arXiv subjects

Fan Bao

Publications and source records attributed to Fan Bao.

At least 19 recordsLinked to original sources

arXiv2026

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

cs.CV↗

arXiv2026

Motus2: A Self-Evolving General World Model for Dexterous Manipulation

General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output head to a world simulator, without coupling them into a closed decision-and-learning loop for policy improvement. We present Motus2, a self-evolving general world model for dexterous manipulation. Motus2 advances world modeling through model scaling and data scaling. For model scaling, a single model with shared weights exposes three control interfaces: a policy (world-action model), a simulator (action-conditioned world model), and an evaluator (value model). The policy proposes candidate action chunks, the simulator predicts their visual consequences, and the evaluator assesses the predicted outcomes. Their coupling forms a closed decision-and-learning loop for policy improvement. This formulation uses curated expert demonstrations for action learning, while failed and suboptimal interactions provide valuable evidence for dynamics modeling and value learning. For data scaling, Motus2 progresses from large-scale monocular egocentric data to synchronized stereo egocentric data, followed by robot-domain adaptation with robot trajectories and supplementary human-robot alignment data. Motus2 further studies global-autoregressive and hybrid-memory extensions of its sliding-window context, adds tactile feedback for contact-aware control, and is instantiated on a fully biomimetic platform with stereo vision, dual arms, dual dexterous hands, and tactile sensing. Together, egocentric data scaling and closed-loop general world model scaling provide a general path toward self-evolving dexterous manipulation.

cs.RO↗

arXiv2026

Vidu S1: A Real-Time Interactive Video Generation Model

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.

cs.CV↗

arXiv2026

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable, causal, and low-latency rollout, which in practice demands a full pipeline spanning data construction, controllable fine-tuning, autoregressive training, few-step distillation, and streaming inference. In this work, we present minWM, a full-stack open-source framework for building real-time interactive video world models. minWM provides an end-to-end pipeline that converts existing bidirectional T2V/TI2V video foundation models into camera-controllable few-step autoregressive world models. Specifically, minWM first fine-tunes a bidirectional video diffusion model with camera control, and then applies the Causal Forcing / Causal Forcing++ pipeline, including AR diffusion training, causal ODE or causal consistency distillation, and asymmetric DMD, to distill it into a few-step autoregressive generator for low-latency rollout. The framework is modular and architecture-extensible: we instantiate it on representative open backbones, including Wan2.1-T2V-1.3B and HY1.5-TI2V-8B, covering both cross-attention-based condition injection and MMDiT-style architectures. minWM also supports adapting existing video world models, such as HY-WorldPlay, to new data distributions, training recipes, and latency targets. Beyond releasing runnable scripts, checkpoints, documentation, and inference code, we provide practical ablations on camera trajectory quality, controllability training steps, and minimal batch-size requirements. We hope minWM serves as a reproducible and extensible recipe for building and adapting real-time interactive video world models. Project Page: [https://github.com/shengshu-ai/minWM](https://github.com/shengshu-ai/minWM)

cs.CV↗

arXiv2026

Motubrain: An Advanced World Action Model for Robot Control

Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present Motubrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, Motubrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, Motubrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.

cs.RO↗

arXiv2025

DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap

Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video, and audio embeddings via a single contrastive loss. However, these methods often overlook the bidirectional interactions and inherent noises present in each modality, which can crucially impact the quality and efficacy of cross-modal integration. To address this limitation, we introduce DiffGAP, a novel approach incorporating a lightweight generative module within the contrastive space. Specifically, our DiffGAP employs a bidirectional diffusion process tailored to bridge the cross-modal gap more effectively. This involves a denoising process on text and video embeddings conditioned on audio embeddings and vice versa, thus facilitating a more nuanced and robust cross-modal interaction. Our experimental results on VGGSound and AudioCaps datasets demonstrate that DiffGAP significantly improves performance in video/text-audio generation and retrieval tasks, confirming its effectiveness in enhancing cross-modal understanding and generation capabilities.

cs.CV↗

arXiv2025

Elucidating the Preconditioning in Consistency Distillation

Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward on the probability flow (PF) ordinary differential equation (ODE) trajectory determined by the teacher model. Preconditioning is a vital technique for stabilizing consistency distillation, by linear combining the input data and the network output with pre-defined coefficients as the consistency function. It imposes the boundary condition of consistency functions without restricting the form and expressiveness of the neural network. However, previous preconditionings are hand-crafted and may be suboptimal choices. In this work, we offer the first theoretical insights into the preconditioning in consistency distillation, by elucidating its design criteria and the connection to the teacher ODE trajectory. Based on these analyses, we further propose a principled way dubbed \textit{Analytic-Precond} to analytically optimize the preconditioning according to the consistency gap (defined as the gap between the teacher denoiser and the optimal student denoiser) on a generalized teacher ODE. We demonstrate that Analytic-Precond can facilitate the learning of trajectory jumpers, enhance the alignment of the student trajectory with the teacher's, and achieve $2\times$ to $3\times$ training acceleration of consistency trajectory models in multi-step generation across various datasets.

cs.LG↗

arXiv2025

Bridge-SR: Schr\"odinger Bridge for Efficient SR

Speech super-resolution (SR), which generates a waveform at a higher sampling rate from its low-resolution version, is a long-standing critical task in speech restoration. Previous works have explored speech SR in different data spaces, but these methods either require additional compression networks or exhibit limited synthesis quality and inference speed. Motivated by recent advances in probabilistic generative models, we present Bridge-SR, a novel and efficient any-to-48kHz SR system in the speech waveform domain. Using tractable Schr\"odinger Bridge models, we leverage the observed low-resolution waveform as a prior, which is intrinsically informative for the high-resolution target. By optimizing a lightweight network to learn the score functions from the prior to the target, we achieve efficient waveform SR through a data-to-data generation process that fully exploits the instructive content contained in the low-resolution observation. Furthermore, we identify the importance of the noise schedule, data scaling, and auxiliary loss functions, which further improve the SR quality of bridge-based systems. The experiments conducted on the benchmark dataset VCTK demonstrate the efficiency of our system: (1) in terms of sample quality, Bridge-SR outperforms several strong baseline methods under different SR settings, using a lightweight network backbone (1.7M); (2) in terms of inference speed, our 4-step synthesis achieves better performance than the 8-step conditional diffusion counterpart (LSD: 0.911 vs 0.927). Demo at https://bridge-sr.github.io.

cs.SD↗

arXiv2024

Consistency Diffusion Bridge Models

Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of generative modeling that builds stochastic processes between fixed data endpoints based on a reference diffusion process, have achieved empirical success across tasks with coupled data distribution, such as image-to-image translation. However, DDBM's sampling process typically requires hundreds of network evaluations to achieve decent performance, which may impede their practical deployment due to high computational demands. In this work, inspired by the recent advance of consistency models in DMs, we tackle this problem by learning the consistency function of the probability-flow ordinary differential equation (PF-ODE) of DDBMs, which directly predicts the solution at a starting step given any point on the ODE trajectory. Based on a dedicated general-form ODE solver, we propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices. Experimental results show that our proposed method could sample $4\times$ to $50\times$ faster than the base DDBM and produce better visual quality given the same step in various tasks with pixel resolution ranging from $64 \times 64$ to $256 \times 256$, as well as supporting downstream tasks such as semantic interpolation in the data space.

cs.LG↗

arXiv2024

Diffusion Bridge Implicit Models

Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions given as endpoints. Despite their promising performance in tasks like image translation, DDBMs require a computationally intensive sampling process that involves the simulation of a (stochastic) differential equation through hundreds of network evaluations. In this work, we take the first step in fast sampling of DDBMs without extra training, motivated by the well-established recipes in diffusion models. We generalize DDBMs via a class of non-Markovian diffusion bridges defined on the discretized timesteps concerning sampling, which share the same marginal distributions and training objectives, give rise to generative processes ranging from stochastic to deterministic, and result in diffusion bridge implicit models (DBIMs). DBIMs are not only up to 25$\times$ faster than the vanilla sampler of DDBMs but also induce a novel, simple, and insightful form of ordinary differential equation (ODE) which inspires high-order numerical solvers. Moreover, DBIMs maintain the generation diversity in a distinguished way, by using a booting noise in the initial sampling step, which enables faithful encoding, reconstruction, and semantic interpolation in image translation tasks. Code is available at https://github.com/thu-ml/DiffusionBridge.

cs.LG↗

arXiv2024

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models

We introduce Vidu, a high-performance text-to-video generator that is capable of producing 1080p videos up to 16 seconds in a single generation. Vidu is a diffusion model with U-ViT as its backbone, which unlocks the scalability and the capability for handling long videos. Vidu exhibits strong coherence and dynamism, and is capable of generating both realistic and imaginative videos, as well as understanding some professional photography techniques, on par with Sora -- the most powerful reported text-to-video generator. Finally, we perform initial experiments on other controllable video generation, including canny-to-video generation, video prediction and subject-driven generation, which demonstrate promising results.

cs.CV↗

arXiv2023

Gaussian Mixture Solvers for Diffusion Models

Recently, diffusion models have achieved great success in generative tasks. Sampling from diffusion models is equivalent to solving the reverse diffusion stochastic differential equations (SDEs) or the corresponding probability flow ordinary differential equations (ODEs). In comparison, SDE-based solvers can generate samples of higher quality and are suited for image translation tasks like stroke-based synthesis. During inference, however, existing SDE-based solvers are severely constrained by the efficiency-effectiveness dilemma. Our investigation suggests that this is because the Gaussian assumption in the reverse transition kernel is frequently violated (even in the case of simple mixture data) given a limited number of discretization steps. To overcome this limitation, we introduce a novel class of SDE-based solvers called \emph{Gaussian Mixture Solvers (GMS)} for diffusion models. Our solver estimates the first three-order moments and optimizes the parameters of a Gaussian mixture transition kernel using generalized methods of moments in each step during sampling. Empirically, our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis in various diffusion models, which validates the motivation and effectiveness of GMS. Our code is available at https://github.com/Guohanzhong/GMS.

cs.LG↗

arXiv2023

ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond

This paper presents \emph{ControlVideo} for text-driven video editing -- generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions (such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating Low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing (e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous works achieved. The code is available at \href{https://github.com/thu-ml/controlvideo}{https://github.com/thu-ml/controlvideo} and the visualization results are available at \href{https://drive.google.com/file/d/1wEgc2io3UwmoC5vTPbkccFvTkwVqsZlK/view?usp=drive_link}{HERE}.

cs.CV↗

arXiv2023

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e., $7.5$). We further present various improvements in the design space for text-to-3D such as distillation time schedule and density initialization, which are orthogonal to the distillation algorithm yet not well explored. Our overall approach, dubbed ProlificDreamer, can generate high rendering resolution (i.e., $512\times512$) and high-fidelity NeRF with rich structure and complex effects (e.g., smoke and drops). Further, initialized from NeRF, meshes fine-tuned by VSD are meticulously detailed and photo-realistic. Project page and codes: https://ml.cs.tsinghua.edu.cn/prolificdreamer/

cs.LG↗

arXiv2023

A Closer Look at Parameter-Efficient Tuning in Diffusion Models

Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language processing, we investigate parameter-efficient tuning in large diffusion models by inserting small learnable modules (termed adapters). In particular, we decompose the design space of adapters into orthogonal factors -- the input position, the output position as well as the function form, and perform Analysis of Variance (ANOVA), a classical statistical approach for analyzing the correlation between discrete (design options) and continuous variables (evaluation metrics). Our analysis suggests that the input position of adapters is the critical factor influencing the performance of downstream tasks. Then, we carefully study the choice of the input position, and we find that putting the input position after the cross-attention block can lead to the best performance, validated by additional visualization analyses. Finally, we provide a recipe for parameter-efficient tuning in diffusion models, which is comparable if not superior to the fully fine-tuned baseline (e.g., DreamBooth) with only 0.75 \% extra parameters, across various customized tasks.

cs.CV↗

arXiv2023

One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale

This paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions relevant to a set of multi-modal data in one model. Our key insight is -- learning diffusion models for marginal, conditional, and joint distributions can be unified as predicting the noise in the perturbed data, where the perturbation levels (i.e. timesteps) can be different for different modalities. Inspired by the unified view, UniDiffuser learns all distributions simultaneously with a minimal modification to the original diffusion model -- perturbs data in all modalities instead of a single modality, inputs individual timesteps in different modalities, and predicts the noise of all modalities instead of a single modality. UniDiffuser is parameterized by a transformer for diffusion models to handle input types of different modalities. Implemented on large-scale paired image-text data, UniDiffuser is able to perform image, text, text-to-image, image-to-text, and image-text pair generation by setting proper timesteps without additional overhead. In particular, UniDiffuser is able to produce perceptually realistic samples in all tasks and its quantitative results (e.g., the FID and CLIP score) are not only superior to existing general-purpose models but also comparable to the bespoken models (e.g., Stable Diffusion and DALL-E 2) in representative tasks (e.g., text-to-image generation).

cs.LG↗

arXiv2023

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called dual pseudo training (DPT), built upon strong semi-supervised learners and diffusion models. DPT operates in three stages: training a classifier on partially labeled data to predict pseudo-labels; training a conditional generative model using these pseudo-labels to generate pseudo images; and retraining the classifier with a mix of real and pseudo images. Empirically, DPT consistently achieves SOTA performance of semi-supervised generation and classification across various settings. In particular, with one or two labels per class, DPT achieves a Fr\'echet Inception Distance (FID) score of 3.08 or 2.52 on ImageNet 256x256. Besides, DPT outperforms competitive semi-supervised baselines substantially on ImageNet classification tasks, achieving top-1 accuracies of 59.0 (+2.8), 69.5 (+3.0), and 74.4 (+2.0) with one, two, or five labels per class, respectively. Notably, our results demonstrate that diffusion can generate realistic images with only a few labels (e.g., <0.1%) and generative augmentation remains viable for semi-supervised classification. Our code is available at https://github.com/ML-GSAI/DPT.

cs.CV↗

arXiv2023

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

A large-scale deep model pre-trained on massive labeled or unlabeled data transfers well to downstream tasks. Linear evaluation freezes parameters in the pre-trained model and trains a linear classifier separately, which is efficient and attractive for transfer. However, little work has investigated the classifier in linear evaluation except for the default logistic regression. Inspired by the statistical efficiency of naive Bayes, the paper revisits the classical topic on discriminative vs. generative classifiers. Theoretically, the paper considers the surrogate loss instead of the zero-one loss in analyses and generalizes the classical results from binary cases to multiclass ones. We show that, under mild assumptions, multiclass naive Bayes requires $O(\log n)$ samples to approach its asymptotic error while the corresponding multiclass logistic regression requires $O(n)$ samples, where $n$ is the feature dimension. To establish it, we present a multiclass $\mathcal{H}$-consistency bound framework and an explicit bound for logistic loss, which are of independent interests. Simulation results on a mixture of Gaussian validate our theoretical findings. Experiments on various pre-trained deep vision models show that naive Bayes consistently converges faster as the number of data increases. Besides, naive Bayes shows promise in few-shot cases and we observe the "two regimes" phenomenon in pre-trained supervised models. Our code is available at https://github.com/ML-GSAI/Revisiting-Dis-vs-Gen-Classifiers.

cs.LG↗