Yiyuan Zhang

Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang et al. · berkeley

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input data from various modalities are mapped into a shared token space, allowing a subsequent encoder with frozen parameters to extract high-level semantic features of the input data. Composed of three main components: a unified data tokenizer, a modality-shared encoder, and task-specific heads for downstream tasks, Meta-Transformer is the first framework to perform unified learning across 12 modalities with unpaired data. Experiments on different benchmarks reveal that Meta-Transformer can handle a wide range of tasks including fundamental perception (text, image, point cloud, audio, video), practical application (X-Ray, infrared, hyperspectral, and IMU), and data mining (graph, tabular, and time-series). Meta-Transformer indicates a promising future for developing unified multimodal intelligence with transformers. Code will be available at https://github.com/invictus717/MetaTransformer

Yiyuan Zhang, Kaixiong Gong, Xiaohan Ding et al. · berkeley

We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures. The core idea of UniDG is to finetune models during the inference stage, which saves the cost of iterative training. Specifically, we encourage models to learn the distribution of test data in an unsupervised manner and impose a penalty regarding the updating step of model parameters. The penalty term can effectively reduce the catastrophic forgetting issue as we would like to maximally preserve the valuable knowledge in the original model. Empirically, across 12 visual backbones, including CNN-, MLP-, and Transformer-based models, ranging from 1.89M to 303M parameters, UniDG shows an average accuracy improvement of +5.4% on DomainBed. These performance results demonstrate the superiority and versatility of UniDG. The code is publicly available at https://github.com/invictus717/UniDG

Xiaohan Ding, Yiyuan Zhang, Yixiao Ge et al. · tencent-ai

Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we contribute from two aspects. 1) We propose four architectural guidelines for designing large-kernel ConvNets, the core of which is to exploit the essential characteristics of large kernels that distinguish them from small kernels - they can see wide without going deep. Following such guidelines, our proposed large-kernel ConvNet shows leading performance in image recognition (ImageNet accuracy of 88.0%, ADE20K mIoU of 55.6%, and COCO box AP of 56.4%), demonstrating better performance and higher speed than the recent powerful competitors. 2) We discover large kernels are the key to unlocking the exceptional performance of ConvNets in domains where they were originally not proficient. With certain modality-related preprocessing approaches, the proposed model achieves state-of-the-art performance on time-series forecasting and audio recognition tasks even without modality-specific customization to the architecture. All the code and models are publicly available on GitHub and Huggingface.

Jiaming Han, Kaixiong Gong, Yiyuan Zhang et al.

Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and are limited to common modalities. In this paper, we present OneLLM, an MLLM that aligns eight modalities to language using a unified framework. We achieve this through a unified multimodal encoder and a progressive multimodal alignment pipeline. In detail, we first train an image projection module to connect a vision encoder with LLM. Then, we build a universal projection module (UPM) by mixing multiple image projection modules and dynamic routing. Finally, we progressively align more modalities to LLM with the UPM. To fully leverage the potential of OneLLM in following instructions, we also curated a comprehensive multimodal instruction dataset, including 2M items from image, audio, video, point cloud, depth/normal map, IMU and fMRI brain activity. OneLLM is evaluated on 25 diverse benchmarks, encompassing tasks such as multimodal captioning, question answering and reasoning, where it delivers excellent performance. Code, data, model and online demo are available at https://github.com/csuhan/OneLLM

Zhixin Zhang, Yiyuan Zhang, Xiaohan Ding et al.

The construction of online vectorized High-Definition (HD) maps is critical for downstream prediction and planning. Recent efforts have built strong baselines for this task, however, shapes and relations of instances in urban road systems are still under-explored, such as parallelism, perpendicular, or rectangle-shape. In our work, we propose GeMap ($\textbf{Ge}$ometry $\textbf{Map}$), which end-to-end learns Euclidean shapes and relations of map instances beyond basic perception. Specifically, we design a geometric loss based on angle and distance clues, which is robust to rigid transformations. We also decouple self-attention to independently handle Euclidean shapes and relations. Our method achieves new state-of-the-art performance on the NuScenes and Argoverse 2 datasets. Remarkably, it reaches a 71.8% mAP on the large-scale Argoverse 2 dataset, outperforming MapTR V2 by +4.4% and surpassing the 70% mAP threshold for the first time. Code is available at https://github.com/cnzzx/GeMap.

Kaituo Feng, Manyuan Zhang, Hongyu Li et al.

Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatility and hinders potential knowledge sharing across tasks and modalities. To this end, we propose OneThinker, an all-in-one reasoning model that unifies image and video understanding across diverse fundamental visual tasks, including question answering, captioning, spatial and temporal grounding, tracking, and segmentation. To achieve this, we construct the OneThinker-600k training corpus covering all these tasks and employ commercial models for CoT annotation, resulting in OneThinker-SFT-340k for SFT cold start. Furthermore, we propose EMA-GRPO to handle reward heterogeneity in multi-task RL by tracking task-wise moving averages of reward standard deviations for balanced optimization. Extensive experiments on diverse visual benchmarks show that OneThinker delivers strong performance on 31 benchmarks, across 10 fundamental visual understanding tasks. Moreover, it exhibits effective knowledge transfer between certain tasks and preliminary zero-shot generalization ability, marking a step toward a unified multimodal reasoning generalist. All code, model, and data are released.

Yiyuan Zhang, Yuhao Kang, Zhixin Zhang et al.

We introduce $\textit{InteractiveVideo}$, a user-centric framework for video generation. Different from traditional generative approaches that operate based on user-provided images or text, our framework is designed for dynamic interaction, allowing users to instruct the generative model through various intuitive mechanisms during the whole generation process, e.g. text and image prompts, painting, drag-and-drop, etc. We propose a Synergistic Multimodal Instruction mechanism, designed to seamlessly integrate users' multimodal instructions into generative models, thus facilitating a cooperative and responsive interaction between user inputs and the generative process. This approach enables iterative and fine-grained refinement of the generation result through precise and effective user instructions. With $\textit{InteractiveVideo}$, users are given the flexibility to meticulously tailor key aspects of a video. They can paint the reference image, edit semantics, and adjust video motions until their requirements are fully met. Code, models, and demo are available at https://github.com/invictus717/InteractiveVideo

Yiyuan Zhang, Wei Fan

The potential of artificial upwelling (AU) as a means of lifting nutrient-rich bottom water to the surface, stimulating seaweed growth, and consequently enhancing ocean carbon sequestration, has been gaining increasing attention in recent years. This has led to the development of the first solar-powered and air-lifted AU system (AUS) in China. However, efficient scheduling of air injection systems in complex marine environments remains a crucial challenge in operating AUS, as it holds the potential to significantly improve energy efficiency. To tackle this challenge, we propose a novel energy management approach that utilizes deep reinforcement learning (DRL) algorithm to develop efficient strategies for operating AUS. Specifically, we formulate the problem of maximizing the energy efficiency of AUS as a Markov decision process and integrate the quantile network in distributional reinforcement learning (QR-DQN) with the deep dueling network to solve it. Through extensive simulations, we evaluate the performance of our algorithm and demonstrate its superior effectiveness over traditional rule-based approaches and other DRL algorithms in reducing energy wastage while ensuring the stable and efficient operation of AUS. Our findings suggest that a DRL-based approach offers a promising way to improve the energy efficiency of AUS and enhance the sustainability of seaweed cultivation and carbon sequestration in the ocean.

Langyu Wang, Bingke Zhu, Yingying Chen et al.

The weakly-supervised audio-visual video parsing (AVVP) aims to predict all modality-specific events and locate their temporal boundaries. Despite significant progress, due to the limitations of the weakly-supervised and the deficiencies of the model architecture, existing methods are lacking in simultaneously improving both the segment-level prediction and the event-level prediction. In this work, we propose a audio-visual Mamba network with pseudo labeling aUGmentation (MUG) for emphasising the uniqueness of each segment and excluding the noise interference from the alternate modalities. Specifically, we annotate some of the pseudo-labels based on previous work. Using unimodal pseudo-labels, we perform cross-modal random combinations to generate new data, which can enhance the model's ability to parse various segment-level event combinations. For feature processing and interaction, we employ a audio-visual mamba network. The AV-Mamba enhances the ability to perceive different segments and excludes additional modal noise while sharing similar modal information. Our extensive experiments demonstrate that MUG improves state-of-the-art results on LLP dataset in all metrics (e.g,, gains of 2.1% and 1.2% in terms of visual Segment-level and audio Segment-level metrics). Our code is available at https://github.com/WangLY136/MUG.

Dong Guo, Faming Wu, Feida Zhu et al. · pku

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

Haoran Hao, Jiaming Han, Yiyuan Zhang et al. · cmu

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast amount of information within the video. Although some recent methods are designed for long video understanding, they often lose crucial information during token compression and struggle with additional modality like audio. In this work, we propose a dynamic long video encoding method utilizing the temporal relationship between frames, named Temporal Dynamic Context (TDC). Firstly, we segment the video into semantically consistent scenes based on inter-frame similarities, then encode each frame into tokens using visual-audio encoders. Secondly, we propose a novel temporal context compressor to reduce the number of tokens within each segment. Specifically, we employ a query-based Transformer to aggregate video, audio, and instruction text tokens into a limited set of temporal context tokens. Finally, we feed the static frame tokens and the temporal context tokens into the LLM for video understanding. Furthermore, to handle extremely long videos, we propose a training-free chain-of-thought strategy that progressively extracts answers from multiple video segments. These intermediate answers serve as part of the reasoning process and contribute to the final answer. We conduct extensive experiments on general video understanding and audio-video understanding benchmarks, where our method demonstrates strong performance. The code and models are available at https://github.com/Hoar012/TDC-Video.

Yiyuan Zhang, Handong Li, Jing Liu et al.

We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up the numbers of modalities and amount of data, together with the model parameters, in the pretraining process. With MiCo, the pretrained models show significant emergent abilities in multimodal learning, which are evaluated on the following tasks: i) single-modality perception benchmarks of 10 different modalities, ii) 25 cross-modality understanding tasks of retrieval, question-answering, captioning, and iii) 18 multimodal large language model benchmarks. Our models establish 37 new records for state-of-the-art performance. We hope that our research could contribute to the development of omni-modal intelligence. Code and Models are at https://github.com/invictus717/MiCo

Yiyuan Zhang, Xiaohan Ding, Kaixiong Gong et al.

We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target modality are irrelevant to the other modalities, which distinguishes our method from other works utilizing paired (e.g., CLIP) or interleaved data of different modalities. We propose a methodology named Multimodal Pathway - given a target modality and a transformer designed for it, we use an auxiliary transformer trained with data of another modality and construct pathways to connect components of the two models so that data of the target modality can be processed by both models. In this way, we utilize the universal sequence-to-sequence modeling abilities of transformers obtained from two modalities. As a concrete implementation, we use a modality-specific tokenizer and task-specific head as usual but utilize the transformer blocks of the auxiliary model via a proposed method named Cross-Modal Re-parameterization, which exploits the auxiliary weights without any inference costs. On the image, point cloud, video, and audio recognition tasks, we observe significant and consistent performance improvements with irrelevant data from other modalities. The code and models are available at https://github.com/AILab-CVC/M2PT.

Yiyuan Zhang, Anye Zhong, Junkai Chen et al.

Cephalopod pulsed-jet locomotion is not a single isolated expulsion event, but a coordinated cycle involving jet expulsion, passive gliding, and mantle refilling. Inspired by this cycle-resolved biological strategy, this paper presents a cephalopod-inspired pulsed-jet robot with a rigid-soft hybrid origami mantle that enables large, actively driven, and geometry-guided body deformation. The proposed mantle integrates rigid folding panels with a compliant silicone framework, allowing a 75% effective cavity-volume reduction during expulsion and reducing the projected cross-sectional drag area by approximately 75.7% in the contracted gliding configuration. Using this platform, we formulate a cycle-resolved framework to separately investigate how expelled volume, glide duration, and refill pathway influence whole-cycle locomotion performance. Experiments show that the robot reaches a peak speed of approximately 0.5 m/s (3.8 BL/s) and an average speed exceeding 0.2 m/s (1.5 BL/s) within the first jetting cycle. The results further demonstrate the roles of high expelled-volume-ratio contraction in speed generation, reduced-drag-area gliding under different glide durations, and mantle-aperture-inspired passive inlet valves in assisting refill. This work provides both a robotic implementation of actively deformable cephalopod-like jet propulsion and a unified experimental platform for studying expulsion-gliding-refilling dynamics in pulsed-jet locomotion.

Lihe Ding, Shaocong Dong, Zhanpeng Huang et al.

Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion(BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D model and efficiency of optimization, reducing the generation process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation. Project website: https://bidiff.github.io/.

Zhixin Zhang, Yiyuan Zhang, Xiaohan Ding et al.

Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before. This challenge is particularly pronounced for large vision-language models (VLMs): if the model has not been exposed to the object depicted in an image, it struggles to generate reliable answers to the user's question regarding that image. Moreover, as new objects and events continuously emerge, frequently updating VLMs is impractical due to heavy computational burdens. To address this limitation, we propose Vision Search Assistant, a novel framework that facilitates collaboration between VLMs and web agents. This approach leverages VLMs' visual understanding capabilities and web agents' real-time information access to perform open-world Retrieval-Augmented Generation via the web. By integrating visual and textual representations through this collaboration, the model can provide informed responses even when the image is novel to the system. Extensive experiments conducted on both open-set and closed-set QA benchmarks demonstrate that the Vision Search Assistant significantly outperforms the other models and can be widely applied to existing VLMs.

Handong Li, Yiyuan Zhang, Longteng Guo et al.

Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, this approach incurs high computational costs, introduces resolution biases, and struggles to capture fine-grained multimodal interactions. To overcome these limitations, we propose ELVA, an encoder-free Video-LLM that directly models nuanced video-language interactions without relying on a vision encoder. ELVA employs token merging to construct a bottom-up hierarchical representation and incorporates a video guidance supervisor for direct spatiotemporal representation learning. Additionally, a hybrid-resolution mechanism strategically integrates high- and low-resolution frames as inputs to achieve an optimal balance between performance and efficiency. With only 7M publicly available video-text pairs, ELVA achieves performance on par with encoder-based Video-LLMs while reducing FLOPs by up to 95\% and inference latency by 92\%, offering a scalable and efficient solution for real-time video understanding.

Zidong Wang, Yiyuan Zhang, Xiaoyu Yue et al.

A fundamental dilemma in generative modeling persists: iterative diffusion models achieve outstanding fidelity, but at a significant computational cost, while efficient few-step alternatives are constrained by a hard quality ceiling. This conflict between generation steps and output quality arises from restrictive training objectives that focus exclusively on either infinitesimal dynamics (PF-ODEs) or direct endpoint prediction. We address this challenge by introducing an exact, continuous-time dynamics equation that analytically defines state transitions across any finite time interval. This leads to a novel generative paradigm, Transition Models (TiM), which adapt to arbitrary-step transitions, seamlessly traversing the generative trajectory from single leaps to fine-grained refinement with more steps. Despite having only 865M parameters, TiM achieves state-of-the-art performance, surpassing leading models such as SD3.5 (8B parameters) and FLUX.1 (12B parameters) across all evaluated step counts. Importantly, unlike previous few-step generators, TiM demonstrates monotonic quality improvement as the sampling budget increases. Additionally, when employing our native-resolution strategy, TiM delivers exceptional fidelity at resolutions up to 4096x4096.

Zidong Wang, Lei Bai, Xiangyu Yue et al.

We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of conventional fixed-resolution, square-image methods by natively handling variable-length visual tokens, a core challenge for traditional techniques. To this end, we introduce the Native-resolution diffusion Transformer (NiT), an architecture designed to explicitly model varying resolutions and aspect ratios within its denoising process. Free from the constraints of fixed formats, NiT learns intrinsic visual distributions from images spanning a broad range of resolutions and aspect ratios. Notably, a single NiT model simultaneously achieves the state-of-the-art performance on both ImageNet-256x256 and 512x512 benchmarks. Surprisingly, akin to the robust zero-shot capabilities seen in advanced large language models, NiT, trained solely on ImageNet, demonstrates excellent zero-shot generalization performance. It successfully generates high-fidelity images at previously unseen high resolutions (e.g., 1536 x 1536) and diverse aspect ratios (e.g., 16:9, 3:1, 4:3), as shown in Figure 1. These findings indicate the significant potential of native-resolution modeling as a bridge between visual generative modeling and advanced LLM methodologies.

Yilei Jiang, Weihong Li, Yiyuan Zhang et al.

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applications, these biases could perpetuate a distorted worldview and hinder opportunities for minority groups. Existing methods on debiasing DMs usually requires model retraining with a human-crafted reference dataset or additional classifiers, which suffer from two major limitations: (1) collecting reference datasets causes expensive annotation cost; (2) the debiasing performance is heavily constrained by the quality of the reference dataset or the additional classifier. To address the above limitations, we propose FairGen, a plug-and-play method that learns attribute latent directions in a self-discovering manner, thus eliminating the reliance on such reference dataset. Specifically, FairGen consists of two parts: a set of attribute adapters and a distribution indicator. Each adapter in the set aims to learn an attribute latent direction, and is optimized via noise composition through a self-discovering process. Then, the distribution indicator is multiplied by the set of adapters to guide the generation process towards the prescribed distribution. Our method enables debiasing multiple attributes in DMs simultaneously, while remaining lightweight and easily integrable with other DMs, eliminating the need for retraining. Extensive experiments on debiasing gender, racial, and their intersectional biases show that our method outperforms previous SOTA by a large margin.

Chenrui Zhang, Yiyuan Zhang, Yunfei Ye et al.

Underwater robots are widely deployed for ocean exploration and manipulation. Underactuated mechanisms are particularly advantageous in aquatic environments, as reducing actuator count lowers the risk of motor leakage while introducing inherent mechanical compliance. However, accurate modeling of underwater underactuated and soft robotic systems remains challenging because it requires identifying a high-dimensional set of internal structural and external hydrodynamic parameters. In this work, we propose a trajectory-driven global optimization framework for unified structural-hydrodynamic modeling of underwater multibody systems. Inspired by the Covariance Matrix Adaptation Evolution Strategy (CMA-ES), the proposed approach simultaneously identifies coupled internal elastic, damping, and distributed hydrodynamic parameters through trajectory-level matching between simulation and experimental motion. This enables high-fidelity reproduction of both underactuated mechanisms and compliant soft robotic systems in underwater environments. We first validate the framework on a link-by-link underactuated multibody mechanism, demonstrating accurate identification of distributed hydrodynamic coefficients, with a normalized end effector position error below 5% across multiple trajectories, varying initial conditions, and both active-passive and fully passive configurations. The identified modeling strategy is then transferred to a single octopus-inspired soft arm, showing strong real-to-sim consistency without manual retuning. Finally, eight identified arms are assembled into a swimming octopus robot, where the unified parameter set enables realistic whole body behavior without additional parameter calibration. These results demonstrate the scalability and transferability of the proposed structural-hydrodynamic modeling framework across underwater underactuated and soft robotic systems.