Recent advances in video generation have made minute-level synthesis possible; however, generating long videos remains challenging due to error accumulation, attribute drift, and the limited availability of long video data. In this paper, we introduce an infinite-length video generation framework that focusing on addressing these issues and produces high-quality, dynamic, and identity-consistent single-shot long videos. We first finetune a diffusion model as a video extension model on large-scale short video data to autoregressively generate temporally coherent clips. Inspired by the success of large language models (LLMs), we adopt causal attention computation between clips to further finetune this model on long video data. In this way, the tokens in one clip (short video) are computed by bidirectional attention while tokens among clips are computed by unidirectional attention. This design leverages the strengths of modern diffusion models while preserving long-term context information, effectively mitigating error accumulation and attribute drift. To achieve memory efficiency during inference, we adopt a key-value (KV) caching mechanism to maintain a constant KV memory. Furthermore, we introduce truncation-rectified flow (T-RFlow) technique to further suppress error accumulation. Experimental results demonstrate the effectiveness of our method. Our framework establishes a new benchmark for realistic and coherent minute-level video synthesis.

In this work, we propose a novel generative learning paradigm, K-Flow, an algorithm that flows along the K-amplitude. Here, k is a scaling parameter that organizes frequency bands (or projected coefficients), and amplitude describes the norm of such projected coefficients. By incorporating the K-amplitude decomposition, K-Flow enables flow matching across the scaling parameter as time. We discuss three venues and six properties of K-Flow, from theoretical foundations, energy and temporal dynamics, and practical applications, respectively. Specifically, from the practical usage perspective, K-Flow allows steerable generation by controlling the information at different scales. To demonstrate the effectiveness of K-Flow, we conduct experiments on unconditional image generation, class-conditional image generation, and molecule assembly generation. Additionally, we conduct three ablation studies to demonstrate how K-Flow steers scaling parameter to effectively control the resolution of image generation.

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an LLM-based unified model for AR video generation with efficient discrete diffusion. Firstly, to fit videos with LLMs, we identify that 1D RoPE is ill-suited for visual spatiotemporal correlation modeling, and while demonstrated to be useful, naive 3D RoPE exhibits imbalanced frequency spectra. Therefore, we propose MM‑RoPE, which preserves the original textual RoPE while seamlessly accommodating video data with comprehensive frequency spectra and scaled 3D positions. Secondly, to fit the video data's nature and overcome the inefficiency of next-token decoding, we adopt a parallel and mask-based discrete diffusion with the intra-frame bidirectional and inter-frame causal attention masks. Based on this attention mask, we uncover the frame‑wise loss imbalance issue caused by spatial information redundancy and propose Autoregressive Discrete Diffusion Forcing, which introduces temporal tube masking during training with a compatible inference‑time masking policy to avoid quality degradation. Despite using only 48 GPUs for pre-training, limited data and a discrete tokenizer, Lumos-1 achieves results surpassing those of Show-o2 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V.

Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction consistency. Recent autoregressive diffusion models enable long-horizon generation through KV cache reuse, yet suffer from two fundamental challenges: failure to preserve long-range interactions due to sliding-window KV cache and error accumulation that progressively degrades generation quality over time. To address these issues, we propose BIFE, a framework that introduces a semantic sparse KV cache for retrieval-based long-range conditioning and a Block Forcing training strategy to enforce cross-block consistency. Together, these designs preserve historical interactions while mitigating drift, enabling stable and coherent minute-long video generation. We also introduce InterVBench, a minute-long video benchmark with fine-grained block-level annotations and Video Drift Error metrics. Extensive experiments on InterVBench and VBench-Long demonstrate that BIFE achieves state-of-the-art performance, including a 22.2

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive sampling steps required. While advancements have been made in expediting the sampling process, the underlying architectural inefficiencies within DiT remain underexplored. We introduce SparseDiT, a novel framework that implements token sparsification across spatial and temporal dimensions to enhance computational efficiency while preserving generative quality. Spatially, SparseDiT employs a tri-segment architecture that allocates token density based on feature requirements at each layer: Poolingformer in the bottom layers for efficient global feature extraction, Sparse-Dense Token Modules (SDTM) in the middle layers to balance global context with local detail, and dense tokens in the top layers to refine high-frequency details. Temporally, SparseDiT dynamically modulates token density across denoising stages, progressively increasing token count as finer details emerge in later timesteps. This synergy between SparseDiT’s spatially adaptive architecture and its temporal pruning strategy enables a unified framework that balances efficiency and fidelity throughout the generation process. Our experiments demonstrate SparseDiT’s effectiveness, achieving a 55\% reduction in FLOPs and a 175\% improvement in inference speed on DiT-XL with similar FID score on 512$\times$512 ImageNet, a 56\% reduction in FLOPs across video generation datasets, and a 69\% improvement in inference speed on PixArt-$\alpha$ on text-to-image generation task with a 0.24 FID score decrease. SparseDiT provides a scalable solution for high-quality diffusion-based generation compatible with sampling optimization techniques. Code is available at https://github.com/changsn/SparseDiT.

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures, depend on bulky external text encoders, or incur prohibitive latency due to next-token decoding. In this paper, we introduce Lumos-1, an LLM-based unified model for AR video generation with efficient discrete diffusion. Firstly, to fit videos with LLMs, we identify that 1D RoPE is ill-suited for visual spatiotemporal correlation modeling, and while demonstrated to be useful, naive 3D RoPE exhibits imbalanced frequency spectra. Therefore, we propose MM-RoPE, which preserves the original textual RoPE while seamlessly accommodating video data with comprehensive frequency spectra and scaled 3D positions. Secondly, to fit the video data's nature and overcome the inefficiency of next-token decoding, we adopt a parallel and mask-based discrete diffusion with the intra-frame bidirectional and inter-frame causal attention masks. Based on this attention mask, we uncover the frame-wise loss imbalance issue caused by spatial information redundancy and propose Autoregressive Discrete Diffusion Forcing, which introduces temporal tube masking during training with a compatible inference-time masking policy to avoid quality degradation. Despite using only 48 GPUs for pre-training and fine-tuning, limited data and a discrete tokenizer, Lumos-1 achieves results surpassing those of Show-o2 on GenEval, COSMOS-Video2World on VBench-I2V, and OpenSoraPlan on VBench-T2V. Code and models are available at https://github.com/alibaba-damo-academy/Lumos.

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adaptor) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths. Specifically, we equivalently transform the traditional cascade of multi-head self-attention (MSA) and feed-forward network (FFN) into three parallel paths in each transformer layer. Then, we utilize the identity connection in our new transformer form and further transform the ViT into an explicit multi-path ensemble network. From the new perspective, these paths perform two functions: the first is to provide the feature for the classifier directly, and the second is to provide the lower-level feature representation for subsequent longer paths. We investigate the influence of each path for the final prediction and discover that some paths even pull down the performance. Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and re-weight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths. We also demonstrate that our path combination strategies can help ViTs go deeper and act as high-pass filters to filter out partial low-frequency signals. To further enhance the representation of paths served for subsequent paths, self-distillation is applied to transfer knowledge from the long paths to the short paths. This work calls for more future research to explain and design ViTs from new perspectives.

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecovery) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone.

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecover) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone.

Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. However, such two-stage methods are generally with low efficiency. We observe that directly unifying detection and action recognition normally suffers from (i) inferior learning due to different desired properties of context representation for detection and action recognition; (ii) optimization difficulty with insufficient training data. In this work, we present a decoupled one-stage network dubbed DOAD, to mitigate above issues and improve the efficiency for spatio-temporal action detection. To achieve it, we decouple detection and action recognition into two branches. Specifically, one branch focuses on detection representation for actor detection, and the other one for action recognition. For the action branch, we design a transformer-based module (TransPC) to model pairwise relationships between people and context. Different from commonly used vector-based dot product in self-attention, it is built upon a novel matrix-based key and value for Hadamard attention to model person-context information. It not only exploits relationships between person pairs but also takes into account context and relative position information. The results on AVA and UCF101-24 datasets show that our method is competitive with two-stage state-of-the-art methods with significant efficiency improvement.

We consider weakly-supervised video anomaly detection in this work. This task aims to learn to localize video frames containing anomaly events with only binary video-level annotation, i.e., anomaly vs. normal. Traditional approaches usually formulate it as a multiple instance learning problem, which ignore the intrinsic data imbalance issue that positive samples are very scarce compared to negative ones. In this paper, we focus on addressing this issue to boost detection performance further. We develop a new light-weight anomaly detection model that fully utilizes enough normal videos to train a classifier with a good discriminative ability for normal videos, and we employ it to improve the selectivity for anomalous segments and filter out normal segments. Specifically, in addition to boosting anomalous prediction, a novel contrastive attention module additionally produces a converted normal feature from anomalous video to refined anomalous predictions by maximizing the classifier making a mistake. Moreover, to remove the stubborn normal segments selected by the attention module, we also design an attention consistency loss to employ the classifier with high confidence for normal features to guide the attention module. Extensive experiments on two large-scale datasets, UCF-Crime, ShanghaiTech and XD-Violence, clearly demonstrate that our model largely improves frame-level AUC over the state-of-the-art. Code is released at https://github.com/changsn/Contrastive-Attention-for-Video-Anomaly-Detection.

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising performance. A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies. However, since the current dense self-attention uses all image patches (tokens) to compute attention matrix, it may neglect locality of images patches and involve noisy tokens (e.g., clutter background and occlusion), leading to a slow training process and potential degradation of performance. To address these problems, we propose the k-NN attention for boosting vision transformers. Specifically, instead of involving all the tokens for attention matrix calculation, we only select the top-k similar tokens from the keys for each query to compute the attention map. The proposed k-NN attention naturally inherits the local bias of CNNs without introducing convolutional operations, as nearby tokens tend to be more similar than others. In addition, the k-NN attention allows for the exploration of long range correlation and at the same time filters out irrelevant tokens by choosing the most similar tokens from the entire image. Despite its simplicity, we verify, both theoretically and empirically, that k-NN attention is powerful in speeding up training and distilling noise from input tokens. Extensive experiments are conducted by using 11 different vision transformer architectures to verify that the proposed k-NN attention can work with any existing transformer architectures to improve its prediction performance. The codes are available at https://github.com/damo-cv/KVT .

Temporal action proposal generation (TAPG) is a fundamental and challenging task in media interpretation and video understanding, especially in temporal action detection. Most previous works focus on capturing the local temporal context and can well locate simple action instances with clean frames and clear boundaries. However, they generally fail in complicated scenarios where interested actions involve irrelevant frames and background clutters, and the local temporal context becomes less effective. To deal with these problems, we present an augmented transformer with adaptive graph network (ATAG) to exploit both long-range and local temporal contexts for TAPG. Specifically, we enhance the vanilla transformer by equipping a snippet actionness loss and a front block, dubbed augmented transformer, and it improves the abilities of capturing long-range dependencies and learning robust feature for noisy action instances. Moreover, an adaptive graph convolutional network (GCN) is proposed to build local temporal context by mining the position information and difference between adjacent features. The features from the two modules carry rich semantic information of the video, and are fused for effective sequential proposal generation. Extensive experiments are conducted on two challenging datasets, THUMOS14 and ActivityNet1.3, and the results demonstrate that our method outperforms state-of-the-art TAPG methods. Our code will be released soon.

Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes. In this paper, we focus on improving spatio-temporal action recognition by fully-utilizing the information of scenes and collecting new data. A top-down strategy is used to overcome the limitations. Specifically, we adopt a strong human detector to detect the spatial location of each frame. We then apply action recognition models to learn the spatio-temporal information from video frames on both the HIE dataset and new data with diverse scenes from the internet, which can improve the generalization ability of our model. Besides, the scenes information is extracted by the semantic segmentation model to assistant the process. As a result, our method achieved an average 26.05 wf\_mAP (ranking 1st place in the ACM MM grand challenge 2020: Human in Events).

This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events[13]; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events. Remarkable progress has been made in multi-pose training in recent years. However, how to track the human pose in crowded and complex environments has not been well addressed. We formulate the problem as several subproblems to be solved. First, we use a multi-object tracking method to assign human ID to each bounding box generated by the detection model. After that, a pose is generated to each bounding box with ID. At last, optical flow is used to take advantage of the temporal information in the videos and generate the final pose tracking result.