论文检索

Computer Vision · Image and Video Generation

Wootaek Jeong, Junghyo Sohn, Jee Seok Yoon, Heung-Il Suk

Text-guided image editing requires more than prompt following—it demands a principled understanding of what to modify versus what to preserve. We investigate the internal guidance mechanism of diffusion models and reveal that the guidance signal follows a structured semantic hierarchy. We formalize this insight as the Semantic Scale Hypothesis: the magnitude of the guidance difference vector ($\Delta\boldsymbol{\epsilon}$) directly encodes the semantic scale of edits. Crucially, this phenomenon is theoretically grounded in Tweedie’s formula, which links score prediction to the variance of the underlying data distribution. Low-variance regions, such as objects, yield large-magnitude differences corresponding to structural edits, whereas high-variance regions, such as backgrounds, yield small-magnitude differences corresponding to stylistic adjustments. Building on this principle, we introduce Prism-Edit, a training-free, plug-and-play module that decomposes the guidance signal into semantic layers, enabling selective and interpretable control. Extensive experiments—spanning direct visualization of the semantic hierarchy, generalization across foundation models, and integration with state-of-the-art editors—demonstrate that Prism-Edit achieves precise, robust, and controllable editing. Our findings establish semantic scale as a foundational axis for understanding and advancing diffusion-based image editing.

Deep Learning · Algorithms

Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang

Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method.

Computer Vision · Image and Video Generation

Jiakui Hu, Zhengjian Yao, Lujia Jin, Yanye Lu

Universal image restoration is a critical task in low-level vision, requiring the model to remove various degradations from low-quality images to produce clean images with rich detail. The challenges lie in sampling the distribution of high-quality images and adjusting the outputs on the basis of the degradation. This paper presents a novel approach, Bridging Degradation discrimination and Generation (BDG), which aims to address these challenges concurrently. First, we propose the Multi-Angle and multi-Scale Gray Level Co-occurrence Matrix (MAS-GLCM) and demonstrate its effectiveness in performing fine-grained discrimination of degradation types and levels. Subsequently, we divide the diffusion training process into three distinct stages: generation, bridging, and restoration. The objective is to preserve the diffusion model's capability of restoring rich textures while simultaneously integrating the discriminative information from the MAS-GLCM into the restoration process. This enhances its proficiency in addressing multi-task and multi-degraded scenarios. Without changing the architecture, BDG achieves significant performance gains in all-in-one restoration and real-world super-resolution tasks, primarily evidenced by substantial improvements in fidelity without compromising perceptual quality.

Applications · Neuroscience, Cognitive Science

Ritik Raina, Abe Leite, Alexandros Graikos, Seoyoung Ahn, Dimitris Samaras, Gregory Zelinsky

Human vision combines low-resolution “gist” information from the visual periphery with sparse but high-resolution information from fixated locations to construct a coherent understanding of a visual scene. In this paper, we introduce MetamerGen, a tool for generating scenes that are aligned with latent human scene representations. MetamerGen is a latent diffusion model that combines peripherally obtained scene gist information with information obtained from scene-viewing fixations to generate image metamers for what humans understand after viewing a scene. Generating images from both high and low resolution (i.e. “foveated”) inputs constitutes a novel image-to-image synthesis problem, which we tackle by introducing a dual-stream representation of the foveated scenes consisting of DINOv2 tokens that fuse detailed features from fixated areas with peripherally degraded features capturing scene context. To evaluate the perceptual alignment of MetamerGen generated images to latent human scene representations, we conducted a same-different behavioral experiment where participants were asked for a “same” or “different” response between the generated and the original image. With that, we identify scene generations that are indeed metamers for the latent scene representations formed by the viewers. MetamerGen is a powerful tool for understanding scene understanding. Our proof-of-concept analyses uncovered specific features at multiple levels of visual processing that contributed to human judgments. While it can generate metamers even conditioned on random fixations, we find that high-level semantic alignment most strongly predicts metamerism when the generated scenes are conditioned on viewers’ own fixated regions.

Deep Learning · Theory

Yiran Zhang, Weihang Xu, Mo Zhou, Maryam Fazel, Simon Du

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functions. Despite its empirical success, the theoretical understanding of the optimization behavior of score matching, particularly in over-parameterized regimes, remains limited. In this work, we study gradient descent for training over-parameterized models to learn a single Gaussian distribution. Specifically, we use a student model with $n$ learnable parameters, motivated by the structure of a Gaussian mixture model, and train it on data generated from a single ground-truth Gaussian using the population score matching objective. We analyze the optimization dynamics under multiple regimes. When the noise scale is sufficiently large, we prove a global convergence result for gradient descent, which resembles the known behavior of gradient EM in over-parameterized settings. In the low-noise regime, we identify the existence of a stationary point, highlighting the difficulty of proving global convergence in this case. Nevertheless, we show convergence under certain initialization conditions: when the parameters are initialized to be exponentially small, gradient descent ensures convergence of all parameters to the ground truth. We further give an example where, without the exponentially small initialization, the parameters may not converge to the ground truth. Finally, we consider the case of random initialization, where parameters are sampled from a Gaussian distribution far from the ground truth. We prove that, with high probability, only one parameter converges while the others diverge to infinity, yet the loss still converges to zero with a $1/\tau$ rate, where $\tau$ is the number of iterations. We also establish a nearly matching lower bound on the convergence rate in this regime. This is the first work to establish global convergence guarantees for Gaussian mixtures with at least three components under the score matching framework.

Computer Vision · Image and Video Generation

Hangjie Yuan, Weihua Chen, Jun CEN, Hu Yu, Jingyun Liang, Shuning Chang, Zhihui Lin, Tao Feng, Pengwei Liu, Jiazheng Xing 等

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

Computer Vision · 3D Rendering & Reconstruction

Youngho Yoon, Kuk-Jin Yoon

Recent advances in novel view synthesis (NVS) have predominantly focused on ideal, clear input settings, limiting their applicability in real-world environments with common degradations such as blur, low-light, haze, rain, and snow. While some approaches address NVS under specific degradation types, they are often tailored to narrow cases, lacking the generalizability needed for broader scenarios. To address this issue, we propose Restoration-based feed-forward Gaussian Splatting, named ReSplat, a novel framework capable of handling degraded multi-view inputs. Our model jointly estimates restored images and gaussians to represent the clear scene for NVS. We enable multi-view consistent universal image restoration by utilizing the 3d gaussians generated during the diffusion sampling process as self-guidance. This results in sharper and more reliable novel views. Notably, our framework adapts to various degradations without prior knowledge of their specific types. Extensive experiments demonstrate that ReSplat significantly outperforms existing methods across challenging conditions, including blur, low-light, haze, rain, and snow, delivering superior visual quality and robust NVS performance. Code is available at https://github.com/yh-yoon/ReSplat.

Applications · Neuroscience, Cognitive Science

Xu Zhang, Ruijie Quan, Wenguan Wang, Yi Yang

Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single neural embedding, using it as static guidance throughout the entire generation process. However, this fixed guidance collapses hierarchical neural information and is misaligned with the stage-dependent demands of image reconstruction. In response, we propose MindHier, a coarse-to-fine fMRI-to-image reconstruction framework built on scale-wise autoregressive modeling. MindHier introduces three components: a Hierarchical fMRI Encoder to extract multi-level neural embeddings, a Hierarchy-to-Hierarchy Alignment scheme to enforce layer-wise correspondence with CLIP features, and a Scale-Aware Coarse-to-Fine Neural Guidance strategy to inject these embeddings into autoregression at matching scales. These designs make MindHier an efficient and cognitively aligned alternative to diffusion-based methods by enabling a hierarchical reconstruction process that synthesizes global semantics before refining local details, akin to human visual perception. Extensive experiments on the NSD dataset show that MindHier achieves superior semantic fidelity, 4.67$\times$ faster inference, and more deterministic results than the diffusion-based baselines.

Computer Vision · Image and Video Generation

Ruihang Xu, Dewei Zhou, Fan Ma, Yi Yang

Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce **ContextGen**, a novel Diffusion Transformer framework for multi-instance generation that is guided by both layout and reference images. Our approach integrates two key technical contributions: a **Contextual Layout Anchoring (CLA)** mechanism that incorporates the composite layout image into the generation context to robustly anchor the objects in their desired positions, and **Identity Consistency Attention (ICA)**, an innovative attention mechanism that leverages contextual reference images to ensure the identity consistency of multiple instances. To address the absence of a large-scale, high-quality dataset for this task, we introduce **IMIG-100K**, the first dataset to provide detailed layout and identity annotations specifically designed for Multi-Instance Generation. Extensive experiments demonstrate that ContextGen sets a new state-of-the-art, outperforming existing methods especially in layout control and identity fidelity.

Computer Vision · 3D Rendering & Reconstruction

Junfeng Ni, Yixin Chen, Zhifei Yang, Yu Liu, Ruijie Lu, Song-Chun Zhu, Siyuan Huang

Despite recent advances in leveraging generative prior from pre-trained diffusion models for 3D scene reconstruction, existing methods still face two critical limitations. First, due to the lack of reliable geometric supervision, they struggle to produce high-quality reconstructions even in observed regions, let alone in unobserved areas. Second, they lack effective mechanisms to mitigate multi-view inconsistencies in the generated images, leading to severe shape–appearance ambiguities and degraded scene geometry. In this paper, we identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction. We first propose to leverage the prevalence of planar structures to derive accurate metric-scale depth maps, providing reliable supervision in both observed and unobserved regions. Furthermore, we incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models, resulting in accurate and consistent scene completion. Extensive experiments on Replica, ScanNet++, DeepBlending and Mip-NeRF 360 show that our method consistently outperforms existing baselines in both geometry and appearance reconstruction, particularly for unobserved regions. Moreover, our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios with practical real-world applicability. Project page: https://dali-jack.github.io/g4splat-web/.

Frederic Wang, Katherine Bouman

The choice of prior is central to solving ill-posed imaging inverse problems, making it essential to select one consistent with the measurements $y$ to avoid severe bias. In Bayesian inverse problems, this could be achieved by evaluating the model evidence $p(y \mid M)$ under different models $M$ that specify the prior and then selecting the one with the highest value. Diffusion models are the state-of-the-art approach to solving inverse problems with a data-driven prior; however, directly computing the model evidence with respect to a diffusion prior is intractable. Furthermore, most existing model evidence estimators require either many pointwise evaluations of the unnormalized prior density or an accurate clean prior score. We propose DiME, an estimator of the model evidence under a diffusion prior by integrating over the time-marginals of posterior sampling methods. Our method leverages the large amount of intermediate samples that are naturally obtained during the reverse diffusion sampling process to obtain an accurate estimation of the model evidence using only a handful of posterior samples (e.g., 20). We demonstrate how to implement our estimator in tandem with recent diffusion posterior sampling methods. Empirically, our estimator matches the model evidence when it can be computed analytically, and it is able to both select the correct diffusion model prior and diagnose prior misfit under different highly ill-conditioned, non-linear inverse problems, including a real-world black hole imaging problem.

Applications · Genetics, Cell Biology, Health, etc

Siyuan Chen, Minghao Guo, Caoliwen Wang, Anka He Chen, Yikun Zhang, Jingjing Chai, Yin Yang, Wojciech Matusik, Peter Yichen Chen

Biomolecular interaction modeling has been substantially advanced by foundation models, yet they often produce all-atom structures that violate basic steric feasibility. We address this limitation by enforcing physical validity as a strict constraint during both training and inference with a unified module. At its core is a differentiable projection that maps the provisional atom coordinates from the diffusion model to the nearest physically valid configuration. This projection is achieved using a Gauss-Seidel scheme, which exploits the locality and sparsity of the constraints to ensure stable and fast convergence at scale. By implicit differentiation to obtain gradients, our module integrates seamlessly into existing frameworks for end-to-end finetuning. With our Gauss-Seidel projection module in place, two denoising steps are sufficient to produce biomolecular complexes that are both physically valid and structurally accurate. Across six benchmarks, our $2$-step model achieves the same structural accuracy as state-of-the-art $200$-step diffusion baselines, delivering ${\sim}10\times$ wall-clock speedups while guaranteeing physical validity. The code is available at https://github.com/chensiyuan030105/ProteinGS.git.

Deep Learning · Generative Models and Autoencoders

Yixuan Ren, Hanyu Wang, Bo He, Hao Chen, Abhinav Shrivastava

We present NeRV-Diffusion, an implicit latent video diffusion model that synthesizes videos via generating neural network weights. The generated weights can be arranged as the parameters of a convolutional network, forming an implicit neural representation (INR) and decoding into videos with frame indices as the input. Our framework consists of two stages: First, a hypernetwork-based tokenizer that encodes raw videos from pixel space to neural parameter space, and the bottleneck latent serves as INR weights to decode; Second, an implicit diffusion transformer that denoises on the latent INR weights. In contrast to traditional video tokenizers that compress videos into frame-wise feature maps, NeRV-Diffusion generates a video as a compact dedicated neural network. This continuous holistic video representation obviates temporal cross-frame attentions while preserving flexible temporal interpolability. The INR decoder and weight latent feature sublinear complexity overhead regarding video resolution and length increase with additional upsampling layers. To enable Gaussian-distributed neural weights with high expressiveness, we reuse the bottleneck latent across all INR layers, as well as reform its weight modulation, upsampling connection and input coordinates. We also introduce SNR-adaptive loss weighting and scheduled sampling for effective training of the implicit diffusion model. NeRV-Diffusion reaches superior video synthesis quality over previous INR-based models and comparable performance to most recent state-of-the-art non-implicit models on real-world video benchmarks including UCF-101 and Kinetics-600. It also achieves outstanding decoding and generation efficiency when scaling up to high-resolution and long videos.

Computer Vision · Image and Video Generation

Sangwon Jang, Taekyung Ki, Jaehyeong Jo, Jaehong Yoon, Soo Ye Kim, Zhe Lin, Sung Ju Hwang

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes increasingly impractical as model sizes continue to grow. In this work, we present Frame Guidance, a training-free guidance for controllable video generation based on frame-level signals, such as keyframes, style reference images, sketches, or depth maps. By applying guidance to only a few selected frames, Frame Guidance can steer the generation of the entire video, resulting in a temporally coherent controlled video. To enable training-free guidance on large-scale video models, we propose a simple latent processing method that dramatically reduces memory usage, and apply a novel latent optimization strategy designed for globally coherent video generation. Frame Guidance enables effective control across diverse tasks, including keyframe guidance, stylization, and looping, without any training, and is compatible with any models. Experimental results show that Frame Guidance can produce high-quality controlled videos for a wide range of tasks and input signals.

Applications · Neuroscience, Cognitive Science

Yule Wang, Joseph Yu, Chengrui Li, Weihan Li, Anqi Wu

Understanding how neural populations in higher visual areas encode object-centered visual information remains a key challenge in computational neuroscience. Prior work has examined representational alignment between artificial neural networks and the visual cortex, but these findings are indirect and provide limited insight into the structure of neural population coding. Decoding-based methods can recover semantic features from neural activity, yet they do not reveal how these features are organized. This leaves an open question: how feature-specific visual information is distributed across neural populations, and whether it forms structured, semantically meaningful subspaces. To address this, we introduce MIG-Vis, a method that leverages diffusion models to visualize and validate visual-semantic attributes encoded in neural latent subspaces. MIG-Vis first learns a group-wise disentangled neural latent representation using a variational autoencoder, and then applies mutual information (MI)-guided diffusion synthesis to visualize the visual-semantic features encoded in each latent group. We validate MIG-Vis on multi-session neural spiking datasets from the inferior temporal (IT) cortex of two macaques. The synthesized results show that MIG-Vis identifies neural latent groups with clear semantic selectivity to diverse visual features, including object pose, inter-category variation, and intra-category content. These findings provide direct and interpretable evidence of structured semantic representation in higher visual cortex.

Social Aspects · Accountability, Transparency and Interpretability

Maty Bohacek, Thomas Fel, Maneesh Agrawala, Ekdeep Singh Lubana

Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -- that are reasonably expected to appear in the training data. These failure modes have largely been documented anecdotally, leaving open the question of whether they reflect idiosyncratic anomalies or more structural limitations of these models. To address this, we introduce a systematic approach for identifying and characterizing "conceptual blindspots" -- concepts present in the training data but absent or misrepresented in a model's generations. Our method leverages sparse autoencoders (SAEs) to extract interpretable concept embeddings, enabling a quantitative comparison of concept prevalence between real and generated images. We train an archetypal SAE (RA-SAE) on DINOv2 features with 32,000 concepts -- the largest such SAE to date -- enabling fine-grained analysis of conceptual disparities. Applied to four popular generative models (Stable Diffusion 1.5/2.1, PixArt, and Kandinsky), our approach reveals specific suppressed blindspots (e.g., bird feeders, DVD discs, and whitespaces on documents) and exaggerated blindspots (e.g., wood background texture and palm trees). At the individual datapoint level, we further isolate memorization artifacts -- instances where models reproduce highly specific visual templates seen during training. Overall, we propose a theoretically grounded framework for systematically identifying conceptual blindspots in generative models by assessing their conceptual fidelity with respect to the underlying data-generating process.

Computer Vision · Image and Video Generation

Uichan Lee, Jeonghyeon Kim, Sangheum Hwang

Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted content. To mitigate such risks, concept erasure techniques have emerged as a promising solution. Prior works have primarily focused on fine-tuning the denoising component (e.g., the U-Net backbone). However, recent causal tracing studies suggest that visual attribute information is localized in the early self-attention layers of the text encoder, indicating a potential alternative for concept erasing. Building on this insight, we conduct preliminary experiments and find that directly fine-tuning early layers can suppress target concepts but often degrades the generation quality of non-target concepts. To overcome this limitation, we propose High-Level Representation Misdirection (HiRM), which misdirects high-level semantic representations of target concepts in the text encoder toward designated vectors such as random directions or semantically defined directions (e.g., super-categories), while updating only early layers that contain causal states of visual attributes. Our decoupling strategy enables precise concept removal with minimal impact on unrelated concepts, as demonstrated by strong results on UnlearnCanvas and NSFW benchmarks across diverse targets (e.g., objects, styles, nudity). HiRM also preserves generative utility at low training cost, transfers to state-of-the-art architectures such as Flux without additional training, and shows synergistic effects with denoiser-based concept erasing methods.

Optimization · Optimization and Learning under Uncertainty

Zihao Zhao, Christopher Yeh, Lingkai Kong, Kai Wang

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely on deterministic point predictions, which are often insufficient to capture the intrinsic stochasticity of real-world environments. To address this challenge, we propose the first diffusion-based DFL approach, which trains a diffusion model to represent the distribution of uncertain parameters and optimizes the decision by solving a stochastic optimization with samples drawn from the diffusion model. Our contributions are twofold. First, we formulate diffusion DFL using the reparameterization trick, enabling end-to-end training through diffusion. While effective, it is memory and compute-intensive due to the need to differentiate through the diffusion sampling process. Second, we propose a lightweight score function estimator that uses only several forward diffusion passes and avoids backpropagation through the sampling. This follows from our results that backpropagating through stochastic optimization can be approximated by a weighted score function formulation. We empirically show that our diffusion DFL approach consistently outperforms strong baselines in decision quality. The source code for all experiments is available at https://github.com/GT-KOALA/Diffusion_DFL.

Deep Learning · Generative Models and Autoencoders

Gautham Anil, Shaan Ul Haque, Nithish Kannen, Dheeraj Nagaraj, Sanjay Shakkottai, Karthikeyan Shanmugam

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications. Towards this, we examine the effect of shaping the distribution at intermediate noise levels induced by diffusion models. First, we show that existing variants of Rejection sAmpling based Fine-Tuning (RAFT), which we unify as GRAFT, can implicitly perform KL regularized reward maximization with reshaped rewards. Motivated by this observation, we introduce P-GRAFT to shape distributions at intermediate noise levels and demonstrate empirically that this can lead to more effective fine-tuning. We mathematically explain this via a bias-variance tradeoff. Next, we look at correcting learning errors in pre-trained flow models based on the developed mathematical framework. In particular, we propose inverse noise correction, a novel algorithm to improve the quality of pre-trained flow models without explicit rewards. We empirically evaluate our methods on text-to-image(T2I) generation, layout generation, molecule generation and unconditional image generation. Notably, our framework, applied to Stable Diffusion v2, improves over policy gradient methods on popular T2I benchmarks in terms of VQAScore and shows an 8.81% relative improvement over the base model. For unconditional image generation, inverse noise correction improves FID of generated images at lower FLOPs/image.

Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, Chunchao Guo, Liujuan Cao

We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, $10 \sim 100\times$ faster than previous works while possessing superior rendering quality. Our approach shifts from the conventional multi-view-oriented (MV-oriented) paradigm, which generates multi-view images for subsequent 3D reconstruction, to a 3D-oriented approach where the model directly produces 3D Gaussian representations during multi-view generation. While ensuring 3D consistency, 3D-oriented method typically suffers poor visual quality. FlashWorld includes a dual-mode pre-training phase followed by a cross-mode post-training phase, effectively integrating the strengths of both paradigms. Specifically, leveraging the prior from a video diffusion model, we first pre-train a dual-mode multi-view diffusion model, which jointly supports MV-oriented and 3D-oriented generation mode. To bridge the quality gap in 3D-oriented generation, we further propose a cross-mode post-training distillation by matching distribution from consistent 3D-oriented mode to high-quality MV-oriented mode. This not only enhances visual quality while maintaining 3D consistency, but also reduces the required denoising steps for inference. Also, we propose a strategy to leverage massive single-view images and text prompts during this process to enhance the model's generalization to out-of-distribution inputs. Extensive experiments demonstrate the superiority and efficiency of our method. Our code is released at https://github.com/imlixinyang/FlashWorld.