Zicheng Liu

Weihao Yu, Zhengyuan Yang, Lingfeng Ren et al. · microsoft-research

MM-Vet, with open-ended vision-language questions targeting at evaluating integrated capabilities, has become one of the most popular benchmarks for large multimodal model evaluation. MM-Vet assesses six core vision-language (VL) capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math. However, its question format is restricted to single image-text pairs, lacking the interleaved image and text sequences prevalent in real-world scenarios. To address this limitation, we introduce MM-Vet v2, which includes a new VL capability called "image-text sequence understanding", evaluating models' ability to process VL sequences. Furthermore, we maintain the high quality of evaluation samples while further expanding the evaluation set size. Using MM-Vet v2 to benchmark large multimodal models, we found that Claude 3.5 Sonnet is the best model with a score of 71.8, slightly outperforming GPT-4o which scored 71.0. Among open-weight models, InternVL2-Llama3-76B leads with a score of 68.4. The code, data, and leaderboard are accessible at https://github.com/yuweihao/MM-Vet.

Yinan Feng, Yinpeng Chen, Shihang Feng et al.

Inversion techniques are widely used to reconstruct subsurface physical properties (e.g., velocity, conductivity) from surface-based geophysical measurements (e.g., seismic, electric/magnetic (EM) data). The problems are governed by partial differential equations (PDEs) like the wave or Maxwell's equations. Solving geophysical inversion problems is challenging due to the ill-posedness and high computational cost. To alleviate those issues, recent studies leverage deep neural networks to learn the inversion mappings from measurements to the property directly. In this paper, we show that such a mapping can be well modeled by a very shallow (but not wide) network with only five layers. This is achieved based on our new finding of an intriguing property: a near-linear relationship between the input and output, after applying integral transform in high dimensional space. In particular, when dealing with the inversion from seismic data to subsurface velocity governed by a wave equation, the integral results of velocity with Gaussian kernels are linearly correlated to the integral of seismic data with sine kernels. Furthermore, this property can be easily turned into a light-weight encoder-decoder network for inversion. The encoder contains the integration of seismic data and the linear transformation without need for fine-tuning. The decoder only consists of a single transformer block to reverse the integral of velocity. Experiments show that this interesting property holds for two geophysics inversion problems over four different datasets. Compared to much deeper InversionNet, our method achieves comparable accuracy, but consumes significantly fewer parameters.

Xingrui Wang, Jiang Liu, Ze Wang et al.

Generating video from various conditions, such as text, image, and audio, enables both spatial and temporal control, leading to high-quality generation results. Videos with dramatic motions often require a higher frame rate to ensure smooth motion. Currently, most audio-to-visual animation models use uniformly sampled frames from video clips. However, these uniformly sampled frames fail to capture significant key moments in dramatic motions at low frame rates and require significantly more memory when increasing the number of frames directly. In this paper, we propose KeyVID, a keyframe-aware audio-to-visual animation framework that significantly improves the generation quality for key moments in audio signals while maintaining computation efficiency. Given an image and an audio input, we first localize keyframe time steps from the audio. Then, we use a keyframe generator to generate the corresponding visual keyframes. Finally, we generate all intermediate frames using the motion interpolator. Through extensive experiments, we demonstrate that KeyVID significantly improves audio-video synchronization and video quality across multiple datasets, particularly for highly dynamic motions. The code is released in https://github.com/XingruiWang/KeyVID.

Hao Chen, Yujin Han, Fangyi Chen et al.

Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain under-explored. Theoretically and empirically, we find that improved generation quality is closely tied to the latent distributions with better structure, such as the ones with fewer Gaussian Mixture modes and more discriminative features. Motivated by these insights, we propose MAETok, an autoencoder (AE) leveraging mask modeling to learn semantically rich latent space while maintaining reconstruction fidelity. Extensive experiments validate our analysis, demonstrating that the variational form of autoencoders is not necessary, and a discriminative latent space from AE alone enables state-of-the-art performance on ImageNet generation using only 128 tokens. MAETok achieves significant practical improvements, enabling a gFID of 1.69 with 76x faster training and 31x higher inference throughput for 512x512 generation. Our findings show that the structure of the latent space, rather than variational constraints, is crucial for effective diffusion models. Code and trained models are released.

Zecheng Tang, Chenfei Wu, Zekai Zhang et al.

To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which is inherently visual semantics rich, naturally compatible with LLMs, and highly compressed. Equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods across various metrics in the vector graphic generation task. Besides, StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.

Taewook Kim, Ze Wang, Zhengyuan Yang et al.

Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle with precisely rendering subjects, such as text spelling. To address this challenge, this paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. In addition, this reference condition empowers the model to be conditioned in ways that the vocabularies of the text tokenizer cannot adequately represent, and further extends the model's generalization to novel capabilities such as generating non-English text spellings. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Each plugin is trained with auxiliary networks and loss functions customized for applications such as English scene-text generation, multi-lingual scene-text generation, and logo-image generation. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.

Yutong Du, Zicheng Liu

Deep neural networks (DNNs) have recently been applied to inverse scattering problems (ISPs) due to their strong nonlinear mapping capabilities. However, supervised DNN solvers require large-scale datasets, which limits their generalization in practical applications. Untrained neural networks (UNNs) address this issue by updating weights from measured electric fields and prior physical knowledge, but existing UNN solvers suffer from long inference time. To overcome these limitations, this paper proposes a contrast-source-based physics-driven neural network (CSPDNN), which predicts the induced current distribution to improve efficiency and incorporates an adaptive total variation loss for robust reconstruction under varying contrast and noise conditions. The improved imaging performance is validated through comprehensive numerical simulations and experimental data.

Xingrui Wang, Jiang Liu, Chao Huang et al.

Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-modal question-answering ability, it remains unclear whether OLLMs achieve modality-invariant reasoning or exhibit modality-specific biases. We introduce XModBench, a large-scale tri-modal benchmark explicitly designed to measure cross-modal consistency. XModBench comprises 60,828 multiple-choice questions spanning five task families and systematically covers all six modality compositions in question-answer pairs, enabling fine-grained diagnosis of an OLLM's modality-invariant reasoning, modality disparity, and directional imbalance. Experiments show that even the strongest model, Gemini 2.5 Pro, (i) struggles with spatial and temporal reasoning, achieving less than 60% accuracy, (ii) reveals persistent modality disparities, with performance dropping substantially when the same semantic content is conveyed through audio rather than text, and (iii) shows systematic directional imbalance, exhibiting lower consistency when vision serves as context compared to text. These findings indicate that current OLLMs remain far from truly modality-invariant reasoning and position XModBench as a fundamental diagnostic tool for evaluating and improving cross-modal competence. All data and evaluation tools will be available at https://xingruiwang.github.io/projects/XModBench/.

Yinpeng Chen, Xiyang Dai, Dongdong Chen et al.

This paper introduces a novel mathematical property applicable to diverse images, referred to as FINOLA (First-Order Norm+Linear Autoregressive). FINOLA represents each image in the latent space as a first-order autoregressive process, in which each regression step simply applies a shared linear model on the normalized value of its immediate neighbor. This intriguing property reveals a mathematical invariance that transcends individual images. Expanding from image grids to continuous coordinates, we unveil the presence of two underlying partial differential equations. We validate the FINOLA property from two distinct angles: image reconstruction and self-supervised learning. Firstly, we demonstrate the ability of FINOLA to auto-regress up to a 256x256 feature map (the same resolution to the image) from a single vector placed at the center, successfully reconstructing the original image by only using three 3x3 convolution layers as decoder. Secondly, we leverage FINOLA for self-supervised learning by employing a simple masked prediction approach. Encoding a single unmasked quadrant block, we autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves highly effective in image classification and object detection tasks, even when integrated into lightweight networks, all without the need for extensive fine-tuning. The code will be made publicly available.

Zicheng Liu, Mayank Roy, Dilip K. Prasad et al.

Solving electromagnetic inverse scattering problems (ISPs) is challenging due to the intrinsic nonlinearity, ill-posedness, and expensive computational cost. Recently, deep neural network (DNN) techniques have been successfully applied on ISPs and shown potential of superior imaging over conventional methods. In this paper, we analyse the analogy between DNN solvers and traditional iterative algorithms and discuss how important physical phenomena cannot be effectively incorporated in the training process. We show the importance of including near-field priors in the learning process of DNNs. To this end, we propose new designs of loss functions which incorporate multiple-scattering based near-field quantities (such as scattered fields or induced currents within domain of interest). Effects of physics-guided loss functions are studied using a variety of numerical experiments. Pros and cons of the investigated ISP solvers with different loss functions are summarized.

Yifeng Zhao, Zicheng Liu, Pei Zhang et al.

A better understanding of dispersion in natural streams requires knowledge of longitudinal dispersion coefficient(LDC). Various methods have been proposed for predictions of LDC. Those studies can be grouped into three types: analytical, statistical and ML-driven researches(Implicit and explicit). However, a comprehensive evaluation of them is still lacking. In this paper, we first present an in-depth analysis of those methods and find out their defects. This is carried out on an extensive database composed of 660 samples of hydraulic and channel properties worldwide. The reliability and representativeness of utilized data are enhanced through the deployment of the Subset Selection of Maximum Dissimilarity(SSMD) for testing set selection and the Inter Quartile Range(IQR) for removal of the outlier. The evaluation reveals the rank of those methods as: ML-driven method > the statistical method > the analytical method. Whereas implicit ML-driven methods are black-boxes in nature, explicit ML-driven methods have more potential in prediction of LDC. Besides, overfitting is a universal problem in existing models. Those models also suffer from a fixed parameter combination. To establish an interpretable model for LDC prediction with higher performance, we then design a novel symbolic regression method called evolutionary symbolic regression network(ESRN). It is a combination of genetic algorithms and neural networks. Strategies are introduced to avoid overfitting and explore more parameter combinations. Results show that the ESRN model has superiorities over other existing symbolic models in performance. The proposed model is suitable for practical engineering problems due to its advantage in low requirement of parameters (only w and U* are required). It can provide convincing solutions for situations where the field test cannot be carried out or limited field information can be obtained.

Lirong Wu, Zicheng Liu, Zelin Zang et al.

Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space. In this paper, we propose a novel Generalized Clustering and Multi-manifold Learning (GCML) framework with geometric structure preservation for generalized data, i.e., not limited to 2-D image data and has a wide range of applications in speech, text, and biology domains. In the proposed framework, manifold clustering is done in the latent space guided by a clustering loss. To overcome the problem that the clustering-oriented loss may deteriorate the geometric structure of the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally. Extensive experimental results have shown that GCML exhibits superior performance to counterparts in terms of qualitative visualizations and quantitative metrics, which demonstrates the effectiveness of preserving geometric structure.