ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos

Humans excel at spatio-temporal reasoning, effortlessly interpreting dynamic visual events from an egocentric viewpoint. However, whether multimodal large language models (MLLMs) can similarly comprehend the 4D world remains uncertain. This paper explores multimodal spatio-temporal reasoning from an egocentric perspective, aiming to equip MLLMs with human-like reasoning capabilities. To support this objective, we introduce Ego-ST Bench, a novel benchmark containing over 5,000 question-answer pairs across four categories, systematically evaluating spatial, temporal, and integrated spatio-temporal reasoning. Additionally, we propose the ST-R1 Video model, a video-based reasoning model that incorporates reverse thinking into its reinforcement learning process, significantly enhancing performance. We combine long-chain-of-thought (long-CoT) supervised fine-tuning with Group Relative Policy Optimization (GRPO) reinforcement learning, achieving notable improvements with limited high-quality data. Ego-ST Bench and ST-R1 provide valuable insights and resources for advancing video-based spatio-temporal reasoning research.

VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we introduce VideoMAP, a Hybrid Mamba-Transformer framework featuring a novel pre-training approach. VideoMAP uses a 4:1 Mamba-to-Transformer ratio, effectively balancing computational cost and model capacity. This architecture, combined with our proposed frame-wise masked autoregressive pre-training strategy, delivers significant performance gains when scaling to larger models. Additionally, VideoMAP exhibits impressive sample efficiency, significantly outperforming existing methods with less training data. Experiments show that VideoMAP outperforms existing models across various datasets, including Kinetics-400, Something-Something V2, Breakfast, and COIN. Furthermore, we demonstrate the potential of VideoMAP as a visual encoder for multimodal large language models, highlighting its ability to reduce memory usage and enable the processing of longer video sequences. The code is open-source at https://github.com/yunzeliu/MAP

MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data

This paper introduces MobileH2R, a framework for learning generalizable vision-based human-to-mobile-robot (H2MR) handover skills. Unlike traditional fixed-base handovers, this task requires a mobile robot to reliably receive objects in a large workspace enabled by its mobility. Our key insight is that generalizable handover skills can be developed in simulators using high-quality synthetic data, without the need for real-world demonstrations. To achieve this, we propose a scalable pipeline for generating diverse synthetic full-body human motion data, an automated method for creating safe and imitation-friendly demonstrations, and an efficient 4D imitation learning method for distilling large-scale demonstrations into closed-loop policies with base-arm coordination. Experimental evaluations in both simulators and the real world show significant improvements (at least +15% success rate) over baseline methods in all cases. Experiments also validate that large-scale and diverse synthetic data greatly enhances robot learning, highlighting our scalable framework.

MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining

Mamba has achieved significant advantages in long-context modeling and autoregressive tasks, but its scalability with large parameters remains a major limitation in vision applications. pretraining is a widely used strategy to enhance backbone model performance. Although the success of Masked Autoencoder in Transformer pretraining is well recognized, it does not significantly improve Mamba's visual learning performance. We found that using the correct autoregressive pretraining can significantly boost the performance of the Mamba architecture. Based on this analysis, we propose Masked Autoregressive Pretraining (MAP) to pretrain a hybrid Mamba-Transformer vision backbone network. This strategy combines the strengths of both MAE and Autoregressive pretraining, improving the performance of Mamba and Transformer modules within a unified paradigm. Additionally, in terms of integrating Mamba and Transformer modules, we empirically found that inserting Transformer layers at regular intervals within Mamba layers can significantly enhance downstream task performance. Experimental results show that both the pure Mamba architecture and the hybrid Mamba-Transformer vision backbone network pretrained with MAP significantly outperform other pretraining strategies, achieving state-of-the-art performance. We validate the effectiveness of the method on both 2D and 3D datasets and provide detailed ablation studies to support the design choices for each component.

Physics-aware Hand-object Interaction Denoising

The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However, due to high occlusions during hand-object interaction, physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers, this paper proposes a novel physically-aware hand motion de-noising method. Specifically, we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy, surpassing current state-of-the-art de-noising methods.

PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation

Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live, work, and communicate. However, it is difficult to learn the diverse interaction patterns of multiple humans and generate physically plausible reactions. The kinematics-based approaches face challenges, including issues like floating feet, sliding, penetration, and other problems that defy physical plausibility. The existing physics-based method often relies on kinematics-based methods to generate reference states, which struggle with the challenges posed by kinematic noise during action execution. Constrained by their reliance on diffusion models, these methods are unable to achieve real-time inference. In this work, we propose a Forward Dynamics Guided 4D Imitation method to generate physically plausible human-like reactions. The learned policy is capable of generating physically plausible and human-like reactions in real-time, significantly improving the speed(x33) and quality of reactions compared with the existing method. Our experiments on the InterHuman and Chi3D datasets, along with ablation studies, demonstrate the effectiveness of our approach.

CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data scarcity and challenges in label acquisition. To address these issues, we propose a self-supervised learning method that leverages the cross-modal relationship between point cloud videos and image videos to acquire meaningful feature representations. Intra-modal and cross-modal contrastive learning techniques are employed to facilitate effective comprehension of point cloud video. We also propose a multi-level contrastive approach for both modalities. Through extensive experiments, we demonstrate that our method significantly surpasses previous state-of-the-art approaches, and we conduct comprehensive ablation studies to validate the effectiveness of our proposed designs.

Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting

We focus on the human-humanoid interaction task optionally with an object. We propose a new task named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The previous work only focuses on human interaction without objects and generates body reactions without hand. Besides, they also do not consider the task as an online setting, which means the inability to observe information beyond the current moment in practical situations. To support this task, we construct two datasets named HHI and CoChair and propose a unified method. Specifically, we propose to construct a social affordance representation. We first select a social affordance carrier and use SE(3)-Equivariant Neural Networks to learn the local frame for the carrier, then we canonicalize the social affordance. Besides, we propose a social affordance forecasting scheme to enable the reactor to predict based on the imagined future. Experiments demonstrate that our approach can effectively generate high-quality reactions on HHI and CoChair. Furthermore, we also validate our method on existing human interaction datasets Interhuman and Chi3D.

NSM4D: Neural Scene Model Based Online 4D Point Cloud Sequence Understanding

Understanding 4D point cloud sequences online is of significant practical value in various scenarios such as VR/AR, robotics, and autonomous driving. The key goal is to continuously analyze the geometry and dynamics of a 3D scene as unstructured and redundant point cloud sequences arrive. And the main challenge is to effectively model the long-term history while keeping computational costs manageable. To tackle these challenges, we introduce a generic online 4D perception paradigm called NSM4D. NSM4D serves as a plug-and-play strategy that can be adapted to existing 4D backbones, significantly enhancing their online perception capabilities for both indoor and outdoor scenarios. To efficiently capture the redundant 4D history, we propose a neural scene model that factorizes geometry and motion information by constructing geometry tokens separately storing geometry and motion features. Exploiting the history becomes as straightforward as querying the neural scene model. As the sequence progresses, the neural scene model dynamically deforms to align with new observations, effectively providing the historical context and updating itself with the new observations. By employing token representation, NSM4D also exhibits robustness to low-level sensor noise and maintains a compact size through a geometric sampling scheme. We integrate NSM4D with state-of-the-art 4D perception backbones, demonstrating significant improvements on various online perception benchmarks in indoor and outdoor settings. Notably, we achieve a 9.6% accuracy improvement for HOI4D online action segmentation and a 3.4% mIoU improvement for SemanticKITTI online semantic segmentation. Furthermore, we show that NSM4D inherently offers excellent scalability to longer sequences beyond the training set, which is crucial for real-world applications.

Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning

Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled 4D datasets is often very expensive and laborious, so it is especially important to investigate how to utilize raw unlabeled data. However, most existing self-supervised point cloud representation learning methods only consider geometry from a static snapshot omitting the fact that sequential observations of dynamic scenes could reveal more comprehensive geometric details. And the video representation learning frameworks mostly model motion as image space flows, let alone being 3D-geometric-aware. To overcome such issues, this paper proposes a new 4D self-supervised pre-training method called Complete-to-Partial 4D Distillation. Our key idea is to formulate 4D self-supervised representation learning as a teacher-student knowledge distillation framework and let the student learn useful 4D representations with the guidance of the teacher. Experiments show that this approach significantly outperforms previous pre-training approaches on a wide range of 4D point cloud sequence understanding tasks including indoor and outdoor scenarios.