Ziluo Ding

Haobin Jiang, Junpeng Yue, Hao Luo et al.

One of the essential missions in the AI research community is to build an autonomous embodied agent that can achieve high-level performance across a wide spectrum of tasks. However, acquiring or manually designing rewards for all open-ended tasks is unrealistic. In this paper, we propose a novel cross-modal contrastive learning framework architecture, CLIP4MC, aiming to learn a reinforcement learning (RL) friendly vision-language model (VLM) that serves as an intrinsic reward function for open-ended tasks. Simply utilizing the similarity between the video snippet and the language prompt is not RL-friendly since standard VLMs may only capture the similarity at a coarse level. To achieve RL-friendliness, we incorporate the task completion degree into the VLM training objective, as this information can assist agents in distinguishing the importance between different states. Moreover, we provide neat YouTube datasets based on the large-scale YouTube database provided by MineDojo. Specifically, two rounds of filtering operations guarantee that the dataset covers enough essential information and that the video-text pair is highly correlated. Empirically, we demonstrate that the proposed method achieves better performance on RL tasks compared with baselines. The code and datasets are available at https://github.com/PKU-RL/CLIP4MC.

Lujie Xia, Ziluo Ding, Rui Zhao et al. · pku

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers architecture, it applies dilated convolutions on temporal dimension to extract features on multi-temporal scales with few parameters. And we design layer attention to dynamically fuse these features. Moreover, we propose an unsupervised learning method for optical flow estimation in a spike-based manner to break the dependence on labeled data. In addition, to verify the robustness, we also build a spike-based synthetic validation dataset for extreme scenarios in autonomous driving, denoted as SSES dataset. It consists of various corner cases. Experiments show that our method can predict optical flow from spike streams in different high-speed scenes, including real scenes. For instance, our method gets $15\%$ and $19\%$ error reduction from the best spike-based work, SCFlow, in $Δt=10$ and $Δt=20$ respectively which are the same settings as the previous works.

Ziluo Ding, Wanpeng Zhang, Junpeng Yue et al. · pku

We investigate the use of natural language to drive the generalization of policies in multi-agent settings. Unlike single-agent settings, the generalization of policies should also consider the influence of other agents. Besides, with the increasing number of entities in multi-agent settings, more agent-entity interactions are needed for language grounding, and the enormous search space could impede the learning process. Moreover, given a simple general instruction,e.g., beating all enemies, agents are required to decompose it into multiple subgoals and figure out the right one to focus on. Inspired by previous work, we try to address these issues at the entity level and propose a novel framework for language grounding in multi-agent reinforcement learning, entity divider (EnDi). EnDi enables agents to independently learn subgoal division at the entity level and act in the environment based on the associated entities. The subgoal division is regularized by opponent modeling to avoid subgoal conflicts and promote coordinated strategies. Empirically, EnDi demonstrates the strong generalization ability to unseen games with new dynamics and expresses the superiority over existing methods.

Ziluo Ding, Zeyuan Liu, Zhirui Fang et al.

The partial observability and stochasticity in multi-agent settings can be mitigated by accessing more information about others via communication. However, the coordination problem still exists since agents cannot communicate actual actions with each other at the same time due to the circular dependencies. In this paper, we propose a novel multi-level communication scheme, Sequential Communication (SeqComm). SeqComm treats agents asynchronously (the upper-level agents make decisions before the lower-level ones) and has two communication phases. In the negotiation phase, agents determine the priority of decision-making by communicating hidden states of observations and comparing the value of intention, obtained by modeling the environment dynamics. In the launching phase, the upper-level agents take the lead in making decisions and then communicate their actions with the lower-level agents. Theoretically, we prove the policies learned by SeqComm are guaranteed to improve monotonically and converge. Empirically, we show that SeqComm outperforms existing methods in various cooperative multi-agent tasks.

Shuanghao Bai, Meng Li, Xinyuan Lv et al.

Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.

Zhirui Fang, Ming Yang, Weishuai Zeng et al.

We explore leveraging large multi-modal models (LMMs) and text2image models to build a more general embodied agent. LMMs excel in planning long-horizon tasks over symbolic abstractions but struggle with grounding in the physical world, often failing to accurately identify object positions in images. A bridge is needed to connect LMMs to the physical world. The paper proposes a novel approach, egocentric vision language planning (EgoPlan), to handle long-horizon tasks from an egocentric perspective in varying household scenarios. This model leverages a diffusion model to simulate the fundamental dynamics between states and actions, integrating techniques like style transfer and optical flow to enhance generalization across different environmental dynamics. The LMM serves as a planner, breaking down instructions into sub-goals and selecting actions based on their alignment with these sub-goals, thus enabling more generalized and effective decision-making. Experiments show that EgoPlan improves long-horizon task success rates from the egocentric view compared to baselines across household scenarios.

Liwen Hu, Rui Zhao, Ziluo Ding et al.

As a bio-inspired sensor with high temporal resolution, the spiking camera has an enormous potential in real applications, especially for motion estimation in high-speed scenes. However, frame-based and event-based methods are not well suited to spike streams from the spiking camera due to the different data modalities. To this end, we present, SCFlow, a tailored deep learning pipeline to estimate optical flow in high-speed scenes from spike streams. Importantly, a novel input representation is introduced which can adaptively remove the motion blur in spike streams according to the prior motion. Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes. Experimental results show that the SCFlow can predict optical flow from spike streams in different high-speed scenes. Moreover, SCFlow shows promising generalization on \textbf{real spike streams}. Codes and datasets refer to https://github.com/Acnext/Optical-Flow-For-Spiking-Camera.

Ziluo Ding, Rui Zhao, Jiyuan Zhang et al.

Event camera has offered promising alternative for visual perception, especially in high speed and high dynamic range scenes. Recently, many deep learning methods have shown great success in providing promising solutions to many event-based problems, such as optical flow estimation. However, existing deep learning methods did not address the importance of temporal information well from the perspective of architecture design and cannot effectively extract spatio-temporal features. Another line of research that utilizes Spiking Neural Network suffers from training issues for deeper architecture.To address these points, a novel input representation is proposed that captures the events' temporal distribution for signal enhancement. Moreover, we introduce a spatio-temporal recurrent encoding-decoding neural network architecture for event-based optical flow estimation, which utilizes Convolutional Gated Recurrent Units to extract feature maps from a series of event images. Besides, our architecture allows some traditional frame-based core modules, such as correlation layer and iterative residual refine scheme, to be incorporated. The network is end-to-end trained with self-supervised learning on the Multi-Vehicle Stereo Event Camera dataset. We have shown that it outperforms all the existing state-of-the-art methods by a large margin. The code link is https://github.com/ruizhao26/STE-FlowNet.

Ziluo Ding, Tiejun Huang, Zongqing Lu

Communication lays the foundation for human cooperation. It is also crucial for multi-agent cooperation. However, existing work focuses on broadcast communication, which is not only impractical but also leads to information redundancy that could even impair the learning process. To tackle these difficulties, we propose Individually Inferred Communication (I2C), a simple yet effective model to enable agents to learn a prior for agent-agent communication. The prior knowledge is learned via causal inference and realized by a feed-forward neural network that maps the agent's local observation to a belief about who to communicate with. The influence of one agent on another is inferred via the joint action-value function in multi-agent reinforcement learning and quantified to label the necessity of agent-agent communication. Furthermore, the agent policy is regularized to better exploit communicated messages. Empirically, we show that I2C can not only reduce communication overhead but also improve the performance in a variety of multi-agent cooperative scenarios, comparing to existing methods. The code is available at https://github.com/PKU-AI-Edge/I2C.

Weihao Tan, Wentao Zhang, Xinrun Xu et al.

Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Cradle can understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games, five software applications, and a comprehensive benchmark, OSWorld. Cradle is the first to enable foundation agents to follow the main storyline and complete 40-minute-long real missions in the complex AAA game Red Dead Redemption 2 (RDR2). Cradle can also create a city of a thousand people in Cities: Skylines, farm and harvest parsnips in Stardew Valley, and trade and bargain with a maximal weekly total profit of 87% in Dealer's Life 2. Cradle can not only operate daily software, like Chrome, Outlook, and Feishu, but also edit images and videos using Meitu and CapCut. Cradle greatly extends the reach of foundation agents by enabling the easy conversion of any software, especially complex games, into benchmarks to evaluate agents' various abilities and facilitate further data collection, thus paving the way for generalist agents.

Xinrun Xu, Yuxin Wang, Chaoyi Xu et al.

The swift evolution of Large-scale Models (LMs), either language-focused or multi-modal, has garnered extensive attention in both academy and industry. But despite the surge in interest in this rapidly evolving area, there are scarce systematic reviews on their capabilities and potential in distinct impactful scenarios. This paper endeavours to help bridge this gap, offering a thorough examination of the current landscape of LM usage in regards to complex game playing scenarios and the challenges still open. Here, we seek to systematically review the existing architectures of LM-based Agents (LMAs) for games and summarize their commonalities, challenges, and any other insights. Furthermore, we present our perspective on promising future research avenues for the advancement of LMs in games. We hope to assist researchers in gaining a clear understanding of the field and to generate more interest in this highly impactful research direction. A corresponding resource, continuously updated, can be found in our GitHub repository.

Haobin Jiang, Ziluo Ding, Zongqing Lu

Exploration in decentralized cooperative multi-agent reinforcement learning faces two challenges. One is that the novelty of global states is unavailable, while the novelty of local observations is biased. The other is how agents can explore in a coordinated way. To address these challenges, we propose MACE, a simple yet effective multi-agent coordinated exploration method. By communicating only local novelty, agents can take into account other agents' local novelty to approximate the global novelty. Further, we newly introduce weighted mutual information to measure the influence of one agent's action on other agents' accumulated novelty. We convert it as an intrinsic reward in hindsight to encourage agents to exert more influence on other agents' exploration and boost coordinated exploration. Empirically, we show that MACE achieves superior performance in three multi-agent environments with sparse rewards.

Yuxuan Wang, Ming Yang, Ziluo Ding et al.

Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control requirements and mismatched data distributions. In this work, we propose BumbleBee (BB), an expert-generalist learning framework that combines motion clustering and sim-to-real adaptation to overcome these challenges. BB first leverages an autoencoder-based clustering method to group behaviorally similar motions using motion features and motion descriptions. Expert policies are then trained within each cluster and refined with real-world data through iterative delta action modeling to bridge the sim-to-real gap. Finally, these experts are distilled into a unified generalist controller that preserves agility and robustness across all motion types. Experiments on two simulations and a real humanoid robot demonstrate that BB achieves state-of-the-art general whole-body control, setting a new benchmark for agile, robust, and generalizable humanoid performance in the real world. The project webpage is available at https://beingbeyond.github.io/BumbleBee/.

Ziluo Ding, Haobin Jiang, Yuxuan Wang et al.

This paper presents JAEGER, a dual-level whole-body controller for humanoid robots that addresses the challenges of training a more robust and versatile policy. Unlike traditional single-controller approaches, JAEGER separates the control of the upper and lower bodies into two independent controllers, so that they can better focus on their distinct tasks. This separation alleviates the dimensionality curse and improves fault tolerance. JAEGER supports both root velocity tracking (coarse-grained control) and local joint angle tracking (fine-grained control), enabling versatile and stable movements. To train the controller, we utilize a human motion dataset (AMASS), retargeting human poses to humanoid poses through an efficient retargeting network, and employ a curriculum learning approach. This method performs supervised learning for initialization, followed by reinforcement learning for further exploration. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-art methods in both simulation and real environments.

Junpeng Yue, Zepeng Wang, Yuxuan Wang et al.

This paper focuses on a critical challenge in robotics: translating text-driven human motions into executable actions for humanoid robots, enabling efficient and cost-effective learning of new behaviors. While existing text-to-motion generation methods achieve semantic alignment between language and motion, they often produce kinematically or physically infeasible motions unsuitable for real-world deployment. To bridge this sim-to-real gap, we propose Reinforcement Learning from Physical Feedback (RLPF), a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation. RLPF employs a motion tracking policy to assess feasibility in a physics simulator, generating rewards for fine-tuning the motion generator. Furthermore, RLPF introduces an alignment verification module to preserve semantic fidelity to text instructions. This joint optimization ensures both physical plausibility and instruction alignment. Extensive experiments show that RLPF greatly outperforms baseline methods in generating physically feasible motions while maintaining semantic correspondence with text instruction, enabling successful deployment on real humanoid robots.

Yuxuan Wang, Haobin Jiang, Shiqing Yao et al.

Existing humanoid control systems often rely on teleoperation or modular generation pipelines that separate language understanding from physical execution. However, the former is entirely human-driven, and the latter lacks tight alignment between language commands and physical behaviors. In this paper, we present SENTINEL, a fully end-to-end language-action model for humanoid whole-body control. We construct a large-scale dataset by tracking human motions in simulation using a pretrained whole body controller, combined with their text annotations. The model directly maps language commands and proprioceptive inputs to low-level actions without any intermediate representation. The model generates action chunks using flow matching, which can be subsequently refined by a residual action head for real-world deployment. Our method exhibits strong semantic understanding and stable execution on humanoid robots in both simulation and real-world deployment, and also supports multi-modal extensions by converting inputs into texts.

Liwen Hu, Yang Li, Mianzhi Liu et al.

Spike camera, a type of neuromorphic sensor with high-temporal resolution, shows great promise for high-speed visual tasks. Unlike traditional cameras, spike camera continuously accumulates photons and fires asynchronous spike streams. Due to unique data modality, spike streams require reconstruction methods to become perceptible to the human eye. However, lots of methods struggle to handle spike streams in low-light high-speed scenarios due to severe noise and sparse information. In this work, we propose Diff-SPK, a diffusion-based reconstruction method. Diff-SPK effectively leverages generative priors to supplement texture information under diverse low-light conditions. Specifically, it first employs an Enhanced Texture from Inter-spike Interval (ETFI) to aggregate sparse information from low-light spike streams. Then, the encoded ETFI by a suitable encoder serve as the input of ControlNet for high-speed scenes generation. To improve the quality of results, we introduce an ETFI-based feature fusion module during the generation process.

Liwen Hu, Ziluo Ding, Mianzhi Liu et al.

As a neuromorphic sensor with high temporal resolution, spike camera can generate continuous binary spike streams to capture per-pixel light intensity. We can use reconstruction methods to restore scene details in high-speed scenarios. However, due to limited information in spike streams, low-light scenes are difficult to effectively reconstruct. In this paper, we propose a bidirectional recurrent-based reconstruction framework, including a Light-Robust Representation (LR-Rep) and a fusion module, to better handle such extreme conditions. LR-Rep is designed to aggregate temporal information in spike streams, and a fusion module is utilized to extract temporal features. Additionally, we have developed a reconstruction benchmark for high-speed low-light scenes. Light sources in the scenes are carefully aligned to real-world conditions. Experimental results demonstrate the superiority of our method, which also generalizes well to real spike streams. Related codes and proposed datasets will be released after publication.