| Total: 2374
Multimodal Large Language Models (MLLMs) contain a substantial amount of factual knowledge, which may become outdated or inaccurate over time. Consequently, various knowledge editing techniques have been proposed to update the knowledge encoded within these models. Previous approaches maintain modality consistency during both the editing and testing phases. However, in practical applications, it is desirable for knowledge to be transferable across different modalities, which can enhance the robustness of knowledge editing and potentially allow for cost-effective editing of multimodal knowledge using textual information. To address this, we introduce the concept of Transitivity of Multimodal Knowledge Editing (TMKE) and design corresponding evaluation criteria. Subsequently, we construct a corresponding TMKE Benchmark through an automated pipeline. We evaluate three MLLMs and five knowledge editing methods, uncovering limitations in the current models and methods concerning transitivity. Additionally, we analyze the intrinsic representations of the model during the editing process based on Knowledge Neurons to interpret the experimental phenomena.
With the increasing attention to pre-trained vision-language models (VLMs), e.g., CLIP, substantial efforts have been devoted to many downstream tasks, especially in test-time adaptation (TTA). However, previous works focus on learning prototypes only in the textual modality while overlooking the ambiguous semantics in class names. These ambiguities lead to textual prototypes that are insufficient to capture visual concepts, resulting in limited performance. To address this issue, we introduce **ProtoMM**, a training-free framework that constructs multimodal prototypes to adapt VLMs during the test time. By viewing the prototype as a discrete distribution over the textual descriptions and visual particles, ProtoMM has the ability to combine the multimodal features for comprehensive prototype learning. More importantly, the visual particles are dynamically updated as the testing stream flows. This allows our multimodal prototypes to continually learn from the data, enhancing their generalizability in unseen scenarios. In addition, we quantify the importance of the prototypes and test images by formulating their semantic distance as an optimal transport problem. Extensive experiments on 15 zero-shot benchmarks demonstrate the effectiveness of our method, achieving a 1.03% average accuracy improvement over state-of-the-art methods on ImageNet and its variant datasets.
We address the task of advertisement image generation and introduce three evaluation metrics to assess Creativity, prompt Alignment, and Persuasiveness (CAP) in generated advertisement images. Despite recent advancements in Text-to-Image (T2I) methods and their performance in generating high-quality images for explicit descriptions, evaluating these models remains challenging. Existing evaluation methods focus largely on assessing alignment with explicit, detailed descriptions, but evaluating alignment with visually implicit prompts remains an open problem. Additionally, creativity and persuasiveness are essential qualities that enhance the effectiveness of advertisement images, yet are seldom measured. To address this, we propose three novel metrics for evaluating the creativity, alignment, and persuasiveness of generated images. We show that current T2I models struggle with creativity, persuasiveness, and alignment when the input text is implicit messages. We further introduce a simple yet effective approach to enhance T2I models' capabilities in producing images that are better aligned, more creative, and more persuasive.
The current text-to-video (T2V) generation has made significant progress in synthesizing realistic general videos, but it is still under-explored in identity-specific human video generation with customized ID images. The key challenge lies in maintaining high ID fidelity consistently while preserving the original motion dynamic and semantic following after the identity injection. Current video identity customization methods mainly rely on reconstructing given identity images on text-to-image models, which have a divergent distribution with the T2V model. This process introduces a tuning-inference gap, leading to dynamic and semantic degradation. To tackle this problem, we propose a novel framework, dubbed PersonalVideo, that applies a mixture of reward supervision on synthesized videos instead of the simple reconstruction objective on images. Specifically, we first incorporate identity consistency reward to effectively inject the reference's identity without the tuning-inference gap. Then we propose a novel semantic consistency reward to align the semantic distribution of the generated videos with the original T2V model, which preserves its dynamic and semantic following capability during the identity injection. With the non-reconstructive reward training, we further employ simulated prompt augmentation to reduce overfitting by supervising generated results in more semantic scenarios, gaining good robustness even with only a single reference image.Extensive experiments demonstrate our method's superiority in delivering high identity faithfulness while preserving the inherent video generation qualities of the original T2V model, outshining prior methods.
Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectively synthesizing shapes and textures under diverse conditions. In this paper, we propose the Multi-View AutoRegressive (MV-AR) method, which leverages an autoregressive model to progressively generate consistent multiview images from arbitrary prompts. Firstly, the next-tokenprediction capability of the AR model significantly enhances its effectiveness in facilitating progressive multi-view synthesis. When generating widely-separated views, MV-AR can utilize all its preceding views to extract effective reference information. Subsequently, we propose a unified model that accommodates various prompts via architecture designing and training strategies. To address multiple conditions, we introduce condition injection modules for text, camera pose, image, and shape. To manage multi-modal conditions simultaneously, a progressive training strategy is employed. This strategy initially adopts the text-to-multiview (t2mv) model as a baseline to enhance the development of a comprehensive X-to-multi-view (X2mv) model through the randomly dropping and combining conditions. Finally, to alleviate the overfitting problem caused by limited high-quality data, we propose the "Shuffle View" data augmentation technique, thus significantly expanding the training data by several magnitudes. Experiments demonstrate the performance and versatility of our MV-AR, which consistently generates consistent multi-view images across a range of conditions and performs on par with leading diffusion-based multi-view image generation models. The code and models are released at https://github.com/MILab-PKU/MVAR.
Video identity customization seeks to produce high-fidelity videos that maintain consistent identity and exhibit significant dynamics based on users' reference images. However, existing approaches face two key challenges: identity degradation over extended video length and reduced dynamics during training, primarily due to their reliance on traditional self-reconstruction training with static images. To address these issues, we introduce MagicID, a novel framework designed to directly promote the generation of identity-consistent and dynamically rich videos tailored to user preferences. Specifically, we propose constructing pairwise preference video data with explicit identity and dynamic rewards for preference learning, instead of sticking to the traditional self-reconstruction. To address the constraints of customized preference data, we introduce a hybrid sampling strategy. This approach first prioritizes identity preservation by leveraging static videos derived from reference images, then enhances dynamic motion quality in the generated videos using a Frontier-based sampling method. By utilizing these hybrid preference pairs, we optimize the model to align with the reward differences between pairs of customized preferences. Extensive experiments show that MagicID successfully achieves consistent identity and natural dynamics, surpassing existing methods across various metrics.
Affordance, defined as the potential actions that an object offers, is crucial for embodied AI agents. For example, such knowledge directs an agent to grasp a knife by the handle for cutting or by the blade for safe handover. While existing approaches have made notable progress, affordance research still faces three key challenges: data scarcity, poor generalization, and real-world deployment. Specifically, there is a lack of large-scale affordance datasets with precise segmentation maps, existing models struggle to generalize across different domains or novel object and affordance classes, and little work demonstrates deployability in real-world scenarios. In this work, we address these issues by proposing a complete affordance learning system that (1) takes in egocentric videos and outputs precise affordance annotations without human labeling, (2) leverages geometric information and vision foundation models to improve generalization, and (3) introduces a framework that facilitates affordance-oriented robotic manipulation such as tool grasping and robot-to-human tool handover. Experimental results show that our model surpasses the state-of-the-art by 13.8% in mIoU, and the framework achieves 77.1% successful grasping among 179 trials, including evaluations on seen, unseen classes, and cluttered scenes. Project page: https://reagan1311.github.io/affgrasp.
Parameter-level model merging is an emerging paradigm in multi-task learning with significant promise. Previous research has explored its connections with prediction-level model ensembling--commonly viewed as the upper bound for merging--to reveal the potential of achieving performance consistency between the two. However, this observation relies on certain preconditions, such as being limited to two models, using ViT-based models, and all models are fine-tuned from the same pre-trained checkpoint. To further understand the intrinsic connections between these two paradigms, this paper explores an interesting possibility: If these restrictions are removed, can performance consistency still be achieved between merging and ensembling? To answer this question, we first theoretically establish a performance correlation between merging and ensembling. We find that even when previous restrictions are not met, there is still a way for model merging to attain a near-identical and superior performance similar to that of ensembling. To verify whether our findings are practical, we introduce a validation framework termed \underline Neu ral \underline Lig and (NeuLig). The learning process of NeuLig is meticulously designed with a specialized loss function supported by theoretical foundations. Experimental results demonstrate the robust resilience of NeuLig in terms of both model scale and the number of collaborating models. For instance, for the case involving 5 CLIP-ViT-B/32 models, parameter-level merging achieves the same performance as prediction-level ensembling (merging: 95.44% vs. ensembling: 95.46%).
Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become particularly relevant. Some creative solutions include token selection and merging. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the baseline of randomly discarding tokens. In this paper we take a closer look at this phenomenon and observe 5 principles of the nature of visual tokens. For example, we observe that the value of tokens follows a clear Pareto-distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. We build on these and further insights to propose a lightweight video model, LITE, that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics-400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy. Experiments also show that LITE generalizes across datasets and even other tasks without the need for retraining. The code is released at https://github.com/maggieHao/Efficient-LITE.
We introduce LLaVA-Reward, an efficient reward model designed to automatically evaluate text-to-image (T2I) generations across multiple perspectives, leveraging pretrained multimodal large language models (MLLMs). Existing MLLM-based approaches require instruction-following data for supervised fine-tuning and evaluate generation quality on analyzing text response, which is time-consuming and difficult to train. To address this problem, we propose LLaVA-Reward, which directly utilizes the hidden states of MLLMs given text-image pairs. To enhance the bidirectional interaction between visual and textual representations in decoder-only MLLMs, we further propose adding a Skip-connection Cross Attention (SkipCA) module. This design enhances text-image correlation reasoning by connecting early-layer visual features with later-layer hidden representations. In addition, LLaVA-Reward supports different types of preference data for efficient fine-tuning, including paired preference data and unpaired data. We train LLaVA-Reward on four evaluation perspectives: text-image alignment, fidelity/artifact, safety, and overall ranking. Empirical results demonstrate that LLaVA-Reward outperforms conventional and MLLM-based methods in generating human-aligned scores for automatic evaluations and inference-time scaling in text-to-image generations.
We present SliderSpace, a framework for automatically decomposing the visual capabilities of diffusion models into controllable and human-understandable directions. Unlike existing control methods that require a user to specify attributes for each edit direction individually, SliderSpace discovers multiple interpretable and diverse directions simultaneously from a single text prompt. Each direction is trained as a low-rank adaptor, enabling compositional control and the discovery of surprising possibilities in the model's latent space. Through extensive experiments on state-of-the-art diffusion models, we demonstrate SliderSpace's effectiveness across three applications: concept decomposition, artistic style exploration, and diversity enhancement. Our quantitative evaluation shows that SliderSpace-discovered directions decompose the visual structure of model's knowledge effectively, offering insights into the latent capabilities encoded within diffusion models. User studies further validate that our method produces more diverse and useful variations compared to baselines.
Video-to-video moment retrieval (Vid2VidMR) is the task of localizing unseen events or moments in a target video using a query video. This task poses several challenges, such as the need for semantic frame-level alignment and modeling complex dependencies between query and target videos. To tackle this challenging problem, we introduce MATR (Moment Alignment TRansformer), a transformer-based model designed to capture semantic context as well as the temporal details necessary for precise moment localization. MATR conditions target video representations on query video features using dual-stage sequence alignment that encodes the required correlations and dependencies. These representations are then used to guide foreground/background classification and boundary prediction heads, enabling the model to accurately identify moments in the target video that semantically match with the query video. Additionally, to provide a strong task-specific initialization for MATR, we propose a self-supervised pre-training technique that involves training the model to localize random clips within videos. Extensive experiments demonstrate that MATR achieves notable performance improvements of 13.1% in R@1 and 8.1% in mIoU on an absolute scale compared to state-of-the-art methods on the popular ActivityNet-VRL dataset. Additionally, on our newly proposed dataset, SportsMoments, MATR shows a 14.7% gain in R@1 and a 14.4% gain in mIoU on an absolute scale over strong baselines.
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward frame- work that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB in- puts. This is achieved by predicting two appropriately de- fined pointmaps for a pair of frames captured at different moments. Specifically, we predict both pointmaps at the same moment, in the same world, capturing both static and dynamic scene geometry while maintaining 3D correspon- dences. Chaining these predictions through the video sequence with respect to a reference frame naturally computes long-range correspondences, effectively combining 3D reconstruction with 3D tracking. Unlike prior methods that rely heavily on 4D ground truth supervision, we employ a novel adaptation scheme based on a reprojection loss. We establish a new extensive benchmark for world-frame re- construction and tracking, demonstrating the effectiveness and efficiency of our unified, data-driven framework. Our code, model, and benchmark will be released.
Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC). DAM preserves both local details and global context through two key innovations: a focal prompt, which ensures high-resolution encoding of targeted regions, and a localized vision backbone, which integrates precise localization with its broader context. To tackle the scarcity of high-quality DLC data, we propose a Semi-supervised learning (SSL)-based Data Pipeline (DLC-SDP). DLC-SDP starts with existing segmentation datasets and expands to unlabeled web images using SSL. We introduce DLC-Bench, a benchmark designed to evaluate DLC without relying on reference captions. DAM sets new state-of-the-art on 7 benchmarks spanning keyword-level, phrase-level, and detailed multi-sentence localized image and video captioning.
Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have attempted to mitigate this issue by focusing on the iterative nature of diffusion models. However, these approaches often overlook outliers, leading to degraded performance at low bit-widths. In this paper, we propose a DMQ which combines Learned Equivalent Scaling (LES) and channel-wise Power-of-Two Scaling (PTS) to effectively address these challenges. Learned Equivalent Scaling optimizes channel-wise scaling factors to redistribute quantization difficulty between weights and activations, reducing overall quantization error. Recognizing that early denoising steps, despite having small quantization errors, crucially impact the final output due to error accumulation, we incorporate an adaptive timestep weighting scheme to prioritize these critical steps during learning. Furthermore, identifying that layers such as skip connections exhibit high inter-channel variance, we introduce channel-wise Power-of-Two Scaling for activations. To ensure robust selection of PTS factors even with small calibration set, we introduce a voting algorithm that enhances reliability. Extensive experiments demonstrate that our method significantly outperforms existing works, especially at low bit-widths such as W4A6 (4-bit weight, 6-bit activation) and W4A8, maintaining high image generation quality and model stability. The code is available at https://github.com/LeeDongYeun/dmq.
The Segment Anything Model (SAM) has demonstrated strong versatility across various visual tasks. However, its large storage requirements and high computational cost pose challenges for practical deployment. Post-training quantization (PTQ) has emerged as an effective strategy for efficient deployment, but we identify two key challenges in SAM that hinder the effectiveness of existing PTQ methods: the heavy-tailed and skewed distribution of post-GELU activations, and significant inter-channel variation in linear projection activations. To address these challenges, we propose AHCPTQ, an accurate and hardware-efficient PTQ method for SAM. AHCPTQ introduces hardware-compatible Hybrid Log-Uniform Quantization (HLUQ) to manage post-GELU activations, employing log2 quantization for dense small values and uniform quantization for sparse large values to enhance quantization resolution. Additionally, AHCPTQ incorporates Channel-Aware Grouping (CAG) to mitigate inter-channel variation by progressively clustering activation channels with similar distributions, enabling them to share quantization parameters and improving hardware efficiency. The combination of HLUQ and CAG not only enhances quantization effectiveness but also ensures compatibility with efficient hardware execution. For instance, under the W4A4 configuration on the SAM-L model, AHCPTQ achieves 36.6% mAP on instance segmentation with the DINO detector, while achieving a 7.89x speedup and 8.64x energy efficiency over its floating-point counterpart in FPGA implementation.
Generating human videos from a single image while ensuring high visual quality and precise control is a challenging task, especially in complex scenarios involving multiple individuals and interactions with objects. Existing methods, while effective for single-human cases, often fail to handle the intricacies of multi-identity interactions because they struggle to associate the correct pairs of human appearance and pose condition and model the distribution of 3D-aware dynamics. To address these limitations, we present Structural Video Diffusion, a novel framework designed for generating realistic multi-human videos. Our approach introduces two core innovations: identity-specific embeddings to maintain consistent appearances across individuals and a structural learning mechanism that incorporates depth and surface-normal cues to model human-object interactions. Additionally, we expand existing human video dataset with 25K new videos featuring diverse multi-human and object interaction scenarios, providing a robust foundation for training. Experimental results demonstrate that Structural Video Diffusion achieves superior performance in generating lifelike, coherent videos for multiple subjects with dynamic and rich interactions, advancing the state of human-centric video generation. Code is available at https://github.com/zhenzhiwang/Multi-HumanVid
Federated Continual Learning (FCL) has recently garnered significant attention due to its ability to continuously learn new tasks while protecting user privacy. However, existing Data-Free Knowledge Transfer (DFKT) methods require training the entire model, leading to high training and communication costs, while prompt pool-based methods with access to other task-specific prompts in the pool may pose a privacy leakage risk. To address these challenges, we propose a novel method: Task-aware Prompt gradient Projection and Replay (TPPR), which leverages visual prompts to build a parameter-efficient tuning architecture. Specifically, we propose the Task-Aware Prompt Gradient Projection (TAPGP) mechanism to balance the learning of task-agnostic and task-specific knowledge. In practice, we make the gradient of the deep prompts orthogonal to the virtual data and prompts of preceding tasks, which prevents the erosion of old task knowledge while allowing the model to learn new information. Additionally, we introduce Dual-Level Prompt Replay (DLPR) based on the exponential moving average to facilitate knowledge review at both inter-task and intra-task levels, effectively inheriting learned knowledge. Extensive experimental results demonstrate that our method effectively reduces model communication overhead and alleviates forgetting while fully protecting privacy. With only 1% of the training parameters, we achieve more than 5% accuracy improvements in all settings than SOTA with the same backbone.
3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework that unifies 3D scene reconstruction with semantic understanding. Instead of treating the scene as a unified whole, ObjectGS models individual objects as local anchors that generate neural Gaussians and share object IDs, enabling precise object-level reconstruction. During training, we dynamically grow or prune these anchors and optimize their features, while a one-hot ID encoding with a classification loss enforces clear semantic constraints. We show through extensive experiments that ObjectGS not only outperforms state-of-the-art methods on open-vocabulary and panoptic segmentation tasks, but also integrates seamlessly with applications like mesh extraction and scene editing.
With the scale capability of increasing training data, model size, and computational cost, video generation has achieved impressive results in digital creation, enabling users to express creativity across various domains. Recently, researchers in Large Language Models (LLMs) have expanded the scaling to test-time, which can significantly improve LLM performance by using more inference-time computation. Instead of scaling up video foundation models through expensive training costs, we explore the power of Test-Time Scaling (TTS) in video generation, aiming to answer the question: if a video generation model is allowed to use non-trivial amount of inference-time compute, how much can it improve generation quality given a challenging text prompt. In this work, we reinterpret the test-time scaling of video generation as a searching problem to sample better trajectories from Gaussian noise space to the target video distribution. Specifically, we build the search space with test-time verifiers to provide feedback and heuristic algorithms to guide searching process. Given a text prompt, we first explore an intuitive linear search strategy by increasing noise candidates at inference time. As full-step denoising all frames simultaneously requires heavy test-time computation costs, we further design a more efficient TTS method for video generation called Tree-of-Frames (ToF) that adaptively expands and prunes video branches in an autoregressive manner. Extensive experiments on text-conditioned video generation benchmarks demonstrate that increasing test-time compute consistently leads to significant improvements in the quality of videos.
The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive, leading to growing interest in inference-time scaling to improve performance. Currently, inference-time scaling for text-to-image diffusion models is largely limited to best-of-N sampling, where multiple images are generated per prompt and a selection model chooses the best output. Inspired by the recent success of reasoning models like DeepSeek-R1 in the language domain, we introduce an alternative to naive best-of-N sampling by equipping text-to-image Diffusion Transformers with in-context reflection capabilities. We propose Reflect-DiT, a method that enables Diffusion Transformers to refine their generations using in-context examples of previously generated images alongside textual feedback describing necessary improvements. Instead of passively relying on random sampling and hoping for a better result in a future generation, Reflect-DiT explicitly tailors its generations to address specific aspects requiring enhancement. Experimental results demonstrate that Reflect-DiT improves performance on the GenEval benchmark (+0.19) using SANA-1.0-1.6B as a base model. Additionally, it achieves a new state-of-the-art score of 0.81 on GenEval while generating only 20 samples per prompt, surpassing the previous best score of 0.80, which was obtained using a significantly larger model (SANA-1.5-4.8B) with 2048 samples under the best-of-N approach.
In this paper, we explore the potential of visual in-context learning to enable a single model to handle multiple tasks and adapt to new tasks during test time without re-training. Unlike previous approaches, our focus is on training in-context learners to adapt to sequences of tasks, rather than individual tasks. Our goal is to solve complex tasks that involve multiple intermediate steps using a single model, allowing users to define entire vision pipelines flexibly at test time. To achieve this, we first examine the properties and limitations of visual in-context learning architectures, with a particular focus on the role of codebooks. We then introduce a novel method for training in-context learners using a synthetic compositional task generation engine. This engine bootstraps task sequences from arbitrary segmentation datasets, enabling the training of visual in-context learners for compositional tasks. Additionally, we investigate different masking-based training objectives to gather insights into how to train models better for solving complex, compositional tasks. Our exploration not only provides important insights especially for multi-modal medical task sequences but also highlights challenges that need to be addressed.
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still falling behind with a typical success rate of 30%-50% on challenging benchmarks. Previous studies on fine-tuning MLLMs with synthetic charts are often restricted by their inadequate similarity to the real charts, which could compromise model training and performance on complex real-world charts. In this study, we show that modularizing chart generation and diversifying visual details improves chart understanding capabilities. In particular, we design a five-step data synthesis pipeline, where we separate data and function creation for single plot generation, condition the generation of later subplots on earlier ones for multi-subplot figures, visually diversify the generated figures, filter out low quality data, and finally generate the question-answer (QA) pairs with GPT-4o. This approach allows us to streamline the generation of fine-tuning datasets and introduce the effective chart dataset (ECD), which contains 10k+ chart images and 300k+ QA pairs, covering 25 topics and featuring 250+ chart type combinations with high visual complexity. We show that ECD consistently improves the performance of various MLLMs on a range of real-world and synthetic test sets. Code, data and models are available at: https://github.com/yuweiyang-anu/ECD.
Despite recent progress in diffusion models, generating realistic head portraits from novel viewpoints remains a significant challenge in computer vision. Most current approaches are constrained to limited angular ranges, predominantly focusing on frontal or near-frontal views. Moreover, although the recent emerging large-scale diffusion models have been proven robust in handling 3D scenes, they underperform on facial data, given their complex structure and the uncanny valley pitfalls. In this paper, we propose SpinMeRound, a diffusion-based approach designed to generate consistent and accurate head portraits from novel viewpoints. By leveraging a number of input views alongside an identity embedding, our method effectively synthesizes diverse viewpoints of a subject whilst robustly maintaining its unique identity features. Through experimentation, we showcase our model's generation capabilities in full head synthesis, while beating current state-of-the-art multi-view diffusion models.
Over the last years, 3D morphable models (3DMMs) have emerged as a state-of-the-art methodology for modeling and generating expressive 3D avatars. However, given their reliance on a strict topology, along with their linear nature, they struggle to represent complex full-head shapes. Following the advent of deep implicit functions, we propose imHead, a novel implicit 3DMM that not only models expressive 3D head avatars but also facilitates localized editing of the facial features. Previous methods directly divided the latent space into local components accompanied by an identity encoding to capture the global shape variations, leading to expensive latent sizes. In contrast, we retain a single compact identity space and introduce an intermediate region-specific latent representation to enable local edits. To train imHead, we curate a large-scale dataset of 4K distinct identities, making a step-towards large scale 3D head modeling. Under a series of experiments we demonstrate the expressive power of the proposed model to represent diverse identities and expressions outperforming previous approaches. Additionally, the proposed approach provides an interpretable solution for 3D face manipulation, allowing the user to make localized edits.