Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He, Maoqing Yao, Guanghui Ren. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood. In this work, we investigate the nuanced role of data diversity in robot learning by examining three critical dimensions-task (what to do), embodiment (which robot to use), and expert (who demonstrates)-challenging the conventional intuition of “more diverse is better”. Throughout extensive experiments on various robot platforms, we reveal that (1) task diversity proves more critical than per-task demonstration quantity, with scene diversity playing a more important role than skill diversity for robustness and generalization under distribution shifts; (2) multi-embodiment pre-training data is non-essential for cross-embodiment transfer-models trained on high-quality single-embodiment data can efficiently transfer to different platforms, showing desirable scaling property during fine-tuning and its potential of replacing large-scale multi-embodiment pre-training; and (3) expert diversity, arising from individual operational preferences and stochastic variations in human demonstrations, can be confounding to policy learning, with action rate multimodality emerging as a key contributing factor. Based on this insight, we propose a distribution debiasing method to mitigate action rate ambiguity, the yielding GO-1-Pro achieves substantial performance gains of 15%, equivalent to using 2.5× pre-training data. Collectively, these findings provide new perspectives and offer practical guidance on how to scale robotic manipulation datasets effectively. The code will be released.

We introduce EnerVerse, a generative robotics foundation model that constructs and interprets embodied spaces. EnerVerse employs a chunk-wise autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning. To model the 3D robotics world, we adopt a multi-view video representation, providing rich perspectives to address challenges like motion ambiguity and 3D grounding. Additionally, EnerVerse-D, a data engine pipeline combining generative modeling with 4D Gaussian Splatting, forms a self-reinforcing data loop to reduce the sim-to-real gap. Leveraging these innovations, EnerVerse translates 4D world representations into physical actions via a policy head (EnerVerse-A), achieving state-of-the-art performance in both simulation and real-world tasks. For efficiency, EnerVerse-A reuses features from the first denoising step and predicts action chunks, achieving about 280 ms per 8-step action chunk on a single RTX 4090. Further video demos, dataset samples could be found in our project page.

精确的、与波长相关的相位调制在许多领域中是必不可少的, 比如超分辨成像、全彩色全息、微纳加工以及光通讯。这一要求很难通过单一的传统光学元件实现, 一般需要使用多个光学元件组合完成。本文提出一种可以实现波长选择性波前整形的超表面设计方法。具体来说, 本文设计了一种超表面, 它能够对785 nm波长的光做涡旋相位调制, 同时不影响590 nm波长的光保持原有相位分布。本文通过干涉仪以及对应点扩散函数的测量来验证不同波长下的波前分布。与已提出的空间复用方式以及色散工程的方法相比, 我们提出的设计方法更加直接, 优化难度小, 适用于需要波长选择性编码的光学系统。本文所提平面光学器件对于需要波长选择性编码的光学系统具有重要应用意义。

In this paper, we target at the Fine-grAined human-Centric Tracklet Segmentation (FACTS) problem, where 12 human parts, e.g., face, pants, left-leg, are segmented. To reduce the heavy and tedious labeling efforts, FACTS requires only one labeled frame per video during training. The small size of human parts and the labeling scarcity makes FACTS very challenging. Considering adjacent frames of videos are continuous and human usually do not change clothes in a short time, we explicitly consider the pixel-level and frame-level context in the proposed Temporal Context segmentation Network (TCNet). On the one hand, optical flow is on-line calculated to propagate the pixel-level segmentation results to neighboring frames. On the other hand, frame-level classification likelihood vectors are also propagated to nearby frames. By fully exploiting the pixel-level and frame-level context, TCNet indirectly uses the large amount of unlabeled frames during training and produces smooth segmentation results during inference. Experimental results on four video datasets show the superiority of TCNet over the state-of-the-arts. The newly annotated datasets can be downloaded via http://liusi-group.com/projects/FACTS for the further studies.

Vision and language understanding techniques have achieved remarkable progress, but currently it is still difficult to well handle problems involving very fine-grained details. For example, when the robot is told to "bring me the book in the girl's left hand", most existing methods would fail if the girl holds one book respectively in her left and right hand. In this work, we introduce a new task named human-centric relation segmentation (HRS), as a fine-grained case of HOI-det. HRS aims to predict the relations between the human and surrounding entities and identify the relation-correlated human parts, which are represented as pixel-level masks. For the above exemplar case, our HRS task produces results in the form of relation triplets 〈girl [left hand], hold, book 〉 and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task. Correspondingly, we collect a new Person In Context (PIC) dataset for this new task, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations, including 141 object categories, 23 relation categories and 25 semantic human parts. We also propose a Simultaneous Matching and Segmentation (SMS) framework as a solution to the HRS task. It contains three parallel branches for entity segmentation, subject object matching and human parsing respectively. Specifically, the entity segmentation branch obtains entity masks by dynamically-generated conditional convolutions; the subject object matching branch detects the existence of any relations, links the corresponding subjects and objects by displacement estimation and classifies the interacted human parts; and the human parsing branch generates the pixelwise human part labels. Outputs of the three branches are fused to produce the final HRS results. Extensive experiments on PIC and V-COCO datasets show that the proposed SMS method outperforms baselines with the 36 FPS inference speed. Notably, SMS outperforms the best performing baseline m-KERN with only 17.6 percent time cost. The dataset and code will be released at http://picdataset.com/challenge/index/.

Scene graph generation has received increasing attention in recent years. Enhancing the predicate representations is an important entry point to this task. There are various methods to fully investigate the context of representation enhancement. In this brief, we analyze the decisive factors that can significantly affect the relation detection results. Our analysis shows that spatial correlations between objects, focused regions of objects, and global hints related to the relations have strong influences in relation prediction and contradiction elimination. Based on our analysis, we propose a hierarchical context network (HCNet) to generate a scene graph. HCNet consists of three contexts, including interaction context, depression context, and global context, which integrates information from pair, object, and graph levels. The experiments show that our method outperforms the state-of-the-art methods on the Visual Genome (VG) data set.

Video relation detection problem refers to the detection of the relationship between different objects in videos, such as spatial relationship and action relationship. In this paper, we present video relation detection with trajectory-aware multi-modal features to solve this task. Considering the complexity of doing visual relation detection in videos, we decompose this task into three sub-tasks: object detection, trajectory proposal and relation prediction. We use the state-of-the-art object detection method to ensure the accuracy of object trajectory detection and multi-modal feature representation to help the prediction of relation between objects. Our method won the first place on the video relation detection task of Video Relation Understanding Grand Challenge in ACM Multimedia 2020 with 11.74% mAP, which surpasses other methods by a large margin.

Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem.

In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

By describing the principle and parameter selection guide in detail, M×N-ary variable width period modulation (MNVWPM) is proposed in this paper to increase the bandwidth efficiency for ultraviolet communication (UVC) through intensity modulation and direct detection. Theoretical analysis and experimental results indicate that, MNVWPM can be used to achieve a bandwidth efficiency higher than those of commonly used on-off keying (OOK) or pulse position modulation (PPM).

Traffic sign classification is an important function for driver assistance systems. In this paper, we propose a hierarchical method for traffic sign classification. There are two hierarchies in the method: the first one classifies traffic signs into several super classes, while the second one further classifies the signs within their super classes and provides the final results. Two perspective adjustment methods are proposed and performed before the second hierarchy, which significantly improves the classification accuracy. Experimental results show that the proposed method gets an accuracy of 99.52% on the German Traffic Sign Recognition Benchmark (GTSRB), which outperforms the state-of-the-art method. In addition, it takes about 40 ms to process one image, making it suitable for realtime applications.

We present a traffic sign detection method which has won the first place for the prohibitory and mandatory signs and the third place for the danger signs in the GTSDB competition. The method uses the histogram of oriented gradient (HOG) and a coarse-to-fine sliding window scheme. Candidate ROIs are first roughly detected within a small-sized window, and then further verified within a large-sized window for higher accuracy. Experimental results show that the proposed method achieves high recall and precision ratios, and is robust to various adverse situations including bad lighting condition, partial occlusion, low quality and small projective deformation.

In this paper, a new effective method of digital modulation recognition is proposed to recognize different modulation types for software defined radio receivers, where an orthogonal wavelet-basis neural network approximator based on a multi-resolution analysis wavelet is training to be a modulation classifier under the condition of lower and wider range of SNR, which can work with the good performance of high robustness because of the insensitivity of the wavelet spectrum to the wide range of SNR of the signal, as well as without the local convergence resulting from non-liner optimization of the BP neural network classifier. To measure the performance of the proposed method, experiments are carried out to classify different types of band-limited modulated signals received by a software radio receiver and corrupted by AWGN. It is found that the overall success rate of the proposed method is over 98.61% at the SNR of 8 dB