Xuhui Jia

Wenhu Chen, Hexiang Hu, Yandong Li et al. · deepmind

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples. However, this process is expensive, since a new expert model must be learned for each subject. In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with in-context learning. Given a few demonstrations of a new subject, SuTI can instantly generate novel renditions of the subject in different scenes, without any subject-specific optimization. SuTI is powered by apprenticeship learning, where a single apprentice model is learned from data generated by a massive number of subject-specific expert models. Specifically, we mine millions of image clusters from the Internet, each centered around a specific visual subject. We adopt these clusters to train a massive number of expert models, each specializing in a different subject. The apprentice model SuTI then learns to imitate the behavior of these fine-tuned experts. SuTI can generate high-quality and customized subject-specific images 20x faster than optimization-based SoTA methods. On the challenging DreamBench and DreamBench-v2, our human evaluation shows that SuTI significantly outperforms existing models like InstructPix2Pix, Textual Inversion, Imagic, Prompt2Prompt, Re-Imagen and DreamBooth, especially on the subject and text alignment aspects.

Xuhui Jia, Yang Zhao, Kelvin C. K. Chan et al.

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object optimization paradigm. Our framework adopts an encoder to capture high-level identifiable semantics of objects, producing an object-specific embedding with only a single feed-forward pass. The acquired object embedding is then passed to a text-to-image synthesis model for subsequent generation. To effectively blend a object-aware embedding space into a well developed text-to-image model under the same generation context, we investigate different network designs and training strategies, and propose a simple yet effective regularized joint training scheme with an object identity preservation loss. Additionally, we propose a caption generation scheme that become a critical piece in fostering object specific embedding faithfully reflected into the generation process, while keeping control and editing abilities. Once trained, the network is able to produce diverse content and styles, conditioned on both texts and objects. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity, without the need of test-time optimization. Systematic studies are also conducted to analyze our models, providing insights for future work.

Yu-Chuan Su, Kelvin C. K. Chan, Yandong Li et al.

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being successful, this approach incurs additional computation and storage overhead for each new identity. Furthermore, it usually expects tens or hundreds of examples per identity to achieve the best performance. To overcome these challenges, we propose an encoder-based approach for personalization. We learn an identity encoder which can extract an identity representation from a set of reference images of a subject, together with a diffusion generator that can generate new images of the subject conditioned on the identity representation. Once being trained, the model can be used to generate images of arbitrary identities given a few examples even if the model hasn't been trained on the identity. Our approach greatly reduces the overhead for personalized image generation and is more applicable in many potential applications. Empirical results show that our approach consistently outperforms existing fine-tuning based approach in both image generation and reconstruction, and the outputs is preferred by users more than 95% of the time compared with the best performing baseline.

Kai Han, Xiaohu Huang, Yandong Li et al.

Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index, without revealing the actual semantic meaning of the object in the image. In contrast, vision-language models like CLIP are able to assign semantic class names to unseen objects in a 'zero-shot' manner, though they are once again provided a pre-defined set of candidate names at test-time. In this paper, we reconsider the recognition problem and task a vision-language model with assigning class names to images given only a large (essentially unconstrained) vocabulary of categories as prior information. We leverage non-parametric methods to establish meaningful relationships between images, allowing the model to automatically narrow down the pool of candidate names. Our proposed approach entails iteratively clustering the data and employing a voting mechanism to determine the most suitable class names. Additionally, we investigate the potential of incorporating additional textual features to enhance clustering performance. To achieve this, we employ the CLIP vision and text encoders to retrieve relevant texts from an external database, which can provide supplementary semantic information to inform the clustering process. Furthermore, we tackle this problem both in unsupervised and partially supervised settings, as well as with a coarse-grained and fine-grained search space as the unconstrained dictionary. Remarkably, our method leads to a roughly 50% improvement over the baseline on ImageNet in the unsupervised setting.

Hong-You Chen, Jike Zhong, Mingda Zhang et al.

Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data while building personalized models tailored to individual clients' data distributions. Existing works offer personalization primarily to clients who participate in the FL process, making it hard to encompass new clients who were absent or newly show up. In this paper, we propose FedBasis, a novel PFL framework to tackle such a deficiency. FedBasis learns a set of few shareable ``basis'' models, which can be linearly combined to form personalized models for clients. Specifically for a new client, only a small set of combination coefficients, not the model weights, needs to be learned. This notion makes FedBasis more parameter-efficient, robust, and accurate than competitive PFL baselines, especially in the low data regime, without increasing the inference cost. To demonstrate the effectiveness and applicability of FedBasis, we also present a more practical PFL testbed for image classification, featuring larger data discrepancies across clients in both the image and label spaces as well as more faithful training and test splits.

Kangning Liu, Yu-Chuan Su, Wei et al.

The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame. Recent methods rely on warping the appearance feature extracted from the source, by using motion fields estimated from the sparse keypoints, that are learned in an unsupervised manner. Due to their lightweight formulation, they are suitable for video conferencing with reduced bandwidth. However, based on our study, current methods suffer from two major limitations: 1) unsatisfactory generation quality in the case of large head poses and the existence of observable pose misalignment between the source and the first frame in driving videos. 2) fail to capture fine yet critical face motion details due to the lack of semantic understanding and appropriate face geometry regularization. To address these shortcomings, we propose a novel method that leverages the rich face prior information, the proposed model can generate face videos with improved semantic consistency (improve baseline by $7\%$ in average keypoint distance) and expression-preserving (outperform baseline by $15 \%$ in average emotion embedding distance) under equivalent bandwidth. Additionally, incorporating such prior information provides us with a convenient interface to achieve highly controllable generation in terms of both pose and expression.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Imagen-Team-Google, Jason Baldridge, Jakob Bauer et al.

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models.

Nanye Ma, Shangyuan Tong, Haolin Jia et al.

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model size, a phenomenon characterized by the scaling laws. Recent research has begun to explore inference-time scaling behavior in Large Language Models (LLMs), revealing how performance can further improve with additional computation during inference. Unlike LLMs, diffusion models inherently possess the flexibility to adjust inference-time computation via the number of denoising steps, although the performance gains typically flatten after a few dozen. In this work, we explore the inference-time scaling behavior of diffusion models beyond increasing denoising steps and investigate how the generation performance can further improve with increased computation. Specifically, we consider a search problem aimed at identifying better noises for the diffusion sampling process. We structure the design space along two axes: the verifiers used to provide feedback, and the algorithms used to find better noise candidates. Through extensive experiments on class-conditioned and text-conditioned image generation benchmarks, our findings reveal that increasing inference-time compute leads to substantial improvements in the quality of samples generated by diffusion models, and with the complicated nature of images, combinations of the components in the framework can be specifically chosen to conform with different application scenario.

Hexiang Hu, Kelvin C. K. Chan, Yu-Chuan Su et al. · deepmind

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format. We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model using the retrieval-augmented training, to enhance model's capabilities to ground its generation on external multimodal context. Subsequently, we fine-tune the adapted model on diverse image generation tasks that requires vision-language understanding (e.g., subject-driven generation, etc.), each paired with a multi-modal instruction encapsulating the task's essence. Human evaluation on various image generation datasets reveals that instruct-imagen matches or surpasses prior task-specific models in-domain and demonstrates promising generalization to unseen and more complex tasks.

Prafull Sharma, Varun Jampani, Yuanzhen Li et al.

We propose a method to control material attributes of objects like roughness, metallic, albedo, and transparency in real images. Our method capitalizes on the generative prior of text-to-image models known for photorealism, employing a scalar value and instructions to alter low-level material properties. Addressing the lack of datasets with controlled material attributes, we generated an object-centric synthetic dataset with physically-based materials. Fine-tuning a modified pre-trained text-to-image model on this synthetic dataset enables us to edit material properties in real-world images while preserving all other attributes. We show the potential application of our model to material edited NeRFs.

Hsin-Ping Huang, Yu-Chuan Su, Deqing Sun et al. · deepmind

Text-to-video generation has shown promising results. However, by taking only natural languages as input, users often face difficulties in providing detailed information to precisely control the model's output. In this work, we propose fine-grained controllable video generation (FACTOR) to achieve detailed control. Specifically, FACTOR aims to control objects' appearances and context, including their location and category, in conjunction with the text prompt. To achieve detailed control, we propose a unified framework to jointly inject control signals into the existing text-to-video model. Our model consists of a joint encoder and adaptive cross-attention layers. By optimizing the encoder and the inserted layer, we adapt the model to generate videos that are aligned with both text prompts and fine-grained control. Compared to existing methods relying on dense control signals such as edge maps, we provide a more intuitive and user-friendly interface to allow object-level fine-grained control. Our method achieves controllability of object appearances without finetuning, which reduces the per-subject optimization efforts for the users. Extensive experiments on standard benchmark datasets and user-provided inputs validate that our model obtains a 70% improvement in controllability metrics over competitive baselines.

Yihong Sun, Hao Zhou, Liangzhe Yuan et al. · deepmind

We explore a novel video creation experience, namely Video Creation by Demonstration. Given a demonstration video and a context image from a different scene, we generate a physically plausible video that continues naturally from the context image and carries out the action concepts from the demonstration. To enable this capability, we present $δ$-Diffusion, a self-supervised training approach that learns from unlabeled videos by conditional future frame prediction. Unlike most existing video generation controls that are based on explicit signals, we adopts the form of implicit latent control for maximal flexibility and expressiveness required by general videos. By leveraging a video foundation model with an appearance bottleneck design on top, we extract action latents from demonstration videos for conditioning the generation process with minimal appearance leakage. Empirically, $δ$-Diffusion outperforms related baselines in terms of both human preference and large-scale machine evaluations, and demonstrates potentials towards interactive world simulation. Sampled video generation results are available at https://delta-diffusion.github.io/.

Kelvin C. K. Chan, Yang Zhao, Xuhui Jia et al.

In subject-driven text-to-image synthesis, the synthesis process tends to be heavily influenced by the reference images provided by users, often overlooking crucial attributes detailed in the text prompt. In this work, we propose Subject-Agnostic Guidance (SAG), a simple yet effective solution to remedy the problem. We show that through constructing a subject-agnostic condition and applying our proposed dual classifier-free guidance, one could obtain outputs consistent with both the given subject and input text prompts. We validate the efficacy of our approach through both optimization-based and encoder-based methods. Additionally, we demonstrate its applicability in second-order customization methods, where an encoder-based model is fine-tuned with DreamBooth. Our approach is conceptually simple and requires only minimal code modifications, but leads to substantial quality improvements, as evidenced by our evaluations and user studies.

Hsin-Ping Huang, Xinyi Wang, Yonatan Bitton et al.

Recent advances in text-to-image generation have improved the quality of synthesized images, but evaluations mainly focus on aesthetics or alignment with text prompts. Thus, it remains unclear whether these models can accurately represent a wide variety of realistic visual entities. To bridge this gap, we propose KITTEN, a benchmark for Knowledge-InTensive image generaTion on real-world ENtities. Using KITTEN, we conduct a systematic study of the latest text-to-image models and retrieval-augmented models, focusing on their ability to generate real-world visual entities, such as landmarks and animals. Analysis using carefully designed human evaluations, automatic metrics, and MLLM evaluations show that even advanced text-to-image models fail to generate accurate visual details of entities. While retrieval-augmented models improve entity fidelity by incorporating reference images, they tend to over-rely on them and struggle to create novel configurations of the entity in creative text prompts.

Jiacheng Chen, Ramin Mehran, Xuhui Jia et al.

We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs into editable 3D entities (layering), (ii) editing them in Blender with 3D-grounded control (editing), and (iii) fusing them into a coherent scene using a generative compositor (compositing). Our generative compositor extends a pre-trained diffusion model to process both the original (source) and edited (target) scenes in parallel. It is fine-tuned on video frames with two key training strategies: (i) source masking, enabling flexible modifications like background replacement; (ii) simulated object jittering, facilitating disentangled control over objects and camera. BlenderFusion significantly outperforms prior methods in complex compositional scene editing tasks.

Xuhui Jia, Kai Han, Yukun Zhu et al.

This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign clusters to unlabelled data. To avoid over-fitting the learnt embedding to labelled data, we take inspiration from self-supervised representation learning by noise-contrastive estimation and extend it to jointly handle labelled and unlabelled data. In particular, we propose using category discrimination on labelled data and cross-modal discrimination on multi-modal data to augment instance discrimination used in conventional contrastive learning approaches. We further employ Winner-Take-All (WTA) hashing algorithm on the shared representation space to generate pairwise pseudo labels for unlabelled data to better predict cluster assignments. We thoroughly evaluate our framework on large-scale multi-modal video benchmarks Kinetics-400 and VGG-Sound, and image benchmarks CIFAR10, CIFAR100 and ImageNet, obtaining state-of-the-art results.

Yandong Li, Xuhui Jia, Ruoxin Sang et al.

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of checkpoints from various sources. Which of them transfers the best to our downstream task of interest? Striving to answer this question thoroughly, we establish a neural checkpoint ranking benchmark (NeuCRaB) and study some intuitive ranking measures. These measures are generic, applying to the checkpoints of different output types without knowing how the checkpoints are pre-trained on which dataset. They also incur low computation cost, making them practically meaningful. Our results suggest that the linear separability of the features extracted by the checkpoints is a strong indicator of transferability. We also arrive at a new ranking measure, NLEEP, which gives rise to the best performance in the experiments.

Bardia Doosti, Ching-Hui Chen, Raviteja Vemulapalli et al.

Mutual gaze detection, i.e., predicting whether or not two people are looking at each other, plays an important role in understanding human interactions. In this work, we focus on the task of image-based mutual gaze detection, and propose a simple and effective approach to boost the performance by using an auxiliary 3D gaze estimation task during the training phase. We achieve the performance boost without additional labeling cost by training the 3D gaze estimation branch using pseudo 3D gaze labels deduced from mutual gaze labels. By sharing the head image encoder between the 3D gaze estimation and the mutual gaze detection branches, we achieve better head features than learned by training the mutual gaze detection branch alone. Experimental results on three image datasets show that the proposed approach improves the detection performance significantly without additional annotations. This work also introduces a new image dataset that consists of 33.1K pairs of humans annotated with mutual gaze labels in 29.2K images.

Zhuoran Shen, Irwan Bello, Raviteja Vemulapalli et al.

Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these works either apply attention only to low-resolution feature maps in later stages of a deep network or restrict the receptive field of attention in each layer to a small local region. To overcome these limitations, this work introduces a new global self-attention module, referred to as the GSA module, which is efficient enough to serve as the backbone component of a deep network. This module consists of two parallel layers: a content attention layer that attends to pixels based only on their content and a positional attention layer that attends to pixels based on their spatial locations. The output of this module is the sum of the outputs of the two layers. Based on the proposed GSA module, we introduce new standalone global attention-based deep networks that use GSA modules instead of convolutions to model pixel interactions. Due to the global extent of the proposed GSA module, a GSA network has the ability to model long-range pixel interactions throughout the network. Our experimental results show that GSA networks outperform the corresponding convolution-based networks significantly on the CIFAR-100 and ImageNet datasets while using less parameters and computations. The proposed GSA networks also outperform various existing attention-based networks on the ImageNet dataset.

Yu Liu, Xuhui Jia, Mingxing Tan et al.

Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture. However, the knowledge of a neural network, which is represented by the network's output distribution conditioned on its input, depends not only on its parameters but also on its architecture. Hence, a more generalized approach for KD is to distill the teacher's knowledge into both the parameters and architecture of the student. To achieve this, we present a new Architecture-aware Knowledge Distillation (AKD) approach that finds student models (pearls for the teacher) that are best for distilling the given teacher model. In particular, we leverage Neural Architecture Search (NAS), equipped with our KD-guided reward, to search for the best student architectures for a given teacher. Experimental results show our proposed AKD consistently outperforms the conventional NAS plus KD approach, and achieves state-of-the-art results on the ImageNet classification task under various latency settings. Furthermore, the best AKD student architecture for the ImageNet classification task also transfers well to other tasks such as million level face recognition and ensemble learning.

Heng Yang, Xuhui Jia, Chen Change Loy et al.

The problem of face alignment has been intensively studied in the past years. A large number of novel methods have been proposed and reported very good performance on benchmark dataset such as 300W. However, the differences in the experimental setting and evaluation metric, missing details in the description of the methods make it hard to reproduce the results reported and evaluate the relative merits. For instance, most recent face alignment methods are built on top of face detection but from different face detectors. In this paper, we carry out a rigorous evaluation of these methods by making the following contributions: 1) we proposes a new evaluation metric for face alignment on a set of images, i.e., area under error distribution curve within a threshold, AUC$_α$, given the fact that the traditional evaluation measure (mean error) is very sensitive to big alignment error. 2) we extend the 300W database with more practical face detections to make fair comparison possible. 3) we carry out face alignment sensitivity analysis w.r.t. face detection, on both synthetic and real data, using both off-the-shelf and re-retrained models. 4) we study factors that are particularly important to achieve good performance and provide suggestions for practical applications. Most of the conclusions drawn from our comparative analysis cannot be inferred from the original publications.