论文检索

Computer Vision · Vision Models & Multimodal

Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener, Angela Yao

Multimodal Large Language Models (MLLMs) have advanced open-world action understanding and can be adapted as generative classifiers for closed-set settings by autoregressively generating action labels as text. However, this approach is inefficient, and shared subwords across action labels introduce semantic overlap, leading to ambiguity in generation. In contrast, discriminative classifiers learn task-specific representations with clear decision boundaries, enabling efficient one-step classification without autoregressive decoding. We first compare generative and discriminative classifiers with MLLMs for closed-set action understanding, revealing the superior accuracy and efficiency of the latter. To bridge the performance gap, we design strategies that elevate generative classifiers toward performance comparable with discriminative ones. Furthermore, we show that generative modeling can complement discriminative classifiers, leading to better performance while preserving efficiency. To this end, we propose Generation-Assisted Discriminative (GAD) classifier for closed-set action understanding. GAD operates only during fine-tuning, preserving full compatibility with MLLM pretraining. Extensive experiments on temporal action understanding benchmarks demonstrate that GAD improves both accuracy and efficiency over generative methods, achieving state-of-the-art results on four tasks across five datasets, including an average 2.5\% accuracy gain and 3$\times$ faster inference on our largest COIN benchmark.

Computer Vision · 3D Rendering & Reconstruction

Feiran Wang, Junyi Wu, Dawen Cai, Yuan Hong, Yan Yan

We present CogniMap3D, a bioinspired framework for dynamic 3D scene understanding and reconstruction that emulates human cognitive processes. Our approach maintains a persistent memory bank of static scenes, enabling efficient spatial knowledge storage and rapid retrieval. CogniMap3D integrates three core capabilities: a multi-stage motion cue framework for identifying dynamic objects, a cognitive mapping system for storing, recalling, and updating static scenes across multiple visits, and a factor graph optimization strategy for refining camera poses. Given an image stream, our model identifies dynamic regions through motion cues with depth and camera pose priors, then matches static elements against its memory bank. When revisiting familiar locations, CogniMap3D retrieves stored scenes, relocates cameras, and updates memory with new observations. Evaluations on video depth estimation, camera pose reconstruction, and 3D mapping tasks demonstrate its state-of-the-art performance, while effectively supporting continuous scene understanding across extended sequences and multiple visits.

Computer Vision · 3D Rendering & Reconstruction

Xiaolu Liu, Yicong Li, Qiyuan He, Jiayin Zhu, Wei Ji, Angela Yao, Jianke Zhu

Textured 3D morphing seeks to generate smooth and plausible transitions between two 3D assets, preserving both structural coherence and fine-grained appearance. This ability is crucial not only for advancing 3D generation research but also for practical applications in animation, editing, and digital content creation. Existing approaches either operate directly on geometry, limiting them to shape-only morphing while neglecting textures, or extend 2D interpolation strategies into 3D, which often causes semantic ambiguity, structural misalignment, and texture blurring. These challenges underscore the necessity to jointly preserve geometric consistency, texture alignment, and robustness throughout the transition process. To address this, we propose Interp3D, a novel training-free framework for textured 3D morphing. It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence. Starting from semantically aligned interpolation in condition space, Interp3D enforces structural consistency via SLAT (Structured Latent)-guided structure interpolation, and finally transfers appearance details through fine-grained texture fusion. For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility. Both quantitative metrics and human studies demonstrate the significant advantages of our proposed approach over previous methods. Source code is available at https://github.com/xiaolul2/Interp3D.

Computer Vision · Vision Models & Multimodal

Ming Zhao, Wenhui Dong, Yang Zhang, wangyou, Zhonghao Zhang, Zian Zhou, YUNZHI GUAN, Liukun Xu, Wei Peng, Zhaoyang Gong 等

Spine disorders affect 619 million people globally and are a leading cause of disability, yet AI-assisted diagnosis remains limited by the lack of level-aware, multimodal datasets. Clinical decision-making for spine disorders requires sophisticated reasoning across X-ray, CT, and MRI at specific vertebral levels. However, progress has been constrained by the absence of traceable, clinically-grounded instruction data and standardized, spine-specific benchmarks. To address this, we introduce SpineMed, an ecosystem co-designed with practicing spine surgeons. It features SpineMed-450k, the first large-scale dataset explicitly designed for vertebral-level reasoning across imaging modalities with over 450,000 instruction instances, and SpineBench, a clinically-grounded evaluation framework. SpineMed-450k is curated from diverse sources, including textbooks, guidelines, open datasets, and $\sim$1,000 de-identified hospital cases, using a clinician-in-the-loop pipeline with a two-stage LLM generation method (draft and revision) to ensure high-quality, traceable data for question-answering, multi-turn consultations, and report generation. SpineBench evaluates models on clinically salient axes, including level identification, pathology assessment, and surgical planning. Our comprehensive evaluation of several recently advanced large vision-language models (LVLMs) on SpineBench reveals systematic weaknesses in fine-grained, level-specific reasoning. In contrast, our model fine-tuned on SpineMed-450k demonstrates consistent and significant improvements across all tasks. Clinician assessments confirm the diagnostic clarity and practical utility of our model's outputs.

General Machine Learning · Representation Learning

Zhao-Rong Lai, Zheng-Sen Zhou, Liangda Fang, Yongsen Zheng, Ziliang Chen

Continuous-time graph representation (CTGR) is a widely-used methodology in machine learning, physics, bioinformatics, and social networks. The sequential survival process in a latent space with the squared $\ell_2$ distance is an important ultra-low-dimensional embedding for CTGR. However, the squared $\ell_2$ distance violates the triangle inequality, which may cause distortion of the relative node positions in the latent space and thus deteriorates in social, contact, and collaboration networks. Reverting to the $\ell_2$ distance is infeasible because the corresponding integral computation is intractable. To solve these problems, we propose a theoretically-sound $\ell_1$ latent distance based continuous-time graph representation ($\ell_1$LD-CTGR). It facilitates a true latent metric space for the sequential survival process. Moreover, the integral of the hazard function is found to be a closed-form piece-wise exponential integral, which well fits the ultra-low-dimensional embedding. To handle the non-differentiable $\ell_1$ norm, we successfully find a descent direction of the hazard function to replace the gradient, enabling mainstream learning architectures to learn the parameters. Extensive experiments using both synthetic and real-world data show the competitive performance of $\ell_1$LD-CTGR.

Computer Vision · 3D Rendering & Reconstruction

Jiahao Chang, Chongjie Ye, Yushuang Wu, Yuantao Chen, Yidan Zhang, Zhongjin Luo, Chenghong Li, Yihao Zhi, Xiaoguang Han

Existing multi-view 3D object reconstruction methods heavily rely on sufficient overlap between input views, where occlusions and sparse coverage in practice frequently yield severe reconstruction incompleteness. Recent advancements in diffusion-based 3D generative techniques offer the potential to address these limitations by leveraging learned generative priors to ‘‘hallucinate" invisible parts of objects, thereby generating plausible 3D structures. However, the stochastic nature of the inference process limits the accuracy and reliability of generation results, preventing existing reconstruction frameworks from integrating such 3D generative priors. In this work, we comprehensively analyze the reasons why diffusion-based 3D generative methods fail to achieve high consistency, including (a) the insufficiency in constructing and leveraging cross-view connections when extracting multi-view image features as conditions, and (b) the poor controllability of iterative denoising during local detail generation, which easily leads to plausible but inconsistent fine geometric and texture details with inputs. Accordingly, we propose ReconViaGen to innovatively integrate reconstruction priors into the generative framework and devise several strategies that effectively address these issues. Extensive experiments demonstrate that our ReconViaGen can reconstruct complete and accurate 3D models consistent with input views in both global structure and local details.

Computer Vision · 3D Rendering & Reconstruction

Seungeun Lee, SeungJun Moon, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park

Recent advances in neural rendering, particularly 3D Gaussian Splatting (3DGS), have enabled animatable 3D human avatars from single videos with efficient rendering and high fidelity. However, current methods struggle with dynamic appearances, especially in loose garments (e.g., skirts), causing unrealistic cloth motion and needle artifacts. This paper introduces a novel approach to dynamic appearance modeling for 3DGS-based avatars, focusing on loose clothing. We identify two key challenges: (1) limited Gaussian deformation under pre-defined template articulation, and (2) a mismatch between body-template assumptions and the geometry of loose apparel. To address these issues, we propose a motion-aware autoregressive structural deformation framework for Gaussians. We structure Gaussians into an approximate graph and recursively predict structure-preserving updates, yielding realistic, template-free cloth dynamics. Our framework enables robust dynamic appearance modeling under the single-view constraint, producing accurate foreground silhouettes and precise alignment of Gaussian points with clothed shapes. To demonstrate the effectiveness of our method, we introduce an evaluation dataset featuring subjects performing dynamic movements in loose clothing, and extensive experiments validate that our approach significantly outperforms existing 3DGS-based methods in modeling dynamic appearances from monocular videos.

Computer Vision · 3D Rendering & Reconstruction

Qiwei Wang, Xianghui Ze, Jingyi Yu, Yujiao Shi

Feed-forward 3D Gaussian Splatting (3DGS) has shown great promise for real-time novel view synthesis, but its application to panoramic imagery remains challenging. Existing methods often rely on multi-view cost volumes for geometric refinement, which struggle to resolve occlusions in sparse-view scenarios. Furthermore, standard volumetric representations like Cartesian Triplanes are poor in capturing the inherent geometry of $360^\circ$ scenes, leading to distortion and aliasing. In this work, we introduce CylinderSplat, a feed-forward framework for panoramic 3DGS that addresses these limitations. The core of our method is a new {cylindrical Triplane} representation, which is better aligned with panoramic data and real-world structures adhering to the Manhattan-world assumption. We use a dual-branch architecture: a pixel-based branch reconstructs well-observed regions, while a volume-based branch leverages the cylindrical Triplane to complete occluded or sparsely-viewed areas. Our framework is designed to flexibly handle a variable number of input views, from single to multiple panoramas. Extensive experiments demonstrate that CylinderSplat achieves state-of-the-art results in both single-view and multi-view panoramic novel view synthesis, outperforming previous methods in both reconstruction quality and geometric accuracy.

Computer Vision · 3D Rendering & Reconstruction

xilong zhou, Bao-Huy Nguyen, Loïc Magne, Vladislav Golyanik, Thomas Leimkuehler, Christian Theobalt

Radiance fields have emerged as a predominant representation for modeling 3D scene appearance. Neural formulations such as Neural Radiance Fields provide high expressivity but require costly ray marching for rendering, whereas primitive-based methods such as 3D Gaussian Splatting offer real-time efficiency through splatting, yet at the expense of representational power. Inspired by advances in both these directions, we introduce splattable neural primitives, a new volumetric representation that reconciles the expressivity of neural models with the efficiency of primitive-based splatting. Each primitive encodes a bounded neural density field parameterized by a shallow neural network. Our formulation admits an exact analytical solution for line integrals, enabling efficient computation of perspectively accurate splatting kernels. As a result, our representation supports integration along view rays without the need for costly ray marching. The primitives flexibly adapt to scene geometry and, being larger than prior analytic primitives, reduce the number required per scene. On novel-view synthesis benchmarks, our approach matches the quality and speed of 3D Gaussian Splatting while using 10x fewer primitives and 6x fewer parameters. These advantages arise directly from the representation itself, without reliance on complex control or adaptation frameworks.

Computer Vision · Vision Models & Multimodal

Yifan Li, Zhenghao Chen, Ziheng Wu, Kun Zhou, Ruipu Luo, Can Zhang, Zhentao he, Yufei Zhan, Xin Zhao, Minghui Qiu

Recent advances in inference-time scaling, particularly those leveraging reinforcement learning with verifiable rewards, have substantially enhanced the reasoning capabilities of Large Vision-Language Models (LVLMs). Inspired by this success, similar strategies have been applied to multimodal reasoning, yet their impact on visual perception remains unclear. To investigate this gap, we introduce DisTANCE, a perception-centric benchmark for visual estimation tasks. Evaluation results show that LVLMs exhibit limited estimation precision, and inference-time scaling offers only marginal gains. We attribute this to the fast perception paradigm of current LVLMs, where visual understanding is treated as a one-shot output without modeling the underlying perceptual process. To address this, we propose Perception-Time Scaling (PTS), a novel paradigm that encourages token-rich perception and decomposes complex perception problems into intermediate tractable sub-problems, thereby enabling perception to align with and benefit from inference-time scaling. Combined with reinforcement learning techniques, PTS significantly improves perception accuracy, raising high-precision performance on DisTANCE from 8.0% to 64.7%, and generalizes well to out-of-domain tasks. Surprisingly, even though PTS data are purely synthetic, combining them with math reasoning data yields consistent gains in both reasoning and real-world perception benchmarks. Further analysis reveals that PTS introduces more perception-related tokens and increases the model’s attention to image tokens. Our code and data are released at https://github.com/RUCAIBox/PTS

Computer Vision · Image and Video Generation

Zhiteng Li, Hanxuan Li, Junyi Wu, Kai Liu, Haotong Qin, Linghe Kong, Guihai Chen, Yulun Zhang, Xiaokang Yang

Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) $\delta$-Guided Bit Switching ($\delta$-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2$\times$ speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be released to facilitate future research.

Computer Vision · Image and Video Generation

Qiyuan He, Yicong Li, Haotian Ye, Jinghao Wang, Xinyao Liao, Pheng-Ann Heng, Stefano Ermon, James Y Zou, Angela Yao

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and rasterization ordering. In this work, we identify a core bottleneck from the perspective of generator-tokenizer inconsistency, i.e., the AR-generated tokens may not be well-decoded by the tokenizer. To address this, we propose reAR, a simple training strategy introducing a token-wise regularization objective: when predicting the next token, the causal transformer is also trained to recover the visual embedding of the current token and predict the embedding of the target token under a noisy context. It requires no changes to the tokenizer, generation order, inference pipeline, or external models. Despite its simplicity, reAR substantially improves performance. On ImageNet, it reduces gFID from 3.02 to 1.86 and improves IS to 316.9 using a standard rasterization-based tokenizer. When applied to advanced tokenizers, it achieves a gFID of 1.42 with only 177M parameters, matching the performance with larger state-of-the-art diffusion models (675M).

Applications · Language, Speech and Dialog

Vishakh Padmakumar, Chen Yueh-Han, Jane Pan, Valerie Chen, He He

As large language models (LLMs) are increasingly used for ideation and scientific discovery, it is important to evaluate their ability to generate novel output. Prior work evaluates novelty as originality with respect to model training data, but original outputs can be of low quality. In contrast, non-expert judges more reliably score quality but may favor memorized outputs, limiting the reliability of human preference as a metric. We introduce a new novelty metric for LLM generations that balances originality and quality---the harmonic mean of the fraction of \ngrams unseen during training and a task-specific quality score. Using this framework, we identify trends that affect the novelty of generations from three families of open-data models (OLMo, OLMo-2, and Pythia) on three creative tasks---story completion, poetry writing, and creative tool use. We find that model-generated text from some base LLMs is less novel than human-written text from the internet. However, increasing model scale (OLMo 1B to 7B to 32B) and post-training reliably improves novelty due to improvements in output quality. We also find that improving the base model at the same scale (\eg OLMo 7B to OLMo-2 7B) leads to higher novelty due to higher originality. Finally, we observe that inference-time methods, such as prompting and providing novel in-context examples, have a much smaller effect on novelty, often increasing originality at the expense of quality. This highlights the need for further research into more effective elicitation strategies as we use models for creative applications.

Computer Vision · Image and Video Generation

Zhijing Cheng, Xuancheng Zhang, Donglin Di, Chen Wei, Hao Li, Xun Yang

Camera control is important in text-to-video generation for achieving realistic scene navigation and view synthesis. This control is defined by parameters that describe movement through 3D space, thereby introducing 3D consistency into the generation process. A core challenge for existing methods is achieving 3D consistency within the 2D pixel domain. Strategies that directly integrate camera conditions into text-to-video models often produce artifacts, while those relying on explicit 3D supervision face challenges with generalization. Both limitations originate from the gap between the 2D pixel space and the underlying 3D world. The key insight is that the projection of a smooth 3D camera movement produces consistency in object view, appearance, and motion across 2D frames. Inspired by this insight, we propose MoCa, a dual-branch framework that bridges this gap by modeling object consistency to implicitly learn 3D relationships between the camera and the scene. To ensure view consistency, we design a Spatial-Temporal Camera Encoder with Plücker embedding, which encodes camera trajectories into a geometrically grounded latent representation. For appearance consistency, we introduce a semantic guidance strategy that leverages persistent vision-language features to maintain object identity and texture across frames. To address motion consistency, we propose an object-aware motion disentanglement mechanism that separates object dynamics from global camera movement, ensuring precise camera control and natural object motion. Experiments show that MoCa achieves accurate camera control while preserving video quality, offering a practical and effective solution for camera-controllable video generation.

Computer Vision · Image and Video Generation

Chubin Chen, Jiashu Zhu, Xiaokun Feng, Nisha Huang, Chen Zhu, Meiqi Wu, Fangyuan Mao, Jiahong Wu, Xiangxiang Chu, Xiu Li

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for generating high-quality samples. However, through an empirical analysis on both Gaussian mixture models with closed-form solutions and real-world data distributions, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to low fidelity and semantic incoherence. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself, without requiring additional training or the integration of external modules. Building on this insight, we propose **$S^2$-Guidance ($S$tochastic $S$elf-Guidance)**, a novel method that leverages stochastic block-dropping during the denoising process to construct sub-networks. This approach effectively guides the model away from potential low-quality predictions, thereby improving sample quality. Extensive qualitative and quantitative experiments across multiple standard benchmarks for text-to-image and text-to-video generation tasks demonstrate that **$S^2$-Guidance** delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.

Computer Vision · Image and Video Generation

Yang Li, Songlin Yang, Wei Wang, Xiaoxuan Han, Jing Dong

Diffusion models have demonstrated remarkable success in high-fidelity image generation, yet aligning them with human preferences remains challenging. Direct Preference Optimization (DPO) offers a promising framework, but its effectiveness is critically hindered by noisy data arising from mislabeled preference pairs and individual preference pairs. We theoretically show that existing DPO objectives are equivalent to minimizing the Forward Kullback–Leibler (KL) divergence, whose mass-covering nature makes it intrinsically sensitive to such noise. To address this limitation, we propose $\alpha$-DPO, which reformulates preference alignment through the lens of $\alpha$-divergence. This formulation promotes mode-seeking behavior and bounds the influence of outliers, thereby enhancing robustness. Furthermore, we introduce a dynamic scheduling mechanism that adaptively adjusts $\alpha$ according to the observed preference distribution, providing data-aware noise tolerance during training. Extensive experiments on synthetic and real-world datasets validate that $\alpha$-DPO consistently outperforms existing baselines, achieving superior robustness and preference alignment.

Computer Vision · Image and Video Generation

Xirui Hu, Yanbo Ding, Jiahao Wang, Tingting Shi, Yali Wang, Guo Zhi, Weizhan Zhang

Character image animation, which synthesizes videos of reference characters driven by pose sequences, has advanced rapidly but remains largely limited to single-human settings. Existing methods struggle to generalize to multi-humanoid scenarios, which involve diverse humanoid forms, complex interactions, and frequent occlusions. We address this gap with two key innovations. First, we introduce unified motion representations that extract identity-agnostic motions and explicitly bind them to corresponding characters, enabling generalization across diverse humanoid forms and seamless extension to multi-humanoid scenarios. Second, we propose a holistic 4D-anchored paradigm that constructs a shared 4D space to fuse motion representations with video latents, and further reinforces this process with hierarchical 4D-level supervision to better handle interactions and occlusions. We instantiate these ideas in MotionWeaver, an end-to-end framework for multi-humanoid image animation. To support this setting, we curate a 46-hour dataset of multi-human videos with rich interactions, and construct a 300-video benchmark featuring paired humanoid characters. Quantitative and qualitative experiments demonstrate that MotionWeaver not only achieves state-of-the-art results on our benchmark but also generalizes effectively across diverse humanoid forms, complex interactions, and challenging multi-humanoid scenarios.

Computer Vision · Image and Video Generation

Matthieu Terris, Samuel Hurault, Maxime Song, Julián Tachella

Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods leveraging pretrained denoisers, and unrolled architectures that are trained end-to-end for specific imaging problems. Iterative methods in the first class are computationally costly and often yield suboptimal reconstruction performance, whereas unrolled architectures are generally problem-specific and require expensive training. In this work, we propose a novel non-iterative, lightweight architecture that incorporates knowledge about the forward operator (acquisition physics and noise parameters) without relying on unrolling. Our model is trained to solve a wide range of inverse problems, such as deblurring, magnetic resonance imaging, computed tomography, inpainting, and super-resolution, and handles arbitrary image sizes and channels, such as grayscale, complex, and color data. The proposed model can be easily adapted to unseen inverse problems or datasets with a few fine-tuning steps (up to a few images) in a self-supervised way, without ground-truth references. Throughout a series of experiments, we demonstrate state-of-the-art performance from medical imaging to low-photon imaging and microscopy. Our code is available at https://github.com/matthieutrs/ram.

Computer Vision · Image and Video Generation

Yu Li, Menghan Xia, Gongye Liu, Jianhong Bai, Xintao WANG, Conglang Zhang, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Yujiu Yang

Recent Text-to-Video (T2V) models have demonstrated powerful capability in visual simulation of real-world geometry and physical laws, indicating its potential as implicit world models. Inspired by this, we explore the feasibility of leveraging the video generation prior for viewpoint planning from given 4D scenes, since videos internally accompany dynamic scenes with natural viewpoints. To this end, we propose a two-stage paradigm to adapt pre-trained T2V models for viewpoint prediction, in a compatible manner. First, we inject the 4D scene representation into the pre-trained T2V model via an adaptive learning branch, where the 4D scene is viewpoint-agnostic and the conditional generated video embeds the viewpoints visually. Then, we formulate viewpoint extraction as a hybrid-condition guided camera extrinsic denoising process. Specifically, a camera extrinsic diffusion branch is further introduced onto the pre-trained T2V model, by taking the generated video and 4D scene as input. Experimental results show the superiority of our proposed method over existing competitors, and ablation studies validate the effectiveness of our key technical designs. To some extent, this work proves the potential of video generation models toward 4D interaction in real world.

Computer Vision · Image and Video Generation

Junsong Chen, Yuyang Zhao, Jincheng YU, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Zhou Daquan, Huan Ling 等

We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720×1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1\% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x} speedup). In summary, SANA-Video enables low-cost, high-quality video generation. Code and model will be publicly released.