverse responses, most use parallel sampling. We study non-independent alternatives: enumeration & iterative sampling. w/ Sergey Troshin 👇

Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.

It's still hard to believe what this tech is capable of nowadays. Prompt adherence is on 🔥; Try it!

First, we are excited to share a number of new updates to our frontier video generation model, Gen-4.5 Soon you will be able to both generate and edit native audio with Gen-4.5 and edit video at arbitrary lengths with multi-shot editing.

Reasoning models are powerful, but they burn thousands of tokens on potentially wrong interpretations for ambiguous requests! 👉 We teach models to think about intent first and provide all interpretations and answers in a single response via RL with dual reward. 🧵1/6