Qiuyu Wang

Haobo Li, Yanhong Zeng, Yunhong Lu et al.

We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation but suffer from motion collapse and training instability, resulting in static videos. AAD-1 addresses these challenges through two key designs in architecture and training strategy. Our key architectural insight is to break the symmetry between generator and discriminator. While the generator remains causal to preserve autoregressive sampling capability, the discriminator attends bidirectionally over the full spatiotemporal context and produces a single holistic realism score for the entire video sequence. This asymmetric design enables the discriminator to effectively detect global temporal failures and long-range drift that cause motion collapse in autoregressive generation. To stabilize training, we introduce a phased strategy that first uses distribution matching to bootstrap a stable one-step generator, providing a warm-up phase that brings the student distribution closer to the teacher before adversarial distillation begins. Extensive experiments on VBench demonstrate that AAD-1 achieves state-of-the-art performance in one-step autoregressive video generation.

Qiuyu Wang, Zifan Shi, Kecheng Zheng et al.

Despite the rapid advance of 3D-aware image synthesis, existing studies usually adopt a mixture of techniques and tricks, leaving it unclear how each part contributes to the final performance in terms of generality. Following the most popular and effective paradigm in this field, which incorporates a neural radiance field (NeRF) into the generator of a generative adversarial network (GAN), we build a well-structured codebase, dubbed Carver, through modularizing the generation process. Such a design allows researchers to develop and replace each module independently, and hence offers an opportunity to fairly compare various approaches and recognize their contributions from the module perspective. The reproduction of a range of cutting-edge algorithms demonstrates the availability of our modularized codebase. We also perform a variety of in-depth analyses, such as the comparison across different types of point feature, the necessity of the tailing upsampler in the generator, the reliance on the camera pose prior, etc., which deepen our understanding of existing methods and point out some further directions of the research work. We release code and models at https://github.com/qiuyu96/Carver to facilitate the development and evaluation of this field.

Robbyant Team, Zelin Gao, Qiuyu Wang et al.

We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning.

Hao Ouyang, Qiuyu Wang, Yuxi Xiao et al.

We present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis. Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline. We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e.g., the object shape) from the video. With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field. We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training. More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog. Project page can be found at https://qiuyu96.github.io/CoDeF/.

Yu Hao, Qiuyu Wang, Cheng Yang et al.

Large language models (LLMs) facilitate the development of autonomous agents. As a core component of such agents, task planning aims to decompose complex natural language requests into concrete, solvable sub-tasks. Since LLM-generated plans are frequently prone to hallucinations and sensitive to long-context prom-pts, recent research has introduced plan verifiers to identify and correct potential flaws. However, most existing approaches still rely on an LLM as the verifier via additional prompting for plan review or self-reflection. LLM-based verifiers can be misled by plausible narration and struggle to detect failures caused by structural relations across steps, such as type mismatches, missing intermediates, or broken dependencies. To address these limitations, we propose a graph-based verifier for LLM task planning. Specifically, the proposed method has four major components: Firstly, we represent a plan as a directed graph with enriched attributes, where nodes denote sub-tasks and edges encode execution order and dependency constraints. Secondly, a graph neural network (GNN) then performs structural evaluation and diagnosis, producing a graph-level plausibility score for plan acceptance as well as node/edge-level risk scores to localize erroneous regions. Thirdly, we construct controllable perturbations from ground truth plan graphs, and automatically generate training data with fine-grained annotations. Finally, guided by the feedback from our GNN verifier, we enable an LLM to conduct local edits (e.g., tool replacement or insertion) to correct the plan when the graph-level score is insufficient. Extensive experiments across diverse datasets, backbone LLMs, and planners demonstrate that our GNNVerifier achieves significant gains in improving plan quality. Our data and code is available at https://github.com/BUPT-GAMMA/GNNVerifier.

Yunhong Lu, Yanhong Zeng, Haobo Li et al.

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain attention performance and reduce error accumulation. However, video frames become overly dependent on these static tokens, resulting in copied initial frames and diminished motion dynamics. To address this, we introduce Reward Forcing, a novel framework with two key designs. First, we propose EMA-Sink, which maintains fixed-size tokens initialized from initial frames and continuously updated by fusing evicted tokens via exponential moving average as they exit the sliding window. Without additional computation cost, EMA-Sink tokens capture both long-term context and recent dynamics, preventing initial frame copying while maintaining long-horizon consistency. Second, to better distill motion dynamics from teacher models, we propose a novel Rewarded Distribution Matching Distillation (Re-DMD). Vanilla distribution matching treats every training sample equally, limiting the model's ability to prioritize dynamic content. Instead, Re-DMD biases the model's output distribution toward high-reward regions by prioritizing samples with greater dynamics rated by a vision-language model. Re-DMD significantly enhances motion quality while preserving data fidelity. We include both quantitative and qualitative experiments to show that Reward Forcing achieves state-of-the-art performance on standard benchmarks while enabling high-quality streaming video generation at 23.1 FPS on a single H100 GPU.

Hanlin Wang, Hao Ouyang, Qiuyu Wang et al.

The intuitive nature of drag-based interaction has led to its growing adoption for controlling object trajectories in image-to-video synthesis. Still, existing methods that perform dragging in the 2D space usually face ambiguity when handling out-of-plane movements. In this work, we augment the interaction with a new dimension, i.e., the depth dimension, such that users are allowed to assign a relative depth for each point on the trajectory. That way, our new interaction paradigm not only inherits the convenience from 2D dragging, but facilitates trajectory control in the 3D space, broadening the scope of creativity. We propose a pioneering method for 3D trajectory control in image-to-video synthesis by abstracting object masks into a few cluster points. These points, accompanied by the depth information and the instance information, are finally fed into a video diffusion model as the control signal. Extensive experiments validate the effectiveness of our approach, dubbed LeviTor, in precisely manipulating the object movements when producing photo-realistic videos from static images. Our code is available at: https://github.com/ant-research/LeviTor.

Zhiheng Liu, Ka Leong Cheng, Qiuyu Wang et al.

Missing values remain a common challenge for depth data across its wide range of applications, stemming from various causes like incomplete data acquisition and perspective alteration. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our model features two notable strengths: (1) it demonstrates resilience to depth-deficient regions, providing reliable completion for both continuous areas and isolated points, and (2) it faithfully preserves scale consistency with the conditioned known depth when filling in missing values. Drawing on these advantages, our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion, exceeding current solutions in both numerical performance and visual quality. Our project page with source code is available at https://johanan528.github.io/depthlab_web/.

Yihao Meng, Hao Ouyang, Hanlin Wang et al.

The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our research focuses on reducing the labor costs in the above process by harnessing the potential of increasingly powerful generative AI. Using video diffusion models as the foundation, AniDoc emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations following the reference character specification. Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations (e.g., posture) between the reference character and each line art frame. In addition, our model could even automate the in-betweening process, such that users can easily create a temporally consistent animation by simply providing a character image as well as the start and end sketches. Our code is available at: https://yihao-meng.github.io/AniDoc_demo.

Zichen Liu, Yue Yu, Hao Ouyang et al.

We propose MagicQuill V2, a novel system that introduces a \textbf{layered composition} paradigm to generative image editing, bridging the gap between the semantic power of diffusion models and the granular control of traditional graphics software. While diffusion transformers excel at holistic generation, their use of singular, monolithic prompts fails to disentangle distinct user intentions for content, position, and appearance. To overcome this, our method deconstructs creative intent into a stack of controllable visual cues: a content layer for what to create, a spatial layer for where to place it, a structural layer for how it is shaped, and a color layer for its palette. Our technical contributions include a specialized data generation pipeline for context-aware content integration, a unified control module to process all visual cues, and a fine-tuned spatial branch for precise local editing, including object removal. Extensive experiments validate that this layered approach effectively resolves the user intention gap, granting creators direct, intuitive control over the generative process.

Hanlin Wang, Hao Ouyang, Qiuyu Wang et al.

We present WorldCanvas, a framework for promptable world events that enables rich, user-directed simulation by combining text, trajectories, and reference images. Unlike text-only approaches and existing trajectory-controlled image-to-video methods, our multimodal approach combines trajectories -- encoding motion, timing, and visibility -- with natural language for semantic intent and reference images for visual grounding of object identity, enabling the generation of coherent, controllable events that include multi-agent interactions, object entry/exit, reference-guided appearance and counterintuitive events. The resulting videos demonstrate not only temporal coherence but also emergent consistency, preserving object identity and scene despite temporary disappearance. By supporting expressive world events generation, WorldCanvas advances world models from passive predictors to interactive, user-shaped simulators. Our project page is available at: https://worldcanvas.github.io/.

Yihao Meng, Zichen Liu, Hao Ouyang et al.

Autoregressive video generation aims at real-time, open-ended synthesis. Yet, cinematic storytelling is not merely the endless extension of a single scene; it requires progressing through evolving events, viewpoint shifts, and discrete shot boundaries. Existing autoregressive models often struggle in this setting. Trained primarily for short-horizon continuation, they treat long sequences as extended single shots, inevitably suffering from motion stagnation and semantic drift during long rollouts. To bridge this gap, we introduce CausalCine, an interactive autoregressive framework that transforms multi-shot video generation into an online directing process. CausalCine generates causally across shot changes, accepts dynamic prompts on the fly, and reuses context without regenerating previous shots. To achieve this, we first train a causal base model on native multi-shot sequences to learn complex shot transitions prior to acceleration. We then propose Content-Aware Memory Routing (CAMR), which dynamically retrieves historical KV entries according to attention-based relevance scores rather than temporal proximity, preserving cross-shot coherence under bounded active memory. Finally, we distill the causal base model into a few-step generator for real-time interactive generation. Extensive experiments demonstrate that CausalCine significantly outperforms autoregressive baselines and approaches the capability of bidirectional models while unlocking the streaming interactivity of causal generation. Demo available at https://yihao-meng.github.io/CausalCine/

Yihao Meng, Hao Ouyang, Yue Yu et al.

State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/.

Zhiheng Liu, Hao Ouyang, Qiuyu Wang et al.

3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion.

Zichen Liu, Yue Yu, Hao Ouyang et al.

Image editing involves a variety of complex tasks and requires efficient and precise manipulation techniques. In this paper, we present MagicQuill, an integrated image editing system that enables swift actualization of creative ideas. Our system features a streamlined yet functionally robust interface, allowing for the articulation of editing operations (e.g., inserting elements, erasing objects, altering color) with minimal input. These interactions are monitored by a multimodal large language model (MLLM) to anticipate editing intentions in real time, bypassing the need for explicit prompt entry. Finally, we apply a powerful diffusion prior, enhanced by a carefully learned two-branch plug-in module, to process editing requests with precise control. Experimental results demonstrate the effectiveness of MagicQuill in achieving high-quality image edits. Please visit https://magic-quill.github.io to try out our system.

Wen Wang, Qiuyu Wang, Kecheng Zheng et al.

We propose Framer for interactive frame interpolation, which targets producing smoothly transitioning frames between two images as per user creativity. Concretely, besides taking the start and end frames as inputs, our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints. Such a design enjoys two clear benefits. First, incorporating human interaction mitigates the issue arising from numerous possibilities of transforming one image to another, and in turn enables finer control of local motions. Second, as the most basic form of interaction, keypoints help establish the correspondence across frames, enhancing the model to handle challenging cases (e.g., objects on the start and end frames are of different shapes and styles). It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and refine the trajectory automatically, to simplify the usage in practice. Extensive experimental results demonstrate the appealing performance of Framer on various applications, such as image morphing, time-lapse video generation, cartoon interpolation, etc. The code, the model, and the interface will be released to facilitate further research.

Wen Wang, Bozhen Fang, Chenchen Jing et al.

Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final output. Our work here reveals a critical phenomenon, temporal oscillation, where correct answers often emerge in the middle process, but are overwritten in later denoising steps. To address this issue, we introduce two complementary methods that exploit temporal consistency: 1) Temporal Self-Consistency Voting, a training-free, test-time decoding strategy that aggregates predictions across denoising steps to select the most consistent output; and 2) a post-training method termed Temporal Consistency Reinforcement, which uses Temporal Semantic Entropy (TSE), a measure of semantic stability across intermediate predictions, as a reward signal to encourage stable generations. Empirical results across multiple benchmarks demonstrate the effectiveness of our approach. Using the negative TSE reward alone, we observe a remarkable average improvement of 24.7% on the Countdown dataset over an existing dLLM. Combined with the accuracy reward, we achieve absolute gains of 2.0% on GSM8K, 4.3% on MATH500, 6.6% on SVAMP, and 25.3% on Countdown, respectively. Our findings underscore the untapped potential of temporal dynamics in dLLMs and offer two simple yet effective tools to harness them.

Qingyan Bai, Zifan Shi, Yinghao Xu et al.

This work presents 3DPE, a practical method that can efficiently edit a face image following given prompts, like reference images or text descriptions, in a 3D-aware manner. To this end, a lightweight module is distilled from a 3D portrait generator and a text-to-image model, which provide prior knowledge of face geometry and superior editing capability, respectively. Such a design brings two compelling advantages over existing approaches. First, our method achieves real-time editing with a feedforward network (i.e., ~0.04s per image), over 100x faster than the second competitor. Second, thanks to the powerful priors, our module could focus on the learning of editing-related variations, such that it manages to handle various types of editing simultaneously in the training phase and further supports fast adaptation to user-specified customized types of editing during inference (e.g., with ~5min fine-tuning per style).

Qingyan Bai, Hao Ouyang, Yinghao Xu et al.

As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.

Ka Leong Cheng, Qiuyu Wang, Zifan Shi et al.

Neural radiance fields, which represent a 3D scene as a color field and a density field, have demonstrated great progress in novel view synthesis yet are unfavorable for editing due to the implicitness. This work studies the task of efficient 3D editing, where we focus on editing speed and user interactivity. To this end, we propose to learn the color field as an explicit 2D appearance aggregation, also called canonical image, with which users can easily customize their 3D editing via 2D image processing. We complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture query. This field is initialized with a pseudo canonical camera model and optimized with offset regularity to ensure the naturalness of the canonical image. Extensive experiments on different datasets suggest that our representation, dubbed AGAP, well supports various ways of 3D editing (e.g., stylization, instance segmentation, and interactive drawing). Our approach demonstrates remarkable efficiency by being at least 20 times faster per edit compared to existing NeRF-based editing methods. Project page is available at https://felixcheng97.github.io/AGAP/.

Wen Wang, Kecheng Zheng, Qiuyu Wang et al.

We offer a new perspective on approaching the task of video generation. Instead of directly synthesizing a sequence of frames, we propose to render a video by warping one static image with a generative deformation field (GenDeF). Such a pipeline enjoys three appealing advantages. First, we can sufficiently reuse a well-trained image generator to synthesize the static image (also called canonical image), alleviating the difficulty in producing a video and thereby resulting in better visual quality. Second, we can easily convert a deformation field to optical flows, making it possible to apply explicit structural regularizations for motion modeling, leading to temporally consistent results. Third, the disentanglement between content and motion allows users to process a synthesized video through processing its corresponding static image without any tuning, facilitating many applications like video editing, keypoint tracking, and video segmentation. Both qualitative and quantitative results on three common video generation benchmarks demonstrate the superiority of our GenDeF method.

Kai Zhao, Zhiming Liu, Jiaqi Liu et al.

Epicardial adipose tissue (EAT) is a type of visceral fat that can secrete large amounts of adipokines to affect the myocardium and coronary arteries. EAT volume and density can be used as independent risk markers measurement of volume by noninvasive magnetic resonance images is the best method of assessing EAT. However, segmenting EAT is challenging due to the low contrast between EAT and pericardial effusion and the presence of motion artifacts. we propose a novel feature latent space multilevel supervision network (SPDNet) with uncertainty-driven and adversarial calibration learning to enhance segmentation for more accurate EAT volume estimation. The network first addresses the blurring of EAT edges due to the medical images in the open medical environments with low quality or out-of-distribution by modeling the uncertainty as a Gaussian distribution in the feature latent space, which using its Bayesian estimation as a regularization constraint to optimize SwinUNETR. Second, an adversarial training strategy is introduced to calibrate the segmentation feature map and consider the multi-scale feature differences between the uncertainty-guided predictive segmentation and the ground truth segmentation, synthesizing the multi-scale adversarial loss directly improves the ability to discriminate the similarity between organizations. Experiments on both the cardiac public MRI dataset (ACDC) and the real-world clinical cohort EAT dataset show that the proposed network outperforms mainstream models, validating that uncertainty-driven and adversarial calibration learning can be used to provide additional information for modeling multi-scale ambiguities.

Qingyan Bai, Qiuyu Wang, Hao Ouyang et al.

Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Ditto-1M with a curriculum learning strategy. The results demonstrate superior instruction-following ability and establish a new state-of-the-art in instruction-based video editing.

Yue Ma, Qingyan Bai, Hao Ouyang et al.

We introduce Calligrapher, a novel diffusion-based framework that innovatively integrates advanced text customization with artistic typography for digital calligraphy and design applications. Addressing the challenges of precise style control and data dependency in typographic customization, our framework incorporates three key technical contributions. First, we develop a self-distillation mechanism that leverages the pre-trained text-to-image generative model itself alongside the large language model to automatically construct a style-centric typography benchmark. Second, we introduce a localized style injection framework via a trainable style encoder, which comprises both Qformer and linear layers, to extract robust style features from reference images. An in-context generation mechanism is also employed to directly embed reference images into the denoising process, further enhancing the refined alignment of target styles. Extensive quantitative and qualitative evaluations across diverse fonts and design contexts confirm Calligrapher's accurate reproduction of intricate stylistic details and precise glyph positioning. By automating high-quality, visually consistent typography, Calligrapher surpasses traditional models, empowering creative practitioners in digital art, branding, and contextual typographic design.

Ming Qian, Bin Tan, Qiuyu Wang et al.

This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given any satellite image and specified camera positions or trajectories. We formulate to learn neural radiance field from paired images captured from satellite and street viewpoints, which comes to be a challenging learning problem due to the sparse-view natural and the extremely-large viewpoint changes between satellite and street-view images. We tackle the challenges based on a task-specific observation that street-view specific elements, including the sky and illumination effects are only visible in street-view panoramas, and present a novel approach Sat2Density++ to accomplish the goal of photo-realistic street-view panoramas rendering by modeling these street-view specific in neural networks. In the experiments, our method is testified on both urban and suburban scene datasets, demonstrating that Sat2Density++ is capable of rendering photorealistic street-view panoramas that are consistent across multiple views and faithful to the satellite image.