UniVR: A New Approach to Pure Visual Reasoning
ByteDance · hf · 2026-07-17
ByteDance proposed UniVR, exploring how to learn broader world knowledge relying solely on pure visual demonstrations, while simultaneously covering three capabilities:
- Complex reasoning
- Fine-grained physical dynamics modeling
- Long-term planning
The core method is VR-GRPO: a reinforcement learning paradigm combining global and step-level rewards to constrain logical and physical consistency during reasoning, without relying on task-specific heuristics or image-text paired data.
They also built the VR-X benchmark, aggregating 16 sources to cover long-horizon manipulation, spatial puzzles, and physical reasoning, serving as a comprehensive evaluation suite under a pure visual protocol. Experiments show UniVR improves performance on VR-X by up to 25%, and its enhanced visual reasoning capabilities also feed back into multiple multimodal understanding benchmarks. Code, data, and models are all open-sourced.
More from Multimodal
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- WanGP v18.81 adds Tencent's Hy-Nomas world model, playable on 8GB VRAM — cocktailpeanut · 2026-10-27
- Butter.video wins over skeptical creator with hundreds of tasteful timeline 'blocks' for video effects — beechinour · 2026-10-27
- AI Video Pits Brock Lesnar Against Duncan the Tall in a Toy Showdown — KloneStudios · 2026-10-27
- $50, 2-hour Kurzgesagt-style AI video reignites debate over intent in AI creation — motionbynick · 2026-10-27
- Fake BTS of a dam disaster made with Dreamina Seedance for 29 cents — Standard_Spell5873 · 2026-10-27