Quande Liu

Hongzheng Yang, Cheng Chen, Meirui Jiang et al.

Test-time adaptation (TTA) has increasingly been an important topic to efficiently tackle the cross-domain distribution shift at test time for medical images from different institutions. Previous TTA methods have a common limitation of using a fixed learning rate for all the test samples. Such a practice would be sub-optimal for TTA, because test data may arrive sequentially therefore the scale of distribution shift would change frequently. To address this problem, we propose a novel dynamic learning rate adjustment method for test-time adaptation, called DLTTA, which dynamically modulates the amount of weights update for each test image to account for the differences in their distribution shift. Specifically, our DLTTA is equipped with a memory bank based estimation scheme to effectively measure the discrepancy of a given test sample. Based on this estimated discrepancy, a dynamic learning rate adjustment strategy is then developed to achieve a suitable degree of adaptation for each test sample. The effectiveness and general applicability of our DLTTA is extensively demonstrated on three tasks including retinal optical coherence tomography (OCT) segmentation, histopathological image classification, and prostate 3D MRI segmentation. Our method achieves effective and fast test-time adaptation with consistent performance improvement over current state-of-the-art test-time adaptation methods. Code is available at: https://github.com/med-air/DLTTA.

Meirui Jiang, Hongzheng Yang, Xiaoxiao Li et al.

Despite recent progress on semi-supervised federated learning (FL) for medical image diagnosis, the problem of imbalanced class distributions among unlabeled clients is still unsolved for real-world use. In this paper, we study a practical yet challenging problem of class imbalanced semi-supervised FL (imFed-Semi), which allows all clients to have only unlabeled data while the server just has a small amount of labeled data. This imFed-Semi problem is addressed by a novel dynamic bank learning scheme, which improves client training by exploiting class proportion information. This scheme consists of two parts, i.e., the dynamic bank construction to distill various class proportions for each local client, and the sub-bank classification to impose the local model to learn different class proportions. We evaluate our approach on two public real-world medical datasets, including the intracranial hemorrhage diagnosis with 25,000 CT slices and skin lesion diagnosis with 10,015 dermoscopy images. The effectiveness of our method has been validated with significant performance improvements (7.61% and 4.69%) compared with the second-best on the accuracy, as well as comprehensive analytical studies. Code is available at https://github.com/med-air/imFedSemi.

Quande Liu, Cheng Chen, Qi Dou et al.

Domain generalization typically requires data from multiple source domains for model learning. However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. This paper studies the important yet challenging single domain generalization problem, in which a model is learned under the worst-case scenario with only one source domain to directly generalize to different unseen target domains. We present a novel approach to address this problem in medical image segmentation, which extracts and integrates the semantic shape prior information of segmentation that are invariant across domains and can be well-captured even from single domain data to facilitate segmentation under distribution shifts. Besides, a test-time adaptation strategy with dual-consistency regularization is further devised to promote dynamic incorporation of these shape priors under each unseen domain to improve model generalizability. Extensive experiments on two medical image segmentation tasks demonstrate the consistent improvements of our method across various unseen domains, as well as its superiority over state-of-the-art approaches in addressing domain generalization under the worst-case scenario.

Quande Liu, Youpeng Wen, Jianhua Han et al.

To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships between unseen and seen object categories, yet requiring large amounts of densely-annotated data with diverse base classes. In this paper, we propose a new open-world semantic segmentation pipeline that makes the first attempt to learn to segment semantic objects of various open-world categories without any efforts on dense annotations, by purely exploiting the image-caption data that naturally exist on the Internet. Our method, Vision-language-driven Semantic Segmentation (ViL-Seg), employs an image and a text encoder to generate visual and text embeddings for the image-caption data, with two core components that endow its segmentation ability: First, the image encoder is jointly trained with a vision-based contrasting and a cross-modal contrasting, which encourage the visual embeddings to preserve both fine-grained semantics and high-level category information that are crucial for the segmentation task. Furthermore, an online clustering head is devised over the image encoder, which allows to dynamically segment the visual embeddings into distinct semantic groups such that they can be classified by comparing with various text embeddings to complete our segmentation pipeline. Experiments show that without using any data with dense annotations, our method can directly segment objects of arbitrary categories, outperforming zero-shot segmentation methods that require data labeling on three benchmark datasets.

Xuanhua He, Quande Liu, Shengju Qian et al.

Generating high-fidelity human video with specified identities has attracted significant attention in the content generation community. However, existing techniques struggle to strike a balance between training efficiency and identity preservation, either requiring tedious case-by-case fine-tuning or usually missing identity details in the video generation process. In this study, we present \textbf{ID-Animator}, a zero-shot human-video generation approach that can perform personalized video generation given a single reference facial image without further training. ID-Animator inherits existing diffusion-based video generation backbones with a face adapter to encode the ID-relevant embeddings from learnable facial latent queries. To facilitate the extraction of identity information in video generation, we introduce an ID-oriented dataset construction pipeline that incorporates unified human attributes and action captioning techniques from a constructed facial image pool. Based on this pipeline, a random reference training strategy is further devised to precisely capture the ID-relevant embeddings with an ID-preserving loss, thus improving the fidelity and generalization capacity of our model for ID-specific video generation. Extensive experiments demonstrate the superiority of ID-Animator to generate personalized human videos over previous models. Moreover, our method is highly compatible with popular pre-trained T2V models like animatediff and various community backbone models, showing high extendability in real-world applications for video generation where identity preservation is highly desired. Our codes and checkpoints are released at https://github.com/ID-Animator/ID-Animator.

Kling Team, Jialu Chen, Yuanzheng Ci et al.

We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds.

Qinghe Wang, Xiaoyu Shi, Baolu Li et al.

Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these challenges, we propose MultiShotMaster, a framework for highly controllable multi-shot video generation. We extend a pretrained single-shot model by integrating two novel variants of RoPE. First, we introduce Multi-Shot Narrative RoPE, which applies explicit phase shift at shot transitions, enabling flexible shot arrangement while preserving the temporal narrative order. Second, we design Spatiotemporal Position-Aware RoPE to incorporate reference tokens and grounding signals, enabling spatiotemporal-grounded reference injection. In addition, to overcome data scarcity, we establish an automated data annotation pipeline to extract multi-shot videos, captions, cross-shot grounding signals and reference images. Our framework leverages the intrinsic architectural properties to support multi-shot video generation, featuring text-driven inter-shot consistency, customized subject with motion control, and background-driven customized scene. Both shot count and duration are flexibly configurable. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework.

Yawen Luo, Xiaoyu Shi, Junhao Zhuang et al.

Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on-the-fly frame generation. By reformulating the task as next-shot generation conditioned on historical context, ShotStream allows users to dynamically instruct ongoing narratives via streaming prompts. We achieve this by first fine-tuning a text-to-video model into a bidirectional next-shot generator, which is then distilled into a causal student via Distribution Matching Distillation. To overcome the challenges of inter-shot consistency and error accumulation inherent in autoregressive generation, we introduce two key innovations. First, a dual-cache memory mechanism preserves visual coherence: a global context cache retains conditional frames for inter-shot consistency, while a local context cache holds generated frames within the current shot for intra-shot consistency. And a RoPE discontinuity indicator is employed to explicitly distinguish the two caches to eliminate ambiguity. Second, to mitigate error accumulation, we propose a two-stage distillation strategy. This begins with intra-shot self-forcing conditioned on ground-truth historical shots and progressively extends to inter-shot self-forcing using self-generated histories, effectively bridging the train-test gap. Extensive experiments demonstrate that ShotStream generates coherent multi-shot videos with sub-second latency, achieving 16 FPS on a single GPU. It matches or exceeds the quality of slower bidirectional models, paving the way for real-time interactive storytelling. Training and inference code, as well as the models, are available on our

Donghao Zhou, Jingyu Lin, Guibao Shen et al.

Recent visual generative models enable story generation with consistent characters from text, but human-centric story generation faces additional challenges, such as maintaining detailed and diverse human face consistency and coordinating multiple characters across different images. This paper presents IdentityStory, a framework for human-centric story generation that ensures consistent character identity across multiple sequential images. By taming identity-preserving generators, the framework features two key components: Iterative Identity Discovery, which extracts cohesive character identities, and Re-denoising Identity Injection, which re-denoises images to inject identities while preserving desired context. Experiments on the ConsiStory-Human benchmark demonstrate that IdentityStory outperforms existing methods, particularly in face consistency, and supports multi-character combinations. The framework also shows strong potential for applications such as infinite-length story generation and dynamic character composition.

Zixuan Ye, Quande Liu, Cong Wei et al.

Recently, the introduction of Chain-of-Thought (CoT) has largely improved the generation ability of unified models. However, it is observed that the current thinking process during generation mainly focuses on the text consistency with the text prompt, ignoring the \textbf{visual context consistency} with the visual reference images during the multi-modal generation, e.g., multi-reference generation. The lack of such consistency results in the failure in maintaining key visual features (like human ID, object attribute, style). To this end, we integrate the visual context consistency into the reasoning of unified models, explicitly motivating the model to sustain such consistency by 1) Adaptive Visual Planning: generating structured visual check list to figure out the visual element of needed consistency keeping, and 2) Iterative Visual Correction: performing self-reflection with the guidance of check lists and refining the generated result in an iterative manner. To achieve this, we use supervised finetuning to teach the model how to plan the visual checking, conduct self-reflection and self-refinement, and use flow-GRPO to further enhance the visual consistency through a customized visual checking reward. The experiments show that our method outperforms both zero-shot unified models and those with text CoTs in multi-modal generation, demonstrating higher visual context consistency.

Wenze Liu, Weicai Ye, Minghong Cai et al.

Recent advancements in video generation have seen a shift towards unified, transformer-based foundation models that can handle multiple conditional inputs in-context. However, these models have primarily focused on modalities like text, images, and depth maps, while strictly time-synchronous signals like audio have been underexplored. This paper introduces In-Context Audio Control of video diffusion transformers (ICAC), a framework that investigates the integration of audio signals for speech-driven video generation within a unified full-attention architecture, akin to FullDiT. We systematically explore three distinct mechanisms for injecting audio conditions: standard cross-attention, 2D self-attention, and unified 3D self-attention. Our findings reveal that while 3D attention offers the highest potential for capturing spatio-temporal audio-visual correlations, it presents significant training challenges. To overcome this, we propose a Masked 3D Attention mechanism that constrains the attention pattern to enforce temporal alignment, enabling stable training and superior performance. Our experiments demonstrate that this approach achieves strong lip synchronization and video quality, conditioned on an audio stream and reference images.

Quande Liu, Hongzheng Yang, Qi Dou et al.

Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. However, despite existing FL algorithms only allow the supervised training setting, most hospitals in realistic usually cannot afford the intricate data labeling due to absence of budget or expertise. This paper studies a practical yet challenging FL problem, named \textit{Federated Semi-supervised Learning} (FSSL), which aims to learn a federated model by jointly utilizing the data from both labeled and unlabeled clients (i.e., hospitals). We present a novel approach for this problem, which improves over traditional consistency regularization mechanism with a new inter-client relation matching scheme. The proposed learning scheme explicitly connects the learning across labeled and unlabeled clients by aligning their extracted disease relationships, thereby mitigating the deficiency of task knowledge at unlabeled clients and promoting discriminative information from unlabeled samples. We validate our method on two large-scale medical image classification datasets. The effectiveness of our method has been demonstrated with the clear improvements over state-of-the-arts as well as the thorough ablation analysis on both tasks\footnote{Code will be made available at \url{https://github.com/liuquande/FedIRM}}.

Quande Liu, Cheng Chen, Jing Qin et al.

Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection. While at clinical deployment, the models trained in federated learning can still suffer from performance drop when applied to completely unseen hospitals outside the federation. In this paper, we point out and solve a novel problem setting of federated domain generalization (FedDG), which aims to learn a federated model from multiple distributed source domains such that it can directly generalize to unseen target domains. We present a novel approach, named as Episodic Learning in Continuous Frequency Space (ELCFS), for this problem by enabling each client to exploit multi-source data distributions under the challenging constraint of data decentralization. Our approach transmits the distribution information across clients in a privacy-protecting way through an effective continuous frequency space interpolation mechanism. With the transferred multi-source distributions, we further carefully design a boundary-oriented episodic learning paradigm to expose the local learning to domain distribution shifts and particularly meet the challenges of model generalization in medical image segmentation scenario. The effectiveness of our method is demonstrated with superior performance over state-of-the-arts and in-depth ablation experiments on two medical image segmentation tasks. The code is available at "https://github.com/liuquande/FedDG-ELCFS".

Haoxuan Che, Xuanhua He, Quande Liu et al.

We introduce GameGen-X, the first diffusion transformer model specifically designed for both generating and interactively controlling open-world game videos. This model facilitates high-quality, open-domain generation by simulating an extensive array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, predicting and altering future content based on the current clip, thus allowing for gameplay simulation. To realize this vision, we first collected and built an Open-World Video Game Dataset from scratch. It is the first and largest dataset for open-world game video generation and control, which comprises over a million diverse gameplay video clips sampling from over 150 games with informative captions from GPT-4o. GameGen-X undergoes a two-stage training process, consisting of foundation model pre-training and instruction tuning. Firstly, the model was pre-trained via text-to-video generation and video continuation, endowing it with the capability for long-sequence, high-quality open-domain game video generation. Further, to achieve interactive controllability, we designed InstructNet to incorporate game-related multi-modal control signal experts. This allows the model to adjust latent representations based on user inputs, unifying character interaction and scene content control for the first time in video generation. During instruction tuning, only the InstructNet is updated while the pre-trained foundation model is frozen, enabling the integration of interactive controllability without loss of diversity and quality of generated video content.

Yuzhou Huang, Ziyang Yuan, Quande Liu et al.

Text-to-video generation has made remarkable advancements through diffusion models. However, Multi-Concept Video Customization (MCVC) remains a significant challenge. We identify two key challenges for this task: 1) the identity decoupling issue, where directly adopting existing customization methods inevitably mix identity attributes when handling multiple concepts simultaneously, and 2) the scarcity of high-quality video-entity pairs, which is crucial for training a model that can well represent and decouple various customized concepts in video generation. To address these challenges, we introduce ConceptMaster, a novel framework that effectively addresses the identity decoupling issues while maintaining concept fidelity in video customization. Specifically, we propose to learn decoupled multi-concept embeddings and inject them into diffusion models in a standalone manner, which effectively guarantees the quality of customized videos with multiple identities, even for highly similar visual concepts. To overcome the scarcity of high-quality MCVC data, we establish a data construction pipeline, which enables collection of high-quality multi-concept video-entity data pairs across diverse scenarios. A multi-concept video evaluation set is further devised to comprehensively validate our method from three dimensions, including concept fidelity, identity decoupling ability, and video generation quality, across six different concept composition scenarios. Extensive experiments demonstrate that ConceptMaster significantly outperforms previous methods for video customization tasks, showing great potential to generate personalized and semantically accurate content for video diffusion models.

Jiwen Yu, Jianhong Bai, Yiran Qin et al.

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we propose Context-as-Memory, which utilizes historical context as memory for video generation. It includes two simple yet effective designs: (1) storing context in frame format without additional post-processing; (2) conditioning by concatenating context and frames to be predicted along the frame dimension at the input, requiring no external control modules. Furthermore, considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module to select truly relevant context frames by determining FOV (Field of View) overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss. Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs, even generalizing effectively to open-domain scenarios not seen during training. The link of our project page is https://context-as-memory.github.io/.

Xuan Ju, Weicai Ye, Quande Liu et al.

Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation. Although adapter-based approaches (e.g., ControlNet) enable additional controls with minimal fine-tuning, they encounter challenges when integrating multiple conditions, including: branch conflicts between independently trained adapters, parameter redundancy leading to increased computational cost, and suboptimal performance compared to full fine-tuning. To address these challenges, we introduce FullDiT, a unified foundation model for video generation that seamlessly integrates multiple conditions via unified full-attention mechanisms. By fusing multi-task conditions into a unified sequence representation and leveraging the long-context learning ability of full self-attention to capture condition dynamics, FullDiT reduces parameter overhead, avoids conditions conflict, and shows scalability and emergent ability. We further introduce FullBench for multi-task video generation evaluation. Experiments demonstrate that FullDiT achieves state-of-the-art results, highlighting the efficacy of full-attention in complex multi-task video generation.

Jiwen Yu, Yiran Qin, Haoxuan Che et al.

Interactive Generative Video (IGV) has emerged as a crucial technology in response to the growing demand for high-quality, interactive video content across various domains. In this paper, we define IGV as a technology that combines generative capabilities to produce diverse high-quality video content with interactive features that enable user engagement through control signals and responsive feedback. We survey the current landscape of IGV applications, focusing on three major domains: 1) gaming, where IGV enables infinite exploration in virtual worlds; 2) embodied AI, where IGV serves as a physics-aware environment synthesizer for training agents in multimodal interaction with dynamically evolving scenes; and 3) autonomous driving, where IGV provides closed-loop simulation capabilities for safety-critical testing and validation. To guide future development, we propose a comprehensive framework that decomposes an ideal IGV system into five essential modules: Generation, Control, Memory, Dynamics, and Intelligence. Furthermore, we systematically analyze the technical challenges and future directions in realizing each component for an ideal IGV system, such as achieving real-time generation, enabling open-domain control, maintaining long-term coherence, simulating accurate physics, and integrating causal reasoning. We believe that this systematic analysis will facilitate future research and development in the field of IGV, ultimately advancing the technology toward more sophisticated and practical applications.

Zixuan Ye, Xuanhua He, Quande Liu et al.

Recent advances in text-to-video generation have sparked interest in generative video editing tasks. Previous methods often rely on task-specific architectures (e.g., additional adapter modules) or dedicated customizations (e.g., DDIM inversion), which limit the integration of versatile editing conditions and the unification of various editing tasks. In this paper, we introduce UNified In-Context Video Editing (UNIC), a simple yet effective framework that unifies diverse video editing tasks within a single model in an in-context manner. To achieve this unification, we represent the inputs of various video editing tasks as three types of tokens: the source video tokens, the noisy video latent, and the multi-modal conditioning tokens that vary according to the specific editing task. Based on this formulation, our key insight is to integrate these three types into a single consecutive token sequence and jointly model them using the native attention operations of DiT, thereby eliminating the need for task-specific adapter designs. Nevertheless, direct task unification under this framework is challenging, leading to severe token collisions and task confusion due to the varying video lengths and diverse condition modalities across tasks. To address these, we introduce task-aware RoPE to facilitate consistent temporal positional encoding, and condition bias that enables the model to clearly differentiate different editing tasks. This allows our approach to adaptively perform different video editing tasks by referring the source video and varying condition tokens "in context", and support flexible task composition. To validate our method, we construct a unified video editing benchmark containing six representative video editing tasks. Results demonstrate that our unified approach achieves superior performance on each task and exhibits emergent task composition abilities.

Jiwen Yu, Yiran Qin, Haoxuan Che et al.

Modern game development faces significant challenges in creativity and cost due to predetermined content in traditional game engines. Recent breakthroughs in video generation models, capable of synthesizing realistic and interactive virtual environments, present an opportunity to revolutionize game creation. In this position paper, we propose Interactive Generative Video (IGV) as the foundation for Generative Game Engines (GGE), enabling unlimited novel content generation in next-generation gaming. GGE leverages IGV's unique strengths in unlimited high-quality content synthesis, physics-aware world modeling, user-controlled interactivity, long-term memory capabilities, and causal reasoning. We present a comprehensive framework detailing GGE's core modules and a hierarchical maturity roadmap (L0-L4) to guide its evolution. Our work charts a new course for game development in the AI era, envisioning a future where AI-powered generative systems fundamentally reshape how games are created and experienced.

Xuanhua He, Quande Liu, Zixuan Ye et al.

Fine-grained and efficient controllability on video diffusion transformers has raised increasing desires for the applicability. Recently, In-context Conditioning emerged as a powerful paradigm for unified conditional video generation, which enables diverse controls by concatenating varying context conditioning signals with noisy video latents into a long unified token sequence and jointly processing them via full-attention, e.g., FullDiT. Despite their effectiveness, these methods face quadratic computation overhead as task complexity increases, hindering practical deployment. In this paper, we study the efficiency bottleneck neglected in original in-context conditioning video generation framework. We begin with systematic analysis to identify two key sources of the computation inefficiencies: the inherent redundancy within context condition tokens and the computational redundancy in context-latent interactions throughout the diffusion process. Based on these insights, we propose FullDiT2, an efficient in-context conditioning framework for general controllability in both video generation and editing tasks, which innovates from two key perspectives. Firstly, to address the token redundancy, FullDiT2 leverages a dynamic token selection mechanism to adaptively identify important context tokens, reducing the sequence length for unified full-attention. Additionally, a selective context caching mechanism is devised to minimize redundant interactions between condition tokens and video latents. Extensive experiments on six diverse conditional video editing and generation tasks demonstrate that FullDiT2 achieves significant computation reduction and 2-3 times speedup in averaged time cost per diffusion step, with minimal degradation or even higher performance in video generation quality. The project page is at \href{https://fulldit2.github.io/}{https://fulldit2.github.io/}.

Shengqiong Wu, Weicai Ye, Jiahao Wang et al.

To address the bottleneck of accurate user intent interpretation within the current video generation community, we present Any2Caption, a novel framework for controllable video generation under any condition. The key idea is to decouple various condition interpretation steps from the video synthesis step. By leveraging modern multimodal large language models (MLLMs), Any2Caption interprets diverse inputs--text, images, videos, and specialized cues such as region, motion, and camera poses--into dense, structured captions that offer backbone video generators with better guidance. We also introduce Any2CapIns, a large-scale dataset with 337K instances and 407K conditions for any-condition-to-caption instruction tuning. Comprehensive evaluations demonstrate significant improvements of our system in controllability and video quality across various aspects of existing video generation models. Project Page: https://sqwu.top/Any2Cap/

Cong Wei, Quande Liu, Zixuan Ye et al.

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design enables accurate interpretation of complex multimodal instructions while preserving visual consistency. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as green-screening characters or changing materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we will release our model and code.

Shengqiong Wu, Weicai Ye, Yuanxing Zhang et al.

Diffusion Transformers have significantly improved video fidelity and temporal coherence, however, practical controllability remains limited. Concise, ambiguous, and compositionally complex user inputs contrast with the detailed prompts used in training, yielding an intent-output mismatch. We propose ReaDe, a universal, model-agnostic interpreter that converts raw instructions into precise, actionable specifications for downstream video generators. ReaDe follows a reason-then-describe paradigm: it first analyzes the user request to identify core requirements and resolve ambiguities, then produces detailed guidance that enables faithful, controllable generation. We train ReaDe via a two-stage optimization: (i) reasoning-augmented supervision imparts analytic parsing with stepwise traces and dense captions, and (ii) a multi-dimensional reward assigner enables stable, feedback-driven refinement for natural-style captions. Experiments across single- and multi-condition scenarios show consistent gains in instruction fidelity, caption accuracy, and downstream video quality, with strong generalization to reasoning-intensive and unseen inputs. ReaDe offers a practical route to aligning controllable video generation with accurately interpreted user intent. Project Page: https://sqwu.top/ReaDe/.

Minghong Cai, Qiulin Wang, Zongli Ye et al.

We introduce the task of arbitrary spatio-temporal video completion, where a video is generated from arbitrary, user-specified patches placed at any spatial location and timestamp, akin to painting on a video canvas. This flexible formulation naturally unifies many existing controllable video generation tasks--including first-frame image-to-video, inpainting, extension, and interpolation--under a single, cohesive paradigm. Realizing this vision, however, faces a fundamental obstacle in modern latent video diffusion models: the temporal ambiguity introduced by causal VAEs, where multiple pixel frames are compressed into a single latent representation, making precise frame-level conditioning structurally difficult. We address this challenge with VideoCanvas, a novel framework that adapts the In-Context Conditioning (ICC) paradigm to this fine-grained control task with zero new parameters. We propose a hybrid conditioning strategy that decouples spatial and temporal control: spatial placement is handled via zero-padding, while temporal alignment is achieved through Temporal RoPE Interpolation, which assigns each condition a continuous fractional position within the latent sequence. This resolves the VAE's temporal ambiguity and enables pixel-frame-aware control on a frozen backbone. To evaluate this new capability, we develop VideoCanvasBench, the first benchmark for arbitrary spatio-temporal video completion, covering both intra-scene fidelity and inter-scene creativity. Experiments demonstrate that VideoCanvas significantly outperforms existing conditioning paradigms, establishing a new state of the art in flexible and unified video generation.

Shian Du, Menghan Xia, Chang Liu et al.

Cascaded video super-resolution has emerged as a promising technique for decoupling the computational burden associated with generating high-resolution videos using large foundation models. Existing studies, however, are largely confined to text-to-video tasks and fail to leverage additional generative conditions beyond text, which are crucial for ensuring fidelity in multi-modal video generation. We address this limitation by presenting UniMMVSR, the first unified generative video super-resolution framework to incorporate hybrid-modal conditions, including text, images, and videos. We conduct a comprehensive exploration of condition injection strategies, training schemes, and data mixture techniques within a latent video diffusion model. A key challenge was designing distinct data construction and condition utilization methods to enable the model to precisely utilize all condition types, given their varied correlations with the target video. Our experiments demonstrate that UniMMVSR significantly outperforms existing methods, producing videos with superior detail and a higher degree of conformity to multi-modal conditions. We also validate the feasibility of combining UniMMVSR with a base model to achieve multi-modal guided generation of 4K video, a feat previously unattainable with existing techniques.

Lin Liu, Quande Liu, Shengju Qian et al.

Video generation is a challenging yet pivotal task in various industries, such as gaming, e-commerce, and advertising. One significant unresolved aspect within T2V is the effective visualization of text within generated videos. Despite the progress achieved in Text-to-Video~(T2V) generation, current methods still cannot effectively visualize texts in videos directly, as they mainly focus on summarizing semantic scene information, understanding, and depicting actions. While recent advances in image-level visual text generation show promise, transitioning these techniques into the video domain faces problems, notably in preserving textual fidelity and motion coherence. In this paper, we propose an innovative approach termed Text-Animator for visual text video generation. Text-Animator contains a text embedding injection module to precisely depict the structures of visual text in generated videos. Besides, we develop a camera control module and a text refinement module to improve the stability of generated visual text by controlling the camera movement as well as the motion of visualized text. Quantitative and qualitative experimental results demonstrate the superiority of our approach to the accuracy of generated visual text over state-of-the-art video generation methods. The project page can be found at https://laulampaul.github.io/text-animator.html.

Cheng Chen, Quande Liu, Yueming Jin et al.

Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. However, in many real-world scenarios, the source data may not be accessible during the model adaptation in the target domain due to privacy issue. This paper studies the practical yet challenging source-free unsupervised domain adaptation problem, in which only an existing source model and the unlabeled target data are available for model adaptation. We present a novel denoised pseudo-labeling method for this problem, which effectively makes use of the source model and unlabeled target data to promote model self-adaptation from pseudo labels. Importantly, considering that the pseudo labels generated from source model are inevitably noisy due to domain shift, we further introduce two complementary pixel-level and class-level denoising schemes with uncertainty estimation and prototype estimation to reduce noisy pseudo labels and select reliable ones to enhance the pseudo-labeling efficacy. Experimental results on cross-domain fundus image segmentation show that without using any source images or altering source training, our approach achieves comparable or even higher performance than state-of-the-art source-dependent unsupervised domain adaptation methods.

Zhao Wang, Quande Liu, Qi Dou

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performances on both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

Quande Liu, Qi Dou, Pheng-Ann Heng

Model generalization capacity at domain shift (e.g., various imaging protocols and scanners) is crucial for deep learning methods in real-world clinical deployment. This paper tackles the challenging problem of domain generalization, i.e., learning a model from multi-domain source data such that it can directly generalize to an unseen target domain. We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation. Our learning scheme roots in the gradient-based meta-learning, by explicitly simulating domain shift with virtual meta-train and meta-test during training. Importantly, considering the deficiencies encountered when applying a segmentation model to unseen domains (i.e., incomplete shape and ambiguous boundary of the prediction masks), we further introduce two complementary loss objectives to enhance the meta-optimization, by particularly encouraging the shape compactness and shape smoothness of the segmentations under simulated domain shift. We evaluate our method on prostate MRI data from six different institutions with distribution shifts acquired from public datasets. Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.

Luyang Luo, Lequan Yu, Hao Chen et al.

Deep learning approaches have demonstrated remarkable progress in automatic Chest X-ray analysis. The data-driven feature of deep models requires training data to cover a large distribution. Therefore, it is substantial to integrate knowledge from multiple datasets, especially for medical images. However, learning a disease classification model with extra Chest X-ray (CXR) data is yet challenging. Recent researches have demonstrated that performance bottleneck exists in joint training on different CXR datasets, and few made efforts to address the obstacle. In this paper, we argue that incorporating an external CXR dataset leads to imperfect training data, which raises the challenges. Specifically, the imperfect data is in two folds: domain discrepancy, as the image appearances vary across datasets; and label discrepancy, as different datasets are partially labeled. To this end, we formulate the multi-label thoracic disease classification problem as weighted independent binary tasks according to the categories. For common categories shared across domains, we adopt task-specific adversarial training to alleviate the feature differences. For categories existing in a single dataset, we present uncertainty-aware temporal ensembling of model predictions to mine the information from the missing labels further. In this way, our framework simultaneously models and tackles the domain and label discrepancies, enabling superior knowledge mining ability. We conduct extensive experiments on three datasets with more than 360,000 Chest X-ray images. Our method outperforms other competing models and sets state-of-the-art performance on the official NIH test set with 0.8349 AUC, demonstrating its effectiveness of utilizing the external dataset to improve the internal classification.

Quande Liu, Lequan Yu, Luyang Luo et al.

Training deep neural networks usually requires a large amount of labeled data to obtain good performance. However, in medical image analysis, obtaining high-quality labels for the data is laborious and expensive, as accurately annotating medical images demands expertise knowledge of the clinicians. In this paper, we present a novel relation-driven semi-supervised framework for medical image classification. It is a consistency-based method which exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations, and leverages a self-ensembling model to produce high-quality consistency targets for the unlabeled data. Considering that human diagnosis often refers to previous analogous cases to make reliable decisions, we introduce a novel sample relation consistency (SRC) paradigm to effectively exploit unlabeled data by modeling the relationship information among different samples. Superior to existing consistency-based methods which simply enforce consistency of individual predictions, our framework explicitly enforces the consistency of semantic relation among different samples under perturbations, encouraging the model to explore extra semantic information from unlabeled data. We have conducted extensive experiments to evaluate our method on two public benchmark medical image classification datasets, i.e.,skin lesion diagnosis with ISIC 2018 challenge and thorax disease classification with ChestX-ray14. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.

Quande Liu, Qi Dou, Lequan Yu et al.

Automated prostate segmentation in MRI is highly demanded for computer-assisted diagnosis. Recently, a variety of deep learning methods have achieved remarkable progress in this task, usually relying on large amounts of training data. Due to the nature of scarcity for medical images, it is important to effectively aggregate data from multiple sites for robust model training, to alleviate the insufficiency of single-site samples. However, the prostate MRIs from different sites present heterogeneity due to the differences in scanners and imaging protocols, raising challenges for effective ways of aggregating multi-site data for network training. In this paper, we propose a novel multi-site network (MS-Net) for improving prostate segmentation by learning robust representations, leveraging multiple sources of data. To compensate for the inter-site heterogeneity of different MRI datasets, we develop Domain-Specific Batch Normalization layers in the network backbone, enabling the network to estimate statistics and perform feature normalization for each site separately. Considering the difficulty of capturing the shared knowledge from multiple datasets, a novel learning paradigm, i.e., Multi-site-guided Knowledge Transfer, is proposed to enhance the kernels to extract more generic representations from multi-site data. Extensive experiments on three heterogeneous prostate MRI datasets demonstrate that our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning.

Qi Dou, Quande Liu, Pheng Ann Heng et al.

Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI, and only employ modality-specific internal normalization layers which compute respective statistics. To effectively train such a highly compact model, we introduce a novel loss term inspired by knowledge distillation, by explicitly constraining the KL-divergence of our derived prediction distributions between modalities. We have extensively validated our approach on two multi-class segmentation problems: i) cardiac structure segmentation, and ii) abdominal organ segmentation. Different network settings, i.e., 2D dilated network and 3D U-net, are utilized to investigate our method's general efficacy. Experimental results on both tasks demonstrate that our novel multi-modal learning scheme consistently outperforms single-modal training and previous multi-modal approaches.