Fengda Zhu

Xiwen Liang, Fengda Zhu, Lingling Li et al.

Vision-language navigation (VLN) is a challenging task due to its large searching space in the environment. To address this problem, previous works have proposed some methods of fine-tuning a large model that pretrained on large-scale datasets. However, the conventional fine-tuning methods require extra human-labeled navigation data and lack self-exploration capabilities in environments, which hinders their generalization of unseen scenes. To improve the ability of fast cross-domain adaptation, we propose Prompt-based Environmental Self-exploration (ProbES), which can self-explore the environments by sampling trajectories and automatically generates structured instructions via a large-scale cross-modal pretrained model (CLIP). Our method fully utilizes the knowledge learned from CLIP to build an in-domain dataset by self-exploration without human labeling. Unlike the conventional approach of fine-tuning, we introduce prompt-based learning to achieve fast adaptation for language embeddings, which substantially improves the learning efficiency by leveraging prior knowledge. By automatically synthesizing trajectory-instruction pairs in any environment without human supervision and efficient prompt-based learning, our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE. Both qualitative and quantitative results show that our ProbES significantly improves the generalization ability of the navigation model.

Pengzhen Ren, Kaidong Zhang, Hetao Zheng et al.

Considering how to make the model accurately understand and follow natural language instructions and perform actions consistent with world knowledge is a key challenge in robot manipulation. This mainly includes human fuzzy instruction reasoning and the following of physical knowledge. Therefore, the embodied intelligence agent must have the ability to model world knowledge from training data. However, most existing vision and language robot manipulation methods mainly operate in less realistic simulator and language settings and lack explicit modeling of world knowledge. To bridge this gap, we introduce a novel and simple robot manipulation framework, called Surfer. It is based on the world model, treats robot manipulation as a state transfer of the visual scene, and decouples it into two parts: action and scene. Then, the generalization ability of the model on new instructions and new scenes is enhanced by explicit modeling of the action and scene prediction in multi-modal information. In addition to the framework, we also built a robot manipulation simulator that supports full physics execution based on the MuJoCo physics engine. It can automatically generate demonstration training data and test data, effectively reducing labor costs. To conduct a comprehensive and systematic evaluation of the robot manipulation model in terms of language understanding and physical execution, we also created a robotic manipulation benchmark with progressive reasoning tasks, called SeaWave. It contains 4 levels of progressive reasoning tasks and can provide a standardized testing platform for embedded AI agents in multi-modal environments. On average, Surfer achieved a success rate of 54.74% on the defined four levels of manipulation tasks, exceeding the best baseline performance of 47.64%.

Jinlai Liu, Jian Han, Bin Yan et al.

We introduce InfinityStar, a unified spacetime autoregressive framework for high-resolution image and dynamic video synthesis. Building on the recent success of autoregressive modeling in both vision and language, our purely discrete approach jointly captures spatial and temporal dependencies within a single architecture. This unified design naturally supports a variety of generation tasks such as text-to-image, text-to-video, image-to-video, and long interactive video synthesis via straightforward temporal autoregression. Extensive experiments demonstrate that InfinityStar scores 83.74 on VBench, outperforming all autoregressive models by large margins, even surpassing some diffusion competitors like HunyuanVideo. Without extra optimizations, our model generates a 5s, 720p video approximately 10x faster than leading diffusion-based methods. To our knowledge, InfinityStar is the first discrete autoregressive video generator capable of producing industrial level 720p videos. We release all code and models to foster further research in efficient, high-quality video generation.

Yifu Zhang, Hao Yang, Yuqi Zhang et al.

We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.

Chong Liu, Fengda Zhu, Xiaojun Chang et al.

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark. The code have released: https://github.com/LCFractal/VLNREM.

Shoufa Chen, Chongjian Ge, Yuqi Zhang et al.

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality visual generation, including the data curation pipeline, model architecture design, flow formulation, and advanced infrastructure for efficient and robust large-scale training. The Goku models demonstrate superior performance in both qualitative and quantitative evaluations, setting new benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and 83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for text-to-video tasks. We believe that this work provides valuable insights and practical advancements for the research community in developing joint image-and-video generation models.

Bingqian Lin, Yanxin Long, Yi Zhu et al.

Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. Despite significant advances, conventional VLN agents are trained typically under disturbance-free environments and may easily fail in real-world scenarios, since they are unaware of how to deal with various possible disturbances, such as sudden obstacles or human interruptions, which widely exist and may usually cause an unexpected route deviation. In this paper, we present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents, by requiring them to learn towards deviation-robust navigation. Specifically, a simple yet effective path perturbation scheme is introduced to implement the route deviation, with which the agent is required to still navigate successfully following the original instruction. Since directly enforcing the agent to learn perturbed trajectories may lead to inefficient training, a progressively perturbed trajectory augmentation strategy is designed, where the agent can self-adaptively learn to navigate under perturbation with the improvement of its navigation performance for each specific trajectory. For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts. Extensive experiments on R2R show that PROPER can benefit multiple VLN baselines in perturbation-free scenarios. We further collect the perturbed path data to construct an introspection subset based on the R2R, called Path-Perturbed R2R (PP-R2R). The results on PP-R2R show unsatisfying robustness of popular VLN agents and the capability of PROPER in improving the navigation robustness.

Xiwen Liang, Fengda Zhu, Yi Zhu et al.

The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to discriminate the similarities and discrepancies across instruction-trajectory pairs and ignore the temporal continuity of sub-instructions. These problems hinder agents from learning distinctive vision-and-language representations, harming the robustness and generalizability of the navigation policy. In this paper, we propose a Contrastive Instruction-Trajectory Learning (CITL) framework that explores invariance across similar data samples and variance across different ones to learn distinctive representations for robust navigation. Specifically, we propose: (1) a coarse-grained contrastive learning objective to enhance vision-and-language representations by contrasting semantics of full trajectory observations and instructions, respectively; (2) a fine-grained contrastive learning objective to perceive instructions by leveraging the temporal information of the sub-instructions; (3) a pairwise sample-reweighting mechanism for contrastive learning to mine hard samples and hence mitigate the influence of data sampling bias in contrastive learning. Our CITL can be easily integrated with VLN backbones to form a new learning paradigm and achieve better generalizability in unseen environments. Extensive experiments show that the model with CITL surpasses the previous state-of-the-art methods on R2R, R4R, and RxR.

Fengda Zhu, Yi Zhu, Vincent CS Lee et al.

"Embodied visual navigation" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in autonomous driving, vacuum cleaner, and rescue robot. A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc. Building such an agent that observes, thinks, and acts is a key to real intelligence. The remarkable learning ability of deep learning methods empowered the agents to accomplish embodied visual navigation tasks. Despite this, embodied visual navigation is still in its infancy since a lot of advanced skills are required, including perceiving partially observed visual input, exploring unseen areas, memorizing and modeling seen scenarios, understanding cross-modal instructions, and adapting to a new environment, etc. Recently, embodied visual navigation has attracted rising attention of the community, and numerous works has been proposed to learn these skills. This paper attempts to establish an outline of the current works in the field of embodied visual navigation by providing a comprehensive literature survey. We summarize the benchmarks and metrics, review different methods, analysis the challenges, and highlight the state-of-the-art methods. Finally, we discuss unresolved challenges in the field of embodied visual navigation and give promising directions in pursuing future research.

Fengda Zhu, Xiwen Liang, Yi Zhu et al.

The ability to navigate like a human towards a language-guided target from anywhere in a 3D embodied environment is one of the 'holy grail' goals of intelligent robots. Most visual navigation benchmarks, however, focus on navigating toward a target from a fixed starting point, guided by an elaborate set of instructions that depicts step-by-step. This approach deviates from real-world problems in which human-only describes what the object and its surrounding look like and asks the robot to start navigation from anywhere. Accordingly, in this paper, we introduce a Scenario Oriented Object Navigation (SOON) task. In this task, an agent is required to navigate from an arbitrary position in a 3D embodied environment to localize a target following a scene description. To give a promising direction to solve this task, we propose a novel graph-based exploration (GBE) method, which models the navigation state as a graph and introduces a novel graph-based exploration approach to learn knowledge from the graph and stabilize training by learning sub-optimal trajectories. We also propose a new large-scale benchmark named From Anywhere to Object (FAO) dataset. To avoid target ambiguity, the descriptions in FAO provide rich semantic scene information includes: object attribute, object relationship, region description, and nearby region description. Our experiments reveal that the proposed GBE outperforms various state-of-the-arts on both FAO and R2R datasets. And the ablation studies on FAO validates the quality of the dataset.

Siyi Hu, Fengda Zhu, Xiaojun Chang et al.

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions. This hinders the experience accumulation and transfer of the learned agent over tasks with diverse levels of difficulty (e.g. 3 vs 3 or 5 vs 6 multi-agent games). In this paper, we make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks with the requirement of different observation and action configurations. Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy by decoupling the policy distribution from the intertwined input observation with an importance weight measured by the merits of the self-attention mechanism. Compared to a standard transformer block, the proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable. UPDeT is general enough to be plugged into any multi-agent reinforcement learning pipeline and equip them with strong generalization abilities that enables the handling of multiple tasks at a time. Extensive experiments on large-scale SMAC multi-agent competitive games demonstrate that the proposed UPDeT-based multi-agent reinforcement learning achieves significant results relative to state-of-the-art approaches, demonstrating advantageous transfer capability in terms of both performance and training speed (10 times faster).

Yi Zhu, Fengda Zhu, Zhaohuan Zhan et al.

Vision-dialog navigation posed as a new holy-grail task in vision-language disciplinary targets at learning an agent endowed with the capability of constant conversation for help with natural language and navigating according to human responses. Besides the common challenges faced in visual language navigation, vision-dialog navigation also requires to handle well with the language intentions of a series of questions about the temporal context from dialogue history and co-reasoning both dialogs and visual scenes. In this paper, we propose the Cross-modal Memory Network (CMN) for remembering and understanding the rich information relevant to historical navigation actions. Our CMN consists of two memory modules, the language memory module (L-mem) and the visual memory module (V-mem). Specifically, L-mem learns latent relationships between the current language interaction and a dialog history by employing a multi-head attention mechanism. V-mem learns to associate the current visual views and the cross-modal memory about the previous navigation actions. The cross-modal memory is generated via a vision-to-language attention and a language-to-vision attention. Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step. Experiments on the CVDN dataset show that our CMN outperforms the previous state-of-the-art model by a significant margin on both seen and unseen environments.

Fengda Zhu, Yi Zhu, Xiaojun Chang et al.

Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit the vision and language features in cross-modal grounding. However, the VLN task remains challenging, since previous works have neglected the rich semantic information contained in the environment (such as implicit navigation graphs or sub-trajectory semantics). In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to take advantage of the additional training signals derived from the semantic information. The auxiliary tasks have four reasoning objectives: explaining the previous actions, estimating the navigation progress, predicting the next orientation, and evaluating the trajectory consistency. As a result, these additional training signals help the agent to acquire knowledge of semantic representations in order to reason about its activity and build a thorough perception of the environment. Our experiments indicate that auxiliary reasoning tasks improve both the performance of the main task and the model generalizability by a large margin. Empirically, we demonstrate that an agent trained with self-supervised auxiliary reasoning tasks substantially outperforms the previous state-of-the-art method, being the best existing approach on the standard benchmark.

Fengda Zhu, Xiaojun Chang, Runhao Zeng et al.

Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge it learned in the past when trained on a new task. We consider this challenge from two perspectives: i) acquiring task-specific skills is difficult since task information and rewards are not highly related; ii) learning knowledge from previous experience is difficult in continuous control domains. In this paper, we introduce an end-to-end framework namely Continual Diversity Adversarial Network (CDAN). We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective. Then, we propose an adversarial self-correction mechanism to learn knowledge by exploiting past experience. The two learning procedures are presumably reciprocal. To evaluate the proposed method, we propose a new continuous reinforcement learning environment named Continual Ant Maze (CAM) and a new metric termed Normalized Shorten Distance (NSD). The experimental results confirm the effectiveness of diversity exploration and self-correction. It is worthwhile noting that our final result outperforms baseline by 18.35% in terms of NSD, and 0.61 according to the average reward.

Fengda Zhu, Linchao Zhu, Yi Yang

There has been an increasing interest in 3D indoor navigation, where a robot in an environment moves to a target according to an instruction. To deploy a robot for navigation in the physical world, lots of training data is required to learn an effective policy. It is quite labour intensive to obtain sufficient real environment data for training robots while synthetic data is much easier to construct by rendering. Though it is promising to utilize the synthetic environments to facilitate navigation training in the real world, real environment are heterogeneous from synthetic environment in two aspects. First, the visual representation of the two environments have significant variances. Second, the houseplans of these two environments are quite different. Therefore two types of information, i.e. visual representation and policy behavior, need to be adapted in the reinforcement model. The learning procedure of visual representation and that of policy behavior are presumably reciprocal. We propose to jointly adapt visual representation and policy behavior to leverage the mutual impacts of environment and policy. Specifically, our method employs an adversarial feature adaptation model for visual representation transfer and a policy mimic strategy for policy behavior imitation. Experiment shows that our method outperforms the baseline by 19.47% without any additional human annotations.