Vision-language models (VLMs) have made significant strides in reasoning, yet they often struggle with complex multimodal tasks and tend to generate overly verbose outputs. A key limitation is their reliance on chain-of-thought (CoT) reasoning, despite many tasks benefiting from alternative topologies like trees or graphs. To address this, we introduce STELAR-Vision, a training framework for topology-aware reasoning. At its core is TopoAug, a synthetic data pipeline that enriches training with diverse topological structures. Using supervised fine-tuning and reinforcement learning, we post-train Qwen2VL models with both accuracy and efficiency in mind. Additionally, we propose Frugal Learning, which reduces output length with minimal accuracy loss. On MATH-V and VLM_S2H, STELAR-Vision improves accuracy by 9.7% over its base model and surpasses the larger Qwen2VL-72B-Instruct by 7.3%. On five out-of-distribution benchmarks, it outperforms Phi-4-Multimodal-Instruct by up to 28.4% and LLaMA-3.2-11B-Vision-Instruct by up to 13.2%, demonstrating strong generalization. Compared to Chain-Only training, our approach achieves 4.3% higher overall accuracy on in-distribution datasets and consistently outperforms across all OOD benchmarks.

Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions often carry lengthy, intertwined contexts that are difficult to parse and frequently overlook essential cues, posing a great barrier for models like GroundingDINO and SDXL, which lack the strong text encoding and syntax analysis needed to fully leverage dense captions. To address this, we propose BACON, a prompting method that breaks down VLM-generated captions into disentangled, structured elements such as objects, relationships, styles, and themes. This approach not only minimizes confusion from handling complex contexts but also allows for efficient transfer into a JSON dictionary, enabling models without linguistic processing capabilities to easily access key information. We annotated 100,000 image-caption pairs using BACON with GPT-4V and trained an LLaVA captioner on this dataset, enabling it to produce BACON-style captions without relying on costly GPT-4V. Evaluations of overall quality, precision, and recall—as well as user studies—demonstrate that the resulting caption model consistently outperforms other SOTA VLM models in generating high-quality captions. Besides, we show that BACON-style captions exhibit better clarity when applied to various models, enabling them to accomplish previously unattainable tasks or surpass existing SOTA solutions without training. For example, BACON-style captions help GroundingDINO achieve 1.51× higher recall scores on open-vocabulary object detection tasks compared to leading methods.

Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the lengthy sampling time of the denoising process remains a significant bottleneck in practical applications. Previous methods either ignore the statistical relationships between adjacent steps or rely on attention or feature similarity between them, which often only works with specific network structures. To address this issue, we discover a new statistical relationship in the transition operator between adjacent steps, focusing on the relationship of the outputs from the network. This relationship does not impose any requirements on the network structure. Based on this observation, we propose a novel training-free acceleration method called LTC-Accel, which uses the identified relationship to estimate the current transition operator based on adjacent steps. Due to no specific assumptions regarding the network structure, LTC-Accel is applicable to almost all diffusion-based methods and orthogonal to almost all existing acceleration techniques, making it easy to combine with them. Experimental results demonstrate that LTC-Accel significantly speeds up sampling in text-to-image and text-to-video synthesis while maintaining competitive sample quality. Specifically, LTC-Accel achieves a speedup of 1.67-fold in Stable Diffusion v2 and a speedup of 1.55-fold in video generation models. When combined with distillation models, LTC-Accel achieves a remarkable 10-fold speedup in video generation, allowing real-time generation of more than 16FPS.

We present The Matrix, a foundational realistic world simulator capable of generating infinitely long 720p high-fidelity real-scene video streams with real-time, responsive control in both first- and third-person perspectives. Trained on limited supervised data from video games like Forza Horizon 5 and Cyberpunk 2077, complemented by large-scale unsupervised footage from real-world settings like Tokyo streets, The Matrix allows users to traverse diverse terrains—deserts, grasslands, water bodies, and urban landscapes—in continuous, uncut hour-long sequences. With speeds of up to 16 FPS, the system supports real-time interactivity and demonstrates zero-shot generalization, translating virtual game environments to real-world contexts where collecting continuous movement data is often infeasible. For example, The Matrix can simulate a BMW X3 driving through an office setting—an environment present in neither gaming data nor real-world sources. This approach showcases the potential of game data to advance robust world models, bridging the gap between simulations and real-world applications in scenarios with limited data.

Image restoration poses a garners substantial interest due to the exponential surge in demands for recovering high-quality images from diverse mobile camera devices, adverse lighting conditions, suboptimal shooting environments, and frequent image compression for efficient transmission purposes. Yet this problem gathers significant challenges as people are blind to the type of restoration the images suffer, which, is usually the case in real-day scenarios and is most urgent to solve for this field. Current research, however, heavily relies on prior knowledge of the restoration type, either explicitly through rules or implicitly through the availability of degraded-clean image pairs to define the restoration process, and consumes considerable effort to collect image pairs of vast degradation types. This paper introduces DreamClean, a training-free method that needs no degradation prior knowledge but yields high-fidelity and generality towards various types of image degradation. DreamClean embeds the degraded image back to the latent of pre-trained diffusion models and re-sample it through a carefully designed diffusion process that mimics those generating clean images. Thanks to the rich image prior in diffusion models and our novel Variance Preservation Sampling (VPS) technique, DreamClean manages to handle various different degradation types at one time and reaches far more satisfied final quality than previous competitors. DreamClean relies on elegant theoretical supports to assure its convergence to clean image when VPS has appropriate parameters, and also enjoys superior experimental performance over various challenging tasks that could be overwhelming for previous methods when degradation prior is unavailable.

Diffusion models, which employ stochastic differential equations to sample images through integrals, have emerged as a dominant class of generative models. However, the rationality of the diffusion process itself receives limited attention, leaving the question of whether the problem is well-posed and well-conditioned. In this paper, we uncover a vexing propensity of diffusion models: they frequently exhibit the infinite Lipschitz near the zero point of timesteps. We provide theoretical proofs to illustrate the presence of infinite Lipschitz constants and empirical results to confirm it. The Lipschitz singularities pose a threat to the stability and accuracy during both the training and inference processes of diffusion models. Therefore, the mitigation of Lipschitz singularities holds great potential for enhancing the performance of diffusion models. To address this challenge, we propose a novel approach, dubbed E-TSDM, which alleviates the Lipschitz singularities of the diffusion model near the zero point. Remarkably, our technique yields a substantial improvement in performance. Moreover, as a byproduct of our method, we achieve a dramatic reduction in the Fréchet Inception Distance of acceleration methods relying on network Lipschitz, including DDIM and DPM-Solver, by over 33\%. Extensive experiments on diverse datasets validate our theory and method. Our work may advance the understanding of the general diffusion process, and also provide insights for the design of diffusion models.

Consistency Models (CMs) have showed a promise in creating high-quality images with few steps. However, the way to add new conditional controls to the pre-trained CMs has not been explored. In this paper, we explore the pivotal subject of leveraging the generative capacity and efficiency of consistency models to facilitate controllable visual content creation via ControlNet. First, it is observed that ControlNet trained for diffusion models (DMs) can be directly applied to CMs for high-level semantic controls but sacrifice image low-level details and realism. To tackle with this issue, we develop a CMs-tailored training strategy for ControlNet using the consistency training. It is substantiated that ControlNet can be successfully established through the consistency training technique. Besides, a unified adapter can be trained utilizing the consistency training, which enhances the adaptation of DM’s ControlNet. We quantitatively and qualitatively evaluate all strategies across various conditional controls, including sketch, hed, canny, depth, human pose, low-resolution image and masked image, with the pre-trained text-to-image latent consistency models.

Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension. We argue that, considering the spatial redundancy in image signals, there is no need to maintain a high dimensionality in the evolution process, especially in the early generation phase. To this end, we make a theoretical generalization of the forward diffusion process via signal decomposition. Concretely, we manage to decompose an image into multiple orthogonal components and control the attenuation of each component when perturbing the image. That way, along with the noise strength increasing, we are able to diminish those inconsequential components and thus use a lower-dimensional signal to represent the source, barely losing information. Such a reformulation allows to vary dimensions in both training and inference of diffusion models. Extensive experiments on a range of datasets suggest that our approach substantially reduces the computational cost and achieves on-par or even better synthesis performance compared to baseline methods. We also show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at$1024\times 1024$resolution from 52.40 to 10.46. Code is available at https://github.com/damo-vilab/dvdp.

Fine-grained sketch-based image retrieval (FG-SBIR) is an emerging topic in high-level computer vision. Among existing methods, edge-only information based ones are convenient to use but incompetent in distinguishing among ambiguous samples. On the other hand, even though the methods using additional color information can significantly improve the retrieval performance, they are not convenient for practical use as the increase of sketch complexity. This paper fills the gap between these two kinds of methods by proposing a novel method, namely dark-aware sketch-based image retrieval (DA-SBIR), which incorporates the dark region information of images into FG-SBIR without a sacrifice of convenience. Our model consists of two branches to process edge structure and dark region, respectively. Specifically, instead of using real color, DA-SBIR only requires some additional free-hand black sketch to represent the dark region. Besides, a Split Generative Adversarial Network is introduced to automatically split a sketch into edge-structure-only and dark-region-only sketches. Moreover, we build a new clothes dataset, SJTU-Cloth, with more ambiguous samples for FG-SBIR. Experimental results on the QMUL-Shoe dataset and our SJTU-Cloth dataset show that our approach achieves consistent improvements over state-of-the-arts. Code and dataset are available at https://github.com/y2242794082/SBIR.git.