Huayi Wang

Huayi Wang, Haochao Ying, Yuyang Xu et al.

Multimodal survival prediction, a crucial yet challenging task, demands the integration of multimodal medical data (\eg Whole Slide Images (WSIs) and Genomic Profiles) to achieve accurate prognostic modeling. Given the inherent heterogeneity across modalities, the feature decoupling-fusion paradigm has emerged as a dominant approach. However, these methods have the following shortcomings: (1) fail to reduce the redundant information of modality features before decoupling, which negatively affects the feature decoupling and fusion effect;(2) lack the ability to model the fine-grained relationships of the features and capture the local information interactions between intra- and inter-modality features. To address these issues, we propose a \underline{H}ierarchical \underline{D}ecoupling-Fusion \underline{M}ixture-\underline{o}f-\underline{E}xperts (HDMoE) framework with two levels of MoE and \underline{R}andom \underline{F}eature \underline{R}eorganization (RFR) modules.In the first-level MoE, shared experts and routed experts are employed to remove redundant information and extract fine-grained specific features within each modality, while the second-level MoE facilitates fine-grained inter-modality feature decoupling. Besides, we design two RFR modules following each level of MoE to finely fuse intra- and inter-modality features, which can help the model capture more fine-grained relationships between modalities. Extensive experimental results on our private Liver Cancer (LC) and three TCGA public datasets confirm the effectiveness of our proposed method. Codes are available at https://github.com/ZJUMAI/HDMoE.

Junli Ren, Junfeng Long, Tao Huang et al.

We present a reinforcement learning framework for autonomous goalkeeping with humanoid robots in real-world scenarios. While prior work has demonstrated similar capabilities on quadrupedal platforms, humanoid goalkeeping introduces two critical challenges: (1) generating natural, human-like whole-body motions, and (2) covering a wider guarding range with an equivalent response time. Unlike existing approaches that rely on separate teleoperation or fixed motion tracking for whole-body control, our method learns a single end-to-end RL policy, enabling fully autonomous, highly dynamic, and human-like robot-object interactions. To achieve this, we integrate multiple human motion priors conditioned on perceptual inputs into the RL training via an adversarial scheme. We demonstrate the effectiveness of our method through real-world experiments, where the humanoid robot successfully performs agile, autonomous, and naturalistic interceptions of fast-moving balls. In addition to goalkeeping, we demonstrate the generalization of our approach through tasks such as ball escaping and grabbing. Our work presents a practical and scalable solution for enabling highly dynamic interactions between robots and moving objects, advancing the field toward more adaptive and lifelike robotic behaviors.

Yingxuan Yang, Huayi Wang, Muning Wen et al.

In the rapidly advancing field of Large Language Models (LLMs), effectively leveraging existing datasets during fine-tuning to maximize the model's potential is of paramount importance. This paper introduces P3, an adaptive framework aimed at optimizing the task-specific fine-tuning process through iterative data pruning. P3 consists of three key components: (1) Policy-driven Difficulty Measurement, which dynamically assesses data difficulty based on the model's real-time performance, replacing static metrics with adaptable evaluations; (2) Pace-Adaptive Selection, leveraging self-paced learning to progressively introduce more challenging data, thereby enhancing model capability; (3) Diversity Promotion, incorporating Determinantal Point Process (DPP) to ensure data diversity across epochs, enriching the learning process. We validate P3 on the reasoning scenarios, APPS and MATH, demonstrating significant improvements over traditional data pruning methods. By advancing dynamic data selection and utilization strategies, P3 contributes both a theoretical framework and concrete approach to fully exploit existing data for LLMs' performance improvement, offering utility across diverse tasks.

Huayi Wang, Zirui Wang, Junli Ren et al.

Traversing risky terrains with sparse footholds poses a significant challenge for humanoid robots, requiring precise foot placements and stable locomotion. Existing learning-based approaches often struggle on such complex terrains due to sparse foothold rewards and inefficient learning processes. To address these challenges, we introduce BeamDojo, a reinforcement learning (RL) framework designed for enabling agile humanoid locomotion on sparse footholds. BeamDojo begins by introducing a sampling-based foothold reward tailored for polygonal feet, along with a double critic to balancing the learning process between dense locomotion rewards and sparse foothold rewards. To encourage sufficient trial-and-error exploration, BeamDojo incorporates a two-stage RL approach: the first stage relaxes the terrain dynamics by training the humanoid on flat terrain while providing it with task-terrain perceptive observations, and the second stage fine-tunes the policy on the actual task terrain. Moreover, we implement a onboard LiDAR-based elevation map to enable real-world deployment. Extensive simulation and real-world experiments demonstrate that BeamDojo achieves efficient learning in simulation and enables agile locomotion with precise foot placement on sparse footholds in the real world, maintaining a high success rate even under significant external disturbances.

Tao Huang, Junli Ren, Huayi Wang et al.

Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems, such as fall recovery. Existing approaches are either limited to simulations that overlook hardware constraints or rely on predefined ground-specific motion trajectories, failing to enable standing up across postures in real-world scenes. To bridge this gap, we present HoST (Humanoid Standing-up Control), a reinforcement learning framework that learns standing-up control from scratch, enabling robust sim-to-real transfer across diverse postures. HoST effectively learns posture-adaptive motions by leveraging a multi-critic architecture and curriculum-based training on diverse simulated terrains. To ensure successful real-world deployment, we constrain the motion with smoothness regularization and implicit motion speed bound to alleviate oscillatory and violent motions on physical hardware, respectively. After simulation-based training, the learned control policies are directly deployed on the Unitree G1 humanoid robot. Our experimental results demonstrate that the controllers achieve smooth, stable, and robust standing-up motions across a wide range of laboratory and outdoor environments. Videos and code are available at https://taohuang13.github.io/humanoid-standingup.github.io/.

Huayi Wang, Jingfan Meng, Jun Xu

Approximate nearest neighbor search under universal L_p metrics (ANNS-U-L_p) is an important and challenging research problem, as it requires answering queries under all possible p (0<p <= 2) values simultaneously without building an index for each possible p value. The state-of-the-art solution, called MLSH, is a Locality-Sensitive Hashing (LSH)-based ANNS method with barely acceptable query performance. In contrast, graph-based ANNS methods, which offer significantly improved query efficiency on the ANNS-L_p problem (with a fixed p-value), cannot be naively extended to the ANNS-U-$L_p$ problem. In this paper, we propose U-HNSW, the first graph-based method for ANNS-U-L_p. Our scheme uses HNSW graph indexes built on two base metrics ($L_1$ and $L_2$) to generate promising nearest neighbors candidates, and then verifies these candidates with an early-termination strategy that substantially reduces the number of expensive L_p distance computations. Experimental results show that U-HNSW not only achieves up to 2670 times shorter query times than the original MLSH implementation running on a RAM disk (up to 15 times shorter than the idealized MLSH), but also outperforms the original HNSW on the ANNS-L_p problem (with a fixed p-value), except for a few special p values.

Tao Huang, Huayi Wang, Junli Ren et al.

Humanoid robots are envisioned to adapt demonstrated motions to diverse real-world conditions while accurately preserving motion patterns. Existing motion prior approaches enable well adaptability with a few motions but often sacrifice imitation accuracy, whereas motion-tracking methods achieve accurate imitation yet require many training motions and a test-time target motion to adapt. To combine their strengths, we introduce AdaMimic, a novel motion tracking algorithm that enables adaptable humanoid control from a single reference motion. To reduce data dependence while ensuring adaptability, our method first creates an augmented dataset by sparsifying the single reference motion into keyframes and applying light editing with minimal physical assumptions. A policy is then initialized by tracking these sparse keyframes to generate dense intermediate motions, and adapters are subsequently trained to adjust tracking speed and refine low-level actions based on the adjustment, enabling flexible time warping that further improves imitation accuracy and adaptability. We validate these significant improvements in our approach in both simulation and the real-world Unitree G1 humanoid robot in multiple tasks across a wide range of adaptation conditions. Videos and code are available at https://taohuang13.github.io/adamimic.github.io/.

Huayi Wang, Wentao Zhang, Runyi Yu et al.

Deploying humanoid robots to interact with real-world environments--such as carrying objects or sitting on chairs--requires generalizable, lifelike motions and robust scene perception. Although prior approaches have advanced each capability individually, combining them in a unified system is still an ongoing challenge. In this work, we present a physical-world humanoid-scene interaction system, PhysHSI, that enables humanoids to autonomously perform diverse interaction tasks while maintaining natural and lifelike behaviors. PhysHSI comprises a simulation training pipeline and a real-world deployment system. In simulation, we adopt adversarial motion prior-based policy learning to imitate natural humanoid-scene interaction data across diverse scenarios, achieving both generalization and lifelike behaviors. For real-world deployment, we introduce a coarse-to-fine object localization module that combines LiDAR and camera inputs to provide continuous and robust scene perception. We validate PhysHSI on four representative interactive tasks--box carrying, sitting, lying, and standing up--in both simulation and real-world settings, demonstrating consistently high success rates, strong generalization across diverse task goals, and natural motion patterns.

Huayi Wang, Haochao Ying, Yuyang Xu et al.

Cancer survival analysis commonly integrates information across diverse medical modalities to make survival-time predictions. Existing methods primarily focus on extracting different decoupled features of modalities and performing fusion operations such as concatenation, attention, and MoE-based (Mixture-of-Experts) fusion. However, these methods still face two key challenges: i) Fixed fusion schemes (concatenation and attention) can lead to model over-reliance on predefined feature combinations, limiting the dynamic fusion of decoupled features; ii) in MoE-based fusion methods, each expert network handles separate decoupled features, which limits information interaction among the decoupled features. To address these challenges, we propose a novel Decoupling-Reorganization-Fusion framework (DeReF), which devises a random feature reorganization strategy between modalities decoupling and dynamic MoE fusion modules.Its advantages are: i) it increases the diversity of feature combinations and granularity, enhancing the generalization ability of the subsequent expert networks; ii) it overcomes the problem of information closure and helps expert networks better capture information among decoupled features. Additionally, we incorporate a regional cross-attention network within the modality decoupling module to improve the representation quality of decoupled features. Extensive experimental results on our in-house Liver Cancer (LC) and three widely used TCGA public datasets confirm the effectiveness of our proposed method. The code will be made publicly available.

Huayi Wang, Chunli Zhu, Liheng Bian

The recently developed image-free sensing technique maintains the advantages of both the light hardware and software, which has been applied in simple target classification and motion tracking. In practical applications, however, there usually exist multiple targets in the field of view, where existing trials fail to produce multi-semantic information. In this letter, we report a novel image-free sensing technique to tackle the multi-target recognition challenge for the first time. Different from the convolutional layer stack of image-free single-pixel networks, the reported CRNN network utilities the bidirectional LSTM architecture to predict the distribution of multiple characters simultaneously. The framework enables to capture the long-range dependencies, providing a high recognition accuracy of multiple characters. We demonstrated the technique's effectiveness in license plate detection, which achieved 87.60% recognition accuracy at a 5% sampling rate with a higher than 100 FPS refresh rate.