Existing video benchmarks often resemble image-based benchmarks, with question types like “What actions does the person perform throughout the video?” or “What color is the woman’s dress in the video?” For these, models can often answer by scanning just a few key frames, without deep temporal reasoning. This limits our ability to assess whether large vision-language models (LVLMs) can truly think with videos rather than perform superficial frame-level analysis. To address this, we introduce , a benchmark specifically designed to evaluate whether LVLMs can genuinely think with videos. Unlike prior benchmarks, emphasizes comprehensive video understanding beyond static image cues. It consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection. All questions are carefully crafted by human annotators and require watching the entire video and reasoning over full video context—this is what we mean by thinking with video. These questions cannot be answered by scanning selected frames or relying on text alone. In human evaluations, achieves 94.82% accuracy, but current LVLMs face significant challenges. Even the best-performing model, GPT-o3, reaches only 66.43%, highlighting that LVLMs still struggle to move beyond surface-level reasoning to truly think with videos. We publicly release our benchmark and code at https://github.com/aiming-lab/GLIMPSE.

In this paper, we propose NUWA-XL, a novel Diffusion over Diffusion architecture for eXtremely Long video generation. Most current work generates long videos segment by segment sequentially, which normally leads to the gap between training on short videos and inferring long videos, and the sequential generation is inefficient. Instead, our approach adopts a “coarse-to-fine” process, in which the video can be generated in parallel at the same granularity. A global diffusion model is applied to generate the keyframes across the entire time range, and then local diffusion models recursively fill in the content between nearby frames. This simple yet effective strategy allows us to directly train on long videos (3376 frames) to reduce the training-inference gap and makes it possible to generate all segments in parallel. To evaluate our model, we build FlintstonesHD dataset, a new benchmark for long video generation. Experiments show that our model not only generates high-quality long videos with both global and local coherence, but also decreases the average inference time from 7.55min to 26s (by 94.26%) at the same hardware setting when generating 1024 frames. The homepage link is [NUWA-XL](https://msra-nuwa.azurewebsites.net)

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on similar tasks and with the same initialization. In this paper, we expand on this concept to a multimodal setup by merging transformers trained on different modalities. Furthermore, we conduct our study for a novel goal where we can merge vision, language, and cross-modal transformers of a modality-specific architecture to create a parameter-efficient modality-agnostic architecture. Through comprehensive experiments, we systematically investigate the key factors impacting model performance after merging, including initialization, merging mechanisms, and model architectures. We also propose two metrics that assess the distance between weights to be merged and can serve as an indicator of the merging outcomes. Our analysis leads to an effective training recipe for matching the performance of the modality-agnostic baseline (i.e., pre-trained from scratch) via model merging. Our method also outperforms naive merging significantly on various tasks, with improvements of 3% on VQA, 7% on COCO retrieval, 25% on NLVR2, 14% on Flickr30k and 3% on ADE20k.