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

• URL: http://arxiv.org/abs/2601.10611v1
• Date: Thu, 15 Jan 2026 17:27:44 GMT
• Title: Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
• Authors: Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna,
• Abstract summary: Molmo2 is a new family of video-language models (VLMs) that are state-of-the-art among open-source models.<n>We show exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks.<n>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.
• Score: 73.52241177491655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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).

Related papers

• PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding [126.15907330726067]
  We study building a Perception Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding.<n>We analyze standard training pipelines without distillation from models and explore large-scale synthetic data to identify critical data gaps.<n>To bridge these gaps, we release PLM-VideoBench, a suite for evaluating challenging video understanding tasks.
  arXiv  Detail & Related papers  (2025-04-17T17:59:56Z)
• Pretrained Image-Text Models are Secretly Video Captioners [38.66202065611397]
  We find that an image-based model can be repurposed to outperform several specialised video captioning systems.<n>Our adapted model demonstrates top tier performance on major benchmarks, ranking 2nd on MSRVTT and MSVD, and 3rd on VATEX.<n>From a resource optimization perspective, this video captioning study focuses on three fundamental factors: optimizing model scale, maximizing data efficiency, and incorporating reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-19T01:53:03Z)
• TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler [10.92767902813594]
  We introduce TinyLLaVA-Video, a lightweight yet powerful video understanding model with approximately 3.6B parameters.<n>The cornerstone of our design is the video-level group resampler, a novel mechanism that significantly reduces and controls the number of visual tokens at the video level.<n>TinyLLaVA-Video demonstrates exceptional efficiency, requiring only one day of training on 8 A100-40G GPUs.
  arXiv  Detail & Related papers  (2025-01-26T13:10:12Z)
• VideoSAVi: Self-Aligned Video Language Models without Human Supervision [0.6854849895338531]
  VideoSAVi is a self-training pipeline that enables Video-LLMs to learn from video content without external supervision.<n>Our approach includes a self-critiquing mechanism that identifies reasoning errors in the model's initial responses.<n>VideoSAVi delivers significant improvements across multiple benchmarks.
  arXiv  Detail & Related papers  (2024-12-01T00:33:05Z)
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models [146.85788712792177]
  Molmo is a new family of vision-language models (VLMs) that are state-of-the-art in their class of openness.<n>Our best-in-class 72B model outperforms others in the class of open weight and data models.
  arXiv  Detail & Related papers  (2024-09-25T17:59:51Z)
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets [36.95521842177614]
  We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. We identify and evaluate three different stages for successful training of video LDMs: text-to-image pretraining, video pretraining, and high-quality video finetuning.
  arXiv  Detail & Related papers  (2023-11-25T22:28:38Z)
• Probabilistic Adaptation of Text-to-Video Models [181.84311524681536]
  Video Adapter is capable of incorporating the broad knowledge and preserving the high fidelity of a large pretrained video model in a task-specific small video model. Video Adapter is able to generate high-quality yet specialized videos on a variety of tasks such as animation, egocentric modeling, and modeling of simulated and real-world robotics data.
  arXiv  Detail & Related papers  (2023-06-02T19:00:17Z)
• MagicVideo: Efficient Video Generation With Latent Diffusion Models [76.95903791630624]
  We present an efficient text-to-video generation framework based on latent diffusion models, termed MagicVideo. Due to a novel and efficient 3D U-Net design and modeling video distributions in a low-dimensional space, MagicVideo can synthesize video clips with 256x256 spatial resolution on a single GPU card. We conduct extensive experiments and demonstrate that MagicVideo can generate high-quality video clips with either realistic or imaginary content.
  arXiv  Detail & Related papers  (2022-11-20T16:40:31Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.