# Ai2 — MolmoMotion: Language-guided 3D motion forecasting

- Company: Ai2 (allenai.org)
- Announced: 2026-06-17
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://allenai.org/blog/molmo-motion
- Record: https://forck.live/items/18551-molmomotion-language-guided-3d-motion-forecasting
- Subject: Olmo / Molmo / Asta
- Open weights: yes
- Models affected: MolmoMotion, MolmoMotion-AR, MolmoMotion-FM

Ai2 released MolmoMotion, a motion forecasting model that predicts future 3D point trajectories from a video frame, query points, and a language instruction. The model uses Molmo 2 as its backbone and comes in two variants: an autoregressive version (MolmoMotion-AR) and a flow-matching version (MolmoMotion-FM). Alongside the model, Ai2 published the MolmoMotion-1M dataset of 1.16M videos with 3D point trajectories and action descriptions, and PointMotionBench, a human-validated benchmark of 2.7K video clips for evaluating object-centric 3D motion forecasting.

## Evidence

Verbatim from https://allenai.org/blog/molmo-motion:

> Given a video frame, 3D points marked on an object, and written instructions describing the intended action (e.g., “Move and rotate the wooden bowl with fruit on the table”), MolmoMotion predicts where those points will move over the next few seconds in 3D space—achieving substantially stronger performance than existing forecasting methods.

---

Record: https://forck.live/items/18551-molmomotion-language-guided-3d-motion-forecasting
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md