# Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

arXiv: https://arxiv.org/abs/2601.10611 · HTML: https://mlsanity.com/paper/2601.10611/

## Key facts

- Cited by 139 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 47 of its 190 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 47)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [MOT20: A benchmark for multi object tracking in crowded scenes](https://mlsanity.com/paper/2003.09003/) (2020)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe](https://mlsanity.com/paper/2509.18154/) (2025)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models](https://mlsanity.com/paper/2407.15841/) (2024)

## Built on by (most cited first, 30 of 139)

- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [MolmoPoint: Better Pointing for VLMs with Grounding Tokens](https://mlsanity.com/paper/2603.28069/) (2026)
- [EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding](https://mlsanity.com/paper/2605.09874/) (2026)
- [The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents](https://mlsanity.com/paper/2604.10577/) (2026)
- [TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs](https://mlsanity.com/paper/2602.00288/) (2026)
- [VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning](https://mlsanity.com/paper/2602.08828/) (2026)
- [Vero: An Open RL Recipe for General Visual Reasoning](https://mlsanity.com/paper/2604.04917/) (2026)
- [VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding](https://mlsanity.com/paper/2607.14935/) (2026)
- [Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model](https://mlsanity.com/paper/2607.24904/) (2026)
- [CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning](https://mlsanity.com/paper/2606.09393/) (2026)
- [SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs](https://mlsanity.com/paper/2602.06566/) (2026)
- [Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders](https://mlsanity.com/paper/2603.06569/) (2026)
- [VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification](https://mlsanity.com/paper/2604.01569/) (2026)
- [AdaCodec: A Predictive Visual Code for Video MLLMs](https://mlsanity.com/paper/2606.02569/) (2026)
- [SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance](https://mlsanity.com/paper/2603.12703/) (2026)
- [Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models](https://mlsanity.com/paper/2606.11324/) (2026)
- [Small Vision-Language Models are Smart Compressors for Long Video Understanding](https://mlsanity.com/paper/2604.08120/) (2026)
- [InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning](https://mlsanity.com/paper/2606.12195/) (2026)
- [MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction](https://mlsanity.com/paper/2606.18558/) (2026)
- [VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models](https://mlsanity.com/paper/2603.24575/) (2026)
- [PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning](https://mlsanity.com/paper/2603.26653/) (2026)
- [Scaling Video Understanding via Compact Latent Multi-Agent Collaboration](https://mlsanity.com/paper/2605.00444/) (2026)
- [Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos](https://mlsanity.com/paper/2605.18984/) (2026)
- [On Test-Time Scaling for Vision-Language Models](https://mlsanity.com/paper/2606.28864/) (2026)
- [Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs](https://mlsanity.com/paper/2608.20492/) (2026)
- [Can Vision-Language Models Solve the Shell Game?](https://mlsanity.com/paper/2603.08436/) (2026)
- [Video-Based Reward Modeling for Computer-Use Agents](https://mlsanity.com/paper/2603.10178/) (2026)

## Abstract (arXiv)

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).