Live drop

UniVR-34B-Planning

ByteDanceDropped Jul 13, 20261 build1 maker

Visual-only long-horizon planning for robotics and tool use from raw demonstrations.

The most interesting things people are building with AI, all in one place — followed and tracked as they evolve from first demo to real product.

347 indexedPress / to search--:--:-- UTC

Home Leaderboard Top creators What is this?Privacy TermsFeedback

DROPDAY.ai

UniVR-34B-Planning — Model Drop — Dropday.ai

dropday.ai

Home

Browse

Model Drops Leaderboard

← All model drops

Live drop

UniVR-34B-Planning

ByteDanceDropped Jul 13, 20261 build1 maker

Visual-only long-horizon planning for robotics and tool use from raw demonstrations.

Browse in feed Submit a build

The most interesting things people are building with AI, all in one place — followed and tracked as they evolve from first demo to real product.

347 indexedPress / to search--:--:-- UTC

Home Leaderboard Top creators What is this?Privacy TermsFeedback

DROPDAY.ai

About this release

What is UniVR-34B-Planning?

UniVR-34B-Planning is a 34B multimodal model built on Emu3.5 that performs unified next-token prediction directly in visual space. It learns complex reasoning, physical dynamics, and multi-step planning from image-based demonstrations without intermediate text chains or task-specific heuristics. Released openly on Hugging Face with checkpoints, code, and dataset, it targets agentic and robotic workflows such as manipulation and control.

Read the official ByteDance launch page

Worth opening first

Standouts

Playable

Flova

All-in-one AI video agent for cinematic films and automated animation workflows.

Playable1

Playable

Flova

All-in-one AI video agent for cinematic films and automated animation workflows.

Apps

Built something with UniVR-34B-Planning?

Paste the URL and Dropday.ai will credit you, track the build as it evolves, and put it on this drop.

Submit a build