Wei Liang

Siyuan Huang, Zan Wang, Puhao Li et al. · pku

We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is intrinsically scene-aware, physics-based, and goal-oriented. With an iterative sampling strategy, SceneDiffuser jointly formulates the scene-aware generation, physics-based optimization, and goal-oriented planning via a diffusion-based denoising process in a fully differentiable fashion. Such a design alleviates the discrepancies among different modules and the posterior collapse of previous scene-conditioned generative models. We evaluate SceneDiffuser with various 3D scene understanding tasks, including human pose and motion generation, dexterous grasp generation, path planning for 3D navigation, and motion planning for robot arms. The results show significant improvements compared with previous models, demonstrating the tremendous potential of SceneDiffuser for the broad community of 3D scene understanding.

Zan Wang, Yixin Chen, Tengyu Liu et al. · pku

Learning to generate diverse scene-aware and goal-oriented human motions in 3D scenes remains challenging due to the mediocre characteristics of the existing datasets on Human-Scene Interaction (HSI); they only have limited scale/quality and lack semantics. To fill in the gap, we propose a large-scale and semantic-rich synthetic HSI dataset, denoted as HUMANISE, by aligning the captured human motion sequences with various 3D indoor scenes. We automatically annotate the aligned motions with language descriptions that depict the action and the unique interacting objects in the scene; e.g., sit on the armchair near the desk. HUMANISE thus enables a new generation task, language-conditioned human motion generation in 3D scenes. The proposed task is challenging as it requires joint modeling of the 3D scene, human motion, and natural language. To tackle this task, we present a novel scene-and-language conditioned generative model that can produce 3D human motions of the desirable action interacting with the specified objects. Our experiments demonstrate that our model generates diverse and semantically consistent human motions in 3D scenes.

Hanqing Wang, Wei Liang, Luc Van Gool et al.

VLN-CE is a recently released embodied task, where AI agents need to navigate a freely traversable environment to reach a distant target location, given language instructions. It poses great challenges due to the huge space of possible strategies. Driven by the belief that the ability to anticipate the consequences of future actions is crucial for the emergence of intelligent and interpretable planning behavior, we propose DREAMWALKER -- a world model based VLN-CE agent. The world model is built to summarize the visual, topological, and dynamic properties of the complicated continuous environment into a discrete, structured, and compact representation. DREAMWALKER can simulate and evaluate possible plans entirely in such internal abstract world, before executing costly actions. As opposed to existing model-free VLN-CE agents simply making greedy decisions in the real world, which easily results in shortsighted behaviors, DREAMWALKER is able to make strategic planning through large amounts of ``mental experiments.'' Moreover, the imagined future scenarios reflect our agent's intention, making its decision-making process more transparent. Extensive experiments and ablation studies on VLN-CE dataset confirm the effectiveness of the proposed approach and outline fruitful directions for future work.

Hanqing Wang, Wei Liang, Luc Van Gool et al.

With the emergence of varied visual navigation tasks (e.g, image-/object-/audio-goal and vision-language navigation) that specify the target in different ways, the community has made appealing advances in training specialized agents capable of handling individual navigation tasks well. Given plenty of embodied navigation tasks and task-specific solutions, we address a more fundamental question: can we learn a single powerful agent that masters not one but multiple navigation tasks concurrently? First, we propose VXN, a large-scale 3D dataset that instantiates four classic navigation tasks in standardized, continuous, and audiovisual-rich environments. Second, we propose Vienna, a versatile embodied navigation agent that simultaneously learns to perform the four navigation tasks with one model. Building upon a full-attentive architecture, Vienna formulates various navigation tasks as a unified, parse-and-query procedure: the target description, augmented with four task embeddings, is comprehensively interpreted into a set of diversified goal vectors, which are refined as the navigation progresses, and used as queries to retrieve supportive context from episodic history for decision making. This enables the reuse of knowledge across navigation tasks with varying input domains/modalities. We empirically demonstrate that, compared with learning each visual navigation task individually, our multitask agent achieves comparable or even better performance with reduced complexity.

Ruiying Chen, Yutong Wang, Houliang Zhou et al.

Longitudinal neuroimaging is essential for modeling disease progression in Alzheimer's disease (AD), yet irregular sampling and missing visits pose substantial challenges for learning reliable temporal representations. To address this challenge, we propose SDE-HGNN, a stochastic differential equation (SDE)-driven spatio-temporal hypergraph neural network for irregular longitudinal fMRI connectome modeling. The framework first employs an SDE-based reconstruction module to recover continuous latent trajectories from irregular observations. Based on these reconstructed representations, dynamic hypergraphs are constructed to capture higher-order interactions among brain regions over time. To further model temporal evolution, hypergraph convolution parameters evolve through SDE-controlled recurrent dynamics conditioned on inter-scan intervals, enabling disease-stage-adaptive connectivity modeling. We also incorporate a sparsity-based importance learning mechanism to identify salient brain regions and discriminative connectivity patterns. Extensive experiments on the OASIS-3 and ADNI cohorts demonstrate consistent improvements over state-of-the-art graph and hypergraph baselines in AD progression prediction. The source code is available at https://anonymous.4open.science/r/SDE-HGNN-017F.

Wei Liang, Lifang He

Brain imaging classification is commonly approached from two perspectives: modeling the full image volume to capture global anatomical context, or constructing ROI-based graphs to encode localized and topological interactions. Although both representations have demonstrated independent efficacy, their relative contributions and potential complementarity remain insufficiently understood. Existing fusion approaches are typically task-specific and do not enable controlled evaluation of each representation under consistent training settings. To address this gap, we propose a unified cross-view contrastive framework for joint imaging-ROI representation learning. Our method learns subject-level global (imaging) and local (ROI-graph) embeddings and aligns them in a shared latent space using a bidirectional contrastive objective, encouraging representations from the same subject to converge while separating those from different subjects. This alignment produces comparable embeddings suitable for downstream fusion and enables systematic evaluation of imaging-only, ROI-only, and joint configurations within a unified training protocol. Extensive experiments on the ADHD-200 and ABIDE datasets demonstrate that joint learning consistently improves classification performance over either branch alone across multiple backbone choices. Moreover, interpretability analyses reveal that imaging-based and ROI-based branches emphasize distinct yet complementary discriminative patterns, explaining the observed performance gains. These findings provide principled evidence that explicitly integrating global volumetric and ROI-level representations is a promising direction for neuroimaging-based brain disorder classification. The source code is available at https://anonymous.4open.science/r/imaging-roi-contrastive-152C/.

Xiangyu Li, Gongning Luo, Kuanquan Wang et al.

Automatic intracranial hemorrhage segmentation in 3D non-contrast head CT (NCCT) scans is significant in clinical practice. Existing hemorrhage segmentation methods usually ignores the anisotropic nature of the NCCT, and are evaluated on different in-house datasets with distinct metrics, making it highly challenging to improve segmentation performance and perform objective comparisons among different methods. The INSTANCE 2022 was a grand challenge held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing. The INSTANCE released a training set of 100 cases with ground-truth and a validation set with 30 cases without ground-truth labels that were available to the participants. A held-out testing set with 70 cases is utilized for the final evaluation and ranking. The methods from different participants are ranked based on four metrics, including Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), Relative Volume Difference (RVD) and Normalized Surface Dice (NSD). A total of 13 teams submitted distinct solutions to resolve the challenges, making several baseline models, pre-processing strategies and anisotropic data processing techniques available to future researchers. The winner method achieved an average DSC of 0.6925, demonstrating a significant growth over our proposed baseline method. To the best of our knowledge, the proposed INSTANCE challenge releases the first intracranial hemorrhage segmentation benchmark, and is also the first challenge that intended to resolve the anisotropic problem in 3D medical image segmentation, which provides new alternatives in these research fields.

Yaohua Liu, Wei Liang, Jinqiang Cui

This paper presents a lightweight, efficient calibration neural network model for denoising low-cost microelectromechanical system (MEMS) gyroscope and estimating the attitude of a robot in real-time. The key idea is extracting local and global features from the time window of inertial measurement units (IMU) measurements to regress the output compensation components for the gyroscope dynamically. Following a carefully deduced mathematical calibration model, LGC-Net leverages the depthwise separable convolution to capture the sectional features and reduce the network model parameters. The Large kernel attention is designed to learn the long-range dependencies and feature representation better. The proposed algorithm is evaluated in the EuRoC and TUM-VI datasets and achieves state-of-the-art on the (unseen) test sequences with a more lightweight model structure. The estimated orientation with our LGC-Net is comparable with the top-ranked visual-inertial odometry systems, although it does not adopt vision sensors. We make our method open-source at: https://github.com/huazai665/LGC-Net

Yixuan Li, Le Ma, Yutang Lin et al. · pku

Whole-body humanoid teleoperation enables humans to remotely control humanoid robots, serving as both a real-time operational tool and a scalable engine for collecting demonstrations for autonomous learning. Despite recent advances, existing systems are validated using aggregate metrics that conflate distinct motion regimes, masking critical failure modes. This lack of diagnostic granularity, compounded by tightly coupled and labor-intensive system configurations, hinders robust real-world deployment. A key open challenge is building a teleoperation system that is simultaneously robust, versatile, and affordable for practical use. Here we present OmniClone, a whole-body humanoid teleoperation system that achieves high-fidelity, multi-skill control on a single consumer GPU with modest data requirements. Central to our approach is OmniBench, a diagnostic benchmark that evaluates policies across stratified motion categories and difficulty levels on unseen motions, exposing the narrow specialization of prior systems. Guided by these diagnostics, we identify an optimized training data recipe and integrate system-level improvements: subject-agnostic retargeting and robust communication, that collectively reduce Mean Per-Joint Position Error (MPJPE) by over 66% while requiring orders-of-magnitude fewer computational resources than comparable methods. Crucially, OmniClone is control-source-agnostic: a single unified policy supports real-time teleoperation, generated motion playback, and Vision-Language-Action (VLA) models, while generalizing across operators of vastly different body proportions. By uniting diagnostic evaluation with practical engineering, OmniClone provides an accessible foundation for scalable humanoid teleoperation and autonomous learning.

Yuke Hu, Wei Liang, Ruofan Wu et al.

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from distributed KGs held among clients while avoiding exchanging clients' sensitive raw KGs, which can still suffer from privacy threats as evidenced in other federated model trainings (e.g., neural networks). However, quantifying and defending against such privacy threats remain unexplored for FKGE which possesses unique properties not shared by previously studied models. In this paper, we conduct the first holistic study of the privacy threat on FKGE from both attack and defense perspectives. For the attack, we quantify the privacy threat by proposing three new inference attacks, which reveal substantial privacy risk by successfully inferring the existence of the KG triple from victim clients. For the defense, we propose DP-Flames, a novel differentially private FKGE with private selection, which offers a better privacy-utility tradeoff by exploiting the entity-binding sparse gradient property of FKGE and comes with a tight privacy accountant by incorporating the state-of-the-art private selection technique. We further propose an adaptive privacy budget allocation policy to dynamically adjust defense magnitude across the training procedure. Comprehensive evaluations demonstrate that the proposed defense can successfully mitigate the privacy threat by effectively reducing the success rate of inference attacks from $83.1\%$ to $59.4\%$ on average with only a modest utility decrease.

Guangyuan Jiang, Manjie Xu, Shiji Xin et al.

Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most fundamental building block of multimodal understanding and reasoning. Despite recent advancements in multimodal learning, a systematic and rigorous evaluation is still missing for human-like word learning in machines. To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human's core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. Specifically, MEWL is a few-shot benchmark suite consisting of nine tasks for probing various word learning capabilities. These tasks are carefully designed to be aligned with the children's core abilities in word learning and echo the theories in the developmental literature. By evaluating multimodal and unimodal agents' performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning. We further discuss these differences between humans and machines and call for human-like few-shot word learning in machines.

Manjie Xu, Chenxing Li, Xinyi Tu et al.

Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comprehensive evaluation pipeline that emphasizes generation quality and video-audio synchronization alignment, we demonstrate that our model exhibits state-of-the-art video-to-audio generation capabilities. Furthermore, we provide critical insights into the impact of different data augmentation methods on enhancing the generation framework's overall capacity. We showcase possibilities to advance the challenge of generating synchronized audio from semantic and temporal perspectives. We hope these insights will serve as a stepping stone toward developing more realistic and accurate audio-visual generation models.

Manjie Xu, Guangyuan Jiang, Wei Liang et al.

Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, responding to questions based on pre-stored knowledge. In stark contrast, humans possess the ability to actively explore, accumulate, and reason using both newfound and existing information to tackle incomplete-information questions. In response to this gap, we introduce $Conan$, an interactive open-world environment devised for the assessment of active reasoning. $Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft. Diverging from previous works that lean primarily on single-round deduction via instruction following, $Conan$ compels agents to actively interact with their surroundings, amalgamating new evidence with prior knowledge to elucidate events from incomplete observations. Our analysis on $Conan$ underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios. Additionally, we explore Abduction from Deduction, where agents harness Bayesian rules to recast the challenge of abduction as a deductive process. Through $Conan$, we aim to galvanize advancements in active reasoning and set the stage for the next generation of artificial intelligence agents adept at dynamically engaging in environments.

Manjie Xu, Guangyuan Jiang, Wei Liang et al.

One of the fundamental cognitive abilities of humans is to quickly resolve uncertainty by generating hypotheses and testing them via active trials. Encountering a novel phenomenon accompanied by ambiguous cause-effect relationships, humans make hypotheses against data, conduct inferences from observation, test their theory via experimentation, and correct the proposition if inconsistency arises. These iterative processes persist until the underlying mechanism becomes clear. In this work, we devise the IVRE (pronounced as "ivory") environment for evaluating artificial agents' reasoning ability under uncertainty. IVRE is an interactive environment featuring rich scenarios centered around Blicket detection. Agents in IVRE are placed into environments with various ambiguous action-effect pairs and asked to determine each object's role. They are encouraged to propose effective and efficient experiments to validate their hypotheses based on observations and actively gather new information. The game ends when all uncertainties are resolved or the maximum number of trials is consumed. By evaluating modern artificial agents in IVRE, we notice a clear failure of today's learning methods compared to humans. Such inefficacy in interactive reasoning ability under uncertainty calls for future research in building human-like intelligence.

Manjie Xu, Chenxing Li, Xinyi Tu et al.

We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable success in various captioning tasks, their insufficient performance in terms of generation speed and diversity impede progress in audio understanding and multimedia applications. Our diffusion-based framework offers unique advantages stemming from its inherent stochasticity and holistic context modeling in captioning. Through rigorous evaluation, we demonstrate that DAC not only achieves SOTA performance levels compared to existing benchmarks in the caption quality, but also significantly outperforms them in terms of generation speed and diversity. The success of DAC illustrates that text generation can also be seamlessly integrated with audio and visual generation tasks using a diffusion backbone, paving the way for a unified, audio-related generative model across different modalities.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Yixuan Li, Zan Wang, Wei Liang

We propose Reasoning to Ground (R2G), a neural symbolic model that grounds the target objects within 3D scenes in a reasoning manner. In contrast to prior works, R2G explicitly models the 3D scene with a semantic concept-based scene graph; recurrently simulates the attention transferring across object entities; thus makes the process of grounding the target objects with the highest probability interpretable. Specifically, we respectively embed multiple object properties within the graph nodes and spatial relations among entities within the edges, utilizing a predefined semantic vocabulary. To guide attention transferring, we employ learning or prompting-based methods to analyze the referential utterance and convert it into reasoning instructions within the same semantic space. In each reasoning round, R2G either (1) merges current attention distribution with the similarity between the instruction and embedded entity properties or (2) shifts the attention across the scene graph based on the similarity between the instruction and embedded spatial relations. The experiments on Sr3D/Nr3D benchmarks show that R2G achieves a comparable result with the prior works while maintaining improved interpretability, breaking a new path for 3D language grounding.

Zan Wang, Yixin Chen, Baoxiong Jia et al.

Despite significant advancements in text-to-motion synthesis, generating language-guided human motion within 3D environments poses substantial challenges. These challenges stem primarily from (i) the absence of powerful generative models capable of jointly modeling natural language, 3D scenes, and human motion, and (ii) the generative models' intensive data requirements contrasted with the scarcity of comprehensive, high-quality, language-scene-motion datasets. To tackle these issues, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals, especially when training with limited data lacking extensive language-scene-motion pairs. Our extensive experiments demonstrate that our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE. Additionally, we validate our model's exceptional generalization capabilities on a specially curated evaluation set featuring previously unseen descriptions and scenes.

Siqi Zhu, Yixuan Li, Junfu Li et al.

While on-body device-based human motion estimation is crucial for applications such as XR interaction, existing methods often suffer from poor wearability, expensive hardware, and cumbersome calibration, which hinder their adoption in daily life. To address these challenges, we present EveryWear, a lightweight and practical human motion capture approach based entirely on everyday wearables: a smartphone, smartwatch, earbuds, and smart glasses equipped with one forward-facing and two downward-facing cameras, requiring no explicit calibration before use. We introduce Ego-Elec, a 9-hour real-world dataset covering 56 daily activities across 17 diverse indoor and outdoor environments, with ground-truth 3D annotations provided by the motion capture (MoCap), to facilitate robust research and benchmarking in this direction. Our approach employs a multimodal teacher-student framework that integrates visual cues from egocentric cameras with inertial signals from consumer devices. By training directly on real-world data rather than synthetic data, our model effectively eliminates the sim-to-real gap that constrains prior work. Experiments demonstrate that our method outperforms baseline models, validating its effectiveness for practical full-body motion estimation.

Zhenhe Cui, Huaxiang Xia, Hangjun Shen et al.

Qualitative Numerical Planning (QNP) serves as an important abstraction model for generalized planning (GP), which aims to compute general plans that solve multiple instances at once. Recent works show that large language models (LLMs) can function as generalized planners. This work investigates whether LLMs can serve as QNP abstraction generators for GP problems and how to fix abstractions via automated debugging. We propose a prompt protocol: input a GP domain and training tasks to LLMs, prompting them to generate abstract features and further abstract the initial state, action set, and goal into QNP problems. An automated debugging method is designed to detect abstraction errors, guiding LLMs to fix abstractions. Experiments demonstrate that under properly guided by automated debugging, some LLMs can generate useful QNP abstractions.

Ruiqi Cheng, Huijun Di, Jian Li et al.

Accurate 3D scene motion perception significantly enhances the safety and reliability of an autonomous driving system. Benefiting from its all-weather operational capability and unique perceptual properties, 4D mmWave radar has emerged as an essential component in advanced autonomous driving. However, sparse and noisy radar points often lead to imprecise motion perception, leaving autonomous vehicles with limited sensing capabilities when optical sensors degrade under adverse weather conditions. In this paper, we propose RadarMP, a novel method for precise 3D scene motion perception using low-level radar echo signals from two consecutive frames. Unlike existing methods that separate radar target detection and motion estimation, RadarMP jointly models both tasks in a unified architecture, enabling consistent radar point cloud generation and pointwise 3D scene flow prediction. Tailored to radar characteristics, we design specialized self-supervised loss functions guided by Doppler shifts and echo intensity, effectively supervising spatial and motion consistency without explicit annotations. Extensive experiments on the public dataset demonstrate that RadarMP achieves reliable motion perception across diverse weather and illumination conditions, outperforming radar-based decoupled motion perception pipelines and enhancing perception capabilities for full-scenario autonomous driving systems.

Xiaozhi Li, Huijun Di, Jian Li et al.

Recent advances in 4D imaging radar have enabled robust perception in adverse weather, while camera sensors provide dense semantic information. Fusing the these complementary modalities has great potential for cost-effective 3D perception. However, most existing camera-radar fusion methods are limited to single-frame inputs, capturing only a partial view of the scene. The incomplete scene information, compounded by image degradation and 4D radar sparsity, hinders overall detection performance. In contrast, multi-frame fusion offers richer spatiotemporal information but faces two challenges: achieving robust and effective object feature fusion across frames and modalities, and mitigating the computational cost of redundant feature extraction. Consequently, we propose M^3Detection, a unified multi-frame 3D object detection framework that performs multi-level feature fusion on multi-modal data from camera and 4D imaging radar. Our framework leverages intermediate features from the baseline detector and employs the tracker to produce reference trajectories, improving computational efficiency and providing richer information for second-stage. In the second stage, we design a global-level inter-object feature aggregation module guided by radar information to align global features across candidate proposals and a local-level inter-grid feature aggregation module that expands local features along the reference trajectories to enhance fine-grained object representation. The aggregated features are then processed by a trajectory-level multi-frame spatiotemporal reasoning module to encode cross-frame interactions and enhance temporal representation. Extensive experiments on the VoD and TJ4DRadSet datasets demonstrate that M^3Detection achieves state-of-the-art 3D detection performance, validating its effectiveness in multi-frame detection with camera-4D imaging radar fusion.

Manjie Xu, Chenxing Li, Duzhen zhang et al.

Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio track. We present a novel approach, referred to as PPAE, which serves as a general module for diffusion models and enables precise audio editing. The editing is based on the input textual prompt only and is entirely training-free. We exploit the cross-attention maps of diffusion models to facilitate accurate local editing and employ a hierarchical local-global pipeline to ensure a smoother editing process. Experimental results highlight the effectiveness of our method in various editing tasks.

Huangyue Yu, Baoxiong Jia, Yixin Chen et al.

Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality standards, however, necessitates the precise replication of real-world object diversity. Existing datasets demonstrate that this process heavily relies on artist-driven designs, which demand substantial human effort and present significant scalability challenges. To scalably produce realistic and interactive 3D scenes, we first present MetaScenes, a large-scale, simulatable 3D scene dataset constructed from real-world scans, which includes 15366 objects spanning 831 fine-grained categories. Then, we introduce Scan2Sim, a robust multi-modal alignment model, which enables the automated, high-quality replacement of assets, thereby eliminating the reliance on artist-driven designs for scaling 3D scenes. We further propose two benchmarks to evaluate MetaScenes: a detailed scene synthesis task focused on small item layouts for robotic manipulation and a domain transfer task in vision-and-language navigation (VLN) to validate cross-domain transfer. Results confirm MetaScene's potential to enhance EAI by supporting more generalizable agent learning and sim-to-real applications, introducing new possibilities for EAI research. Project website: https://meta-scenes.github.io/.

Ziyu Zhu, Xilin Wang, Yixuan Li et al.

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstruction, such as meshes and point clouds, but lack the ability to actively perceive and explore their environment. To address this limitation, we introduce \underline{\textbf{M}}ove \underline{\textbf{t}}o \underline{\textbf{U}}nderstand (\textbf{\model}), a unified framework that integrates active perception with \underline{\textbf{3D}} vision-language learning, enabling embodied agents to effectively explore and understand their environment. This is achieved by three key innovations: 1) Online query-based representation learning, enabling direct spatial memory construction from RGB-D frames, eliminating the need for explicit 3D reconstruction. 2) A unified objective for grounding and exploring, which represents unexplored locations as frontier queries and jointly optimizes object grounding and frontier selection. 3) End-to-end trajectory learning that combines \textbf{V}ision-\textbf{L}anguage-\textbf{E}xploration pre-training over a million diverse trajectories collected from both simulated and real-world RGB-D sequences. Extensive evaluations across various embodied navigation and question-answering benchmarks show that MTU3D outperforms state-of-the-art reinforcement learning and modular navigation approaches by 14\%, 23\%, 9\%, and 2\% in success rate on HM3D-OVON, GOAT-Bench, SG3D, and A-EQA, respectively. \model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images. These findings highlight the importance of bridging visual grounding and exploration for embodied intelligence.

Bin Feng, Meng Zheng, Wei Liang et al.

In this paper, we propose a generalizable deep neural network model for indoor pathloss radio map prediction (termed as IPP-Net). IPP-Net is based on a UNet architecture and learned from both large-scale ray tracing simulation data and a modified 3GPP indoor hotspot model. The performance of IPP-Net is evaluated in the First Indoor Pathloss Radio Map Prediction Challenge in ICASSP 2025. The evaluation results show that IPP-Net achieves a weighted root mean square error of 9.501 dB on three competition tasks and obtains the second overall ranking.

Jiaxin Li, Weiqi Huang, Zan Wang et al.

Humans naturally rely on floor plans to navigate in unfamiliar environments, as they are readily available, reliable, and provide rich geometrical guidance. However, existing visual navigation settings overlook this valuable prior knowledge, leading to limited efficiency and accuracy. To eliminate this gap, we introduce a novel navigation task: Floor Plan Visual Navigation (FloNa), the first attempt to incorporate floor plan into embodied visual navigation. While the floor plan offers significant advantages, two key challenges emerge: (1) handling the spatial inconsistency between the floor plan and the actual scene layout for collision-free navigation, and (2) aligning observed images with the floor plan sketch despite their distinct modalities. To address these challenges, we propose FloDiff, a novel diffusion policy framework incorporating a localization module to facilitate alignment between the current observation and the floor plan. We further collect $20k$ navigation episodes across $117$ scenes in the iGibson simulator to support the training and evaluation. Extensive experiments demonstrate the effectiveness and efficiency of our framework in unfamiliar scenes using floor plan knowledge. Project website: https://gauleejx.github.io/flona/.

Chuanqi Zang, Jiji Tang, Rongsheng Zhang et al.

Storytelling aims to generate reasonable and vivid narratives based on an ordered image stream. The fidelity to the image story theme and the divergence of story plots attract readers to keep reading. Previous works iteratively improved the alignment of multiple modalities but ultimately resulted in the generation of simplistic storylines for image streams. In this work, we propose a new pipeline, termed LLaMS, to generate multimodal human-level stories that are embodied in expressiveness and consistency. Specifically, by fully exploiting the commonsense knowledge within the LLM, we first employ a sequence data auto-enhancement strategy to enhance factual content expression and leverage a textual reasoning architecture for expressive story generation and prediction. Secondly, we propose SQ-Adatpter module for story illustration generation which can maintain sequence consistency. Numerical results are conducted through human evaluation to verify the superiority of proposed LLaMS. Evaluations show that LLaMS achieves state-of-the-art storytelling performance and 86% correlation and 100% consistency win rate as compared with previous SOTA methods. Furthermore, ablation experiments are conducted to verify the effectiveness of proposed sequence data enhancement and SQ-Adapter.

Xiaozhi Li, Huijun Di, Jian Li et al.

3D object detection is essential for autonomous driving. As an emerging sensor, 4D imaging radar offers advantages as low cost, long-range detection, and accurate velocity measurement, making it highly suitable for object detection. However, its sparse point clouds and low resolution limit object geometric representation and hinder multi-modal fusion. In this study, we introduce SFGFusion, a novel camera-4D imaging radar detection network guided by surface fitting. By estimating quadratic surface parameters of objects from image and radar data, the explicit surface fitting model enhances spatial representation and cross-modal interaction, enabling more reliable prediction of fine-grained dense depth. The predicted depth serves two purposes: 1) in an image branch to guide the transformation of image features from perspective view (PV) to a unified bird's-eye view (BEV) for multi-modal fusion, improving spatial mapping accuracy; and 2) in a surface pseudo-point branch to generate dense pseudo-point cloud, mitigating the radar point sparsity. The original radar point cloud is also encoded in a separate radar branch. These two point cloud branches adopt a pillar-based method and subsequently transform the features into the BEV space. Finally, a standard 2D backbone and detection head are used to predict object labels and bounding boxes from BEV features. Experimental results show that SFGFusion effectively fuses camera and 4D radar features, achieving superior performance on the TJ4DRadSet and view-of-delft (VoD) object detection benchmarks.

Zan Wang, Jingze Zhang, Yixin Chen et al.

Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale perspective, limiting the capability in complex patterns modeling; (ii) they lack compositional flexibility, which is crucial for model's generalization in diverse generation tasks. To address these challenges, we introduce MSQ, a novel quantization method that compresses the motion sequence into multi-scale discrete tokens across spatial and temporal dimensions. MSQ employs distinct encoders to capture body parts at varying spatial granularities and temporally interpolates the encoded features into multiple scales before quantizing them into discrete tokens. Building on this representation, we establish a generative mask modeling model to effectively support motion editing, motion control, and conditional motion generation. Through quantitative and qualitative analysis, we show that our quantization method enables the seamless composition of motion tokens without requiring specialized design or re-training. Furthermore, extensive evaluations demonstrate that our approach outperforms existing baseline methods on various benchmarks.

Qingliang Meng, Hao Wu, Wei Liang et al.

The deep integration of large language models and automatic speech recognition systems has become a promising research direction with high practical value. To address the overfitting issue commonly observed in Low-Rank Adaptation (LoRA) during the supervised fine-tuning (SFT) stage, this work proposes an innovative training paradigm Iterative LoRA Training (ILT) in combination with an Iterative Pseudo Labeling strategy, effectively enhancing the theoretical upper bound of model performance. Based on Whisper-large-v3 and Qwen2-Audio, we conduct systematic experiments using a three-stage training process: Focus Training, Feed Back Training, and Fix Training. Experimental results demonstrate the effectiveness of the proposed method. Furthermore, the MegaAIS research team applied this technique in the Interspeech 2025 Multilingual Conversational Speech Language Modeling Challenge (MLC-SLM), achieving 4th in Track 1 (Multilingual ASR Task) and 1st place in Track 2 (Speech Separation and Recognition Task), showcasing the practical feasibility and strong application potential of our approach.

Manjie Xu, Xinyi Yang, Wei Liang et al.

Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly in collaborative roles. Although recent studies on embodied intelligence have advanced significantly, they typically adopt generalized approaches that overlook personal preferences in planning. We address this limitation by developing agents that not only learn preferences from few demonstrations but also learn to adapt their planning strategies based on these preferences. Our research leverages the observation that preferences, though implicitly expressed through minimal demonstrations, can generalize across diverse planning scenarios. To systematically evaluate this hypothesis, we introduce Preference-based Planning (PbP) benchmark, an embodied benchmark featuring hundreds of diverse preferences spanning from atomic actions to complex sequences. Our evaluation of SOTA methods reveals that while symbol-based approaches show promise in scalability, significant challenges remain in learning to generate and execute plans that satisfy personalized preferences. We further demonstrate that incorporating learned preferences as intermediate representations in planning significantly improves the agent's ability to construct personalized plans. These findings establish preferences as a valuable abstraction layer for adaptive planning, opening new directions for research in preference-guided plan generation and execution.

Wei Liang, Yiting Zhang, Ji Zhang et al.

Ensuring thermal comfort is essential for the well-being and productivity of individuals in built environments. Of the various thermal comfort indicators, the mean radiant temperature (MRT) is very challenging to measure. Most common measurement methodologies are time-consuming and not user-friendly. To address this issue, this paper proposes a novel MRT measurement framework that uses visual simultaneous localization and mapping (SLAM) and semantic segmentation techniques. The proposed approach follows the rule of thumb of the traditional MRT calculation method using surface temperature and view factors. However, it employs visual SLAM and creates a 3D thermal point cloud with enriched surface temperature information. The framework then implements Grounded SAM, a new object detection and segmentation tool to extract features with distinct temperature profiles on building surfaces. The detailed segmentation of thermal features not only reduces potential errors in the calculation of the MRT but also provides an efficient reconstruction of the spatial MRT distribution in the indoor environment. We also validate the calculation results with the reference measurement methodology. This data-driven framework offers faster and more efficient MRT measurements and spatial mapping than conventional methods. It can enable the direct engagement of researchers and practitioners in MRT measurements and contribute to research on thermal comfort and radiant cooling and heating systems.

Wei Liang, Hui Yu, Derui Ding et al.

Head avatar reenactment focuses on creating animatable personal avatars from monocular videos, serving as a foundational element for applications like social signal understanding, gaming, human-machine interaction, and computer vision. Recent advances in 3D Morphable Model (3DMM)-based facial reconstruction methods have achieved remarkable high-fidelity face estimation. However, on the one hand, they struggle to capture the entire head, including non-facial regions and background details in real time, which is an essential aspect for producing realistic, high-fidelity head avatars. On the other hand, recent approaches leveraging generative adversarial networks (GANs) for head avatar generation from videos can achieve high-quality reenactments but encounter limitations in reproducing fine-grained head details, such as wrinkles and hair textures. In addition, existing methods generally rely on a large amount of training data, and rarely focus on using only a simple selfie video to achieve avatar reenactment. To address these challenges, this study introduces a method for detailed head avatar reenactment using a selfie video. The approach combines 3DMMs with a StyleGAN-based generator. A detailed reconstruction model is proposed, incorporating mixed loss functions for foreground reconstruction and avatar image generation during adversarial training to recover high-frequency details. Qualitative and quantitative evaluations on self-reenactment and cross-reenactment tasks demonstrate that the proposed method achieves superior head avatar reconstruction with rich and intricate textures compared to existing approaches.

Yuhui Zhang, Hui Yu, Wei Liang et al.

Dynamic Neural Radiance Fields (NeRF) have demonstrated considerable success in generating high-fidelity 3D models of talking portraits. Despite significant advancements in the rendering speed and generation quality, challenges persist in accurately and efficiently capturing mouth movements in talking portraits. To tackle this challenge, we propose an automatic method based on blink embedding and hash grid landmarks encoding in this study, which can substantially enhance the fidelity of talking faces. Specifically, we leverage facial features encoded as conditional features and integrate audio features as residual terms into our model through a Dynamic Landmark Transformer. Furthermore, we employ neural radiance fields to model the entire face, resulting in a lifelike face representation. Experimental evaluations have validated the superiority of our approach to existing methods.

Zan Wang, Siyu Chen, Luya Mo et al.

We present DogMo, a large-scale multi-view RGB-D video dataset capturing diverse canine movements for the task of motion recovery from images. DogMo comprises 1.2k motion sequences collected from 10 unique dogs, offering rich variation in both motion and breed. It addresses key limitations of existing dog motion datasets, including the lack of multi-view and real 3D data, as well as limited scale and diversity. Leveraging DogMo, we establish four motion recovery benchmark settings that support systematic evaluation across monocular and multi-view, RGB and RGB-D inputs. To facilitate accurate motion recovery, we further introduce a three-stage, instance-specific optimization pipeline that fits the SMAL model to the motion sequences. Our method progressively refines body shape and pose through coarse alignment, dense correspondence supervision, and temporal regularization. Our dataset and method provide a principled foundation for advancing research in dog motion recovery and open up new directions at the intersection of computer vision, computer graphics, and animal behavior modeling.

Manjie Xu, Xinyi Yang, Jiayu Zhan et al.

Self-play constitutes a fundamental paradigm for autonomous skill acquisition, whereby agents iteratively enhance their capabilities through self-directed environmental exploration. Conventional self-play frameworks exploit agent symmetry within zero-sum competitive settings, yet this approach proves inadequate for open-ended learning scenarios characterized by inherent asymmetry. Human pedagogical systems exemplify asymmetric instructional frameworks wherein educators systematically construct challenges calibrated to individual learners' developmental trajectories. The principal challenge resides in operationalizing these asymmetric, adaptive pedagogical mechanisms within artificial systems capable of autonomously synthesizing appropriate curricula without predetermined task hierarchies. Here we present Heterogeneous Adversarial Play (HAP), an adversarial Automatic Curriculum Learning framework that formalizes teacher-student interactions as a minimax optimization wherein task-generating instructor and problem-solving learner co-evolve through adversarial dynamics. In contrast to prevailing ACL methodologies that employ static curricula or unidirectional task selection mechanisms, HAP establishes a bidirectional feedback system wherein instructors continuously recalibrate task complexity in response to real-time learner performance metrics. Experimental validation across multi-task learning domains demonstrates that our framework achieves performance parity with SOTA baselines while generating curricula that enhance learning efficacy in both artificial agents and human subjects.

Yushi Du, Yixuan Li, Baoxiong Jia et al. · pku

Human-humanoid collaboration shows significant promise for applications in healthcare, domestic assistance, and manufacturing. While compliant robot-human collaboration has been extensively developed for robotic arms, enabling compliant human-humanoid collaboration remains largely unexplored due to humanoids' complex whole-body dynamics. In this paper, we propose a proprioception-only reinforcement learning approach, COLA, that combines leader and follower behaviors within a single policy. The model is trained in a closed-loop environment with dynamic object interactions to predict object motion patterns and human intentions implicitly, enabling compliant collaboration to maintain load balance through coordinated trajectory planning. We evaluate our approach through comprehensive simulator and real-world experiments on collaborative carrying tasks, demonstrating the effectiveness, generalization, and robustness of our model across various terrains and objects. Simulation experiments demonstrate that our model reduces human effort by 24.7%. compared to baseline approaches while maintaining object stability. Real-world experiments validate robust collaborative carrying across different object types (boxes, desks, stretchers, etc.) and movement patterns (straight-line, turning, slope climbing). Human user studies with 23 participants confirm an average improvement of 27.4% compared to baseline models. Our method enables compliant human-humanoid collaborative carrying without requiring external sensors or complex interaction models, offering a practical solution for real-world deployment.

Shuguang Zhao, Qiangzhong Feng, Zhiyang He et al.

Medical consultation dialogues contain critical clinical information, yet their unstructured nature hinders effective utilization in diagnosis and treatment. Traditional methods, relying on rule-based or shallow machine learning techniques, struggle to capture deep and implicit semantics. Recently, large pre-trained language models and Low-Rank Adaptation (LoRA), a lightweight fine-tuning method, have shown promise for structured information extraction. We propose EMRModel, a novel approach that integrates LoRA-based fine-tuning with code-style prompt design, aiming to efficiently convert medical consultation dialogues into structured electronic medical records (EMRs). Additionally, we construct a high-quality, realistically grounded dataset of medical consultation dialogues with detailed annotations. Furthermore, we introduce a fine-grained evaluation benchmark for medical consultation information extraction and provide a systematic evaluation methodology, advancing the optimization of medical natural language processing (NLP) models. Experimental results show EMRModel achieves an F1 score of 88.1%, improving by49.5% over standard pre-trained models. Compared to traditional LoRA fine-tuning methods, our model shows superior performance, highlighting its effectiveness in structured medical record extraction tasks.

Hanqing Wang, Wei Liang, Jianbing Shen et al.

Since the rise of vision-language navigation (VLN), great progress has been made in instruction following -- building a follower to navigate environments under the guidance of instructions. However, far less attention has been paid to the inverse task: instruction generation -- learning a speaker~to generate grounded descriptions for navigation routes. Existing VLN methods train a speaker independently and often treat it as a data augmentation tool to strengthen the follower while ignoring rich cross-task relations. Here we describe an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa. Without the need of aligned instruction-path pairs, such cycle-consistent learning scheme is complementary to task-specific training targets defined on labeled data, and can also be applied over unlabeled paths (sampled without paired instructions). Another agent, called~creator is added to generate counterfactual environments. It greatly changes current scenes yet leaves novel items -- which are vital for the execution of original instructions -- unchanged. Thus more informative training scenes are synthesized and the three agents compose a powerful VLN learning system. Extensive experiments on a standard benchmark show that our approach improves the performance of various follower models and produces accurate navigation instructions.

Hanqing Wang, Zan Wang, Wei Liang et al.

Scene Rearrangement Planning (SRP) is an interior task proposed recently. The previous work defines the action space of this task with handcrafted coarse-grained actions that are inflexible to be used for transforming scene arrangement and intractable to be deployed in practice. Additionally, this new task lacks realistic indoor scene rearrangement data to feed popular data-hungry learning approaches and meet the needs of quantitative evaluation. To address these problems, we propose a fine-grained action definition for SRP and introduce a large-scale scene rearrangement dataset. We also propose a novel learning paradigm to efficiently train an agent through self-playing, without any prior knowledge. The agent trained via our paradigm achieves superior performance on the introduced dataset compared to the baseline agents. We provide a detailed analysis of the design of our approach in our experiments.

Hanqing Wang, Wenguan Wang, Wei Liang et al.

Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply store their past experiences/observations as latent states in recurrent networks, failing to capture environment layouts and make long-term planning. To address these limitations, we propose a crucial architecture, called Structured Scene Memory (SSM). It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment. SSM has a collect-read controller that adaptively collects information for supporting current decision making and mimics iterative algorithms for long-range reasoning. As SSM provides a complete action space, i.e., all the navigable places on the map, a frontier-exploration based navigation decision making strategy is introduced to enable efficient and global planning. Experiment results on two VLN datasets (i.e., R2R and R4R) show that our method achieves state-of-the-art performance on several metrics.

Hanqing Wang, Wenguan Wang, Tianmin Shu et al.

Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. Agents trained by current approaches typically suffer from this and would consequently struggle to avoid random and inefficient actions at every step. In contrast, when humans face such a challenge, they can still maintain robust navigation by actively exploring the surroundings to gather more information and thus make more confident navigation decisions. This work draws inspiration from human navigation behavior and endows an agent with an active information gathering ability for a more intelligent vision-language navigation policy. To achieve this, we propose an end-to-end framework for learning an exploration policy that decides i) when and where to explore, ii) what information is worth gathering during exploration, and iii) how to adjust the navigation decision after the exploration. The experimental results show promising exploration strategies emerged from training, which leads to significant boost in navigation performance. On the R2R challenge leaderboard, our agent gets promising results all three VLN settings, i.e., single run, pre-exploration, and beam search.

Guangcun Shan, Hongyu Wang, Wei Liang et al.

Recently, deep learning technology have been extensively used in the field of image recognition. However, its main application is the recognition and detection of ordinary pictures and common scenes. It is challenging to effectively and expediently analyze remote-sensing images obtained by the image acquisition systems on unmanned aerial vehicles (UAVs), which includes the identification of the target and calculation of its position. Aerial remote sensing images have different shooting angles and methods compared with ordinary pictures or images, which makes remote-sensing images play an irreplaceable role in some areas. In this study, a new target detection and recognition method in remote-sensing images is proposed based on deep convolution neural network (CNN) for the provision of multilevel information of images in combination with a region proposal network used to generate multiangle regions-of-interest. The proposed method generated results that were much more accurate and precise than those obtained with traditional ways. This demonstrated that the model proposed herein displays tremendous applicability potential in remote-sensing image recognition.

Guangcun Shan, Hongyu Wang, Wei Liang

Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition. On one hand, it is how to correctly recognize different mathematical symbols. On the other hand, it is how to correctly recognize the two-dimensional structure existing in mathematical expressions. Inspired by recent work in deep learning, a new neural network model that combines a Multi-Scale convolutional neural network (CNN) with an Attention recurrent neural network (RNN) is proposed to identify two-dimensional handwritten mathematical expressions as one-dimensional LaTeX sequences. As a result, the model proposed in the present work has achieved a WER error of 25.715% and ExpRate of 28.216%.

Hanqing Wang, Jiaolong Yang, Wei Liang et al.

3D object reconstruction is a fundamental task of many robotics and AI problems. With the aid of deep convolutional neural networks (CNNs), 3D object reconstruction has witnessed a significant progress in recent years. However, possibly due to the prohibitively high dimension of the 3D object space, the results from deep CNNs are often prone to missing some shape details. In this paper, we present an approach which aims to preserve more shape details and improve the reconstruction quality. The key idea of our method is to leverage object mask and pose estimation from CNNs to assist the 3D shape learning by constructing a probabilistic single-view visual hull inside of the network. Our method works by first predicting a coarse shape as well as the object pose and silhouette using CNNs, followed by a novel 3D refinement CNN which refines the coarse shapes using the constructed probabilistic visual hulls. Experiment on both synthetic data and real images show that embedding a single-view visual hull for shape refinement can significantly improve the reconstruction quality by recovering more shapes details and improving shape consistency with the input image.