Zhenglong Sun

Peipei Zhu, Xiao Wang, Lin Zhu et al.

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement learning. However, these existing works were only able to learn limited cross-domain information in vision and language domains, which restrains the captioning performance of UIC. Inspired by the success of Vision-Language Pre-Trained Models (VL-PTMs) in this research, we attempt to infer the cross-domain cue information about a given image from the large VL-PTMs for the UIC task. This research is also motivated by recent successes of prompt learning in many downstream multi-modal tasks, including image-text retrieval and vision question answering. In this work, a semantic prompt is introduced and aggregated with visual features for more accurate caption prediction under the adversarial learning framework. In addition, a metric prompt is designed to select high-quality pseudo image-caption samples obtained from the basic captioning model and refine the model in an iterative manner. Extensive experiments on the COCO and Flickr30K datasets validate the promising captioning ability of the proposed model. We expect that the proposed prompt-based UIC model will stimulate a new line of research for the VL-PTMs based captioning.

Peipei Zhu, Xiao Wang, Yong Luo et al.

The goal of unpaired image captioning (UIC) is to describe images without using image-caption pairs in the training phase. Although challenging, we except the task can be accomplished by leveraging a training set of images aligned with visual concepts. Most existing studies use off-the-shelf algorithms to obtain the visual concepts because the Bounding Box (BBox) labels or relationship-triplet labels used for the training are expensive to acquire. In order to resolve the problem in expensive annotations, we propose a novel approach to achieve cost-effective UIC. Specifically, we adopt image-level labels for the optimization of the UIC model in a weakly-supervised manner. For each image, we assume that only the image-level labels are available without specific locations and numbers. The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e.g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN). The proposed approach achieves comparable or even better performance compared with previous methods without the expensive cost of annotations. Furthermore, we design an unrecognized object (UnO) loss combined with a visual concept reward to improve the alignment of the inferred object and relationship information with the images. It can effectively alleviate the issue encountered by existing UIC models about generating sentences with nonexistent objects. To the best of our knowledge, this is the first attempt to solve the problem of Weakly-Supervised visual concept recognition for UIC (WS-UIC) based only on image-level labels. Extensive experiments have been carried out to demonstrate that the proposed WS-UIC model achieves inspiring results on the COCO dataset while significantly reducing the cost of labeling.

Sihan Shang, Jiancheng Yang, Zhenglong Sun et al.

In the realm of healthcare, the challenges of copyright protection and unauthorized third-party misuse are increasingly significant. Traditional methods for data copyright protection are applied prior to data distribution, implying that models trained on these data become uncontrollable. This paper introduces a novel approach, named DataCook, designed to safeguard the copyright of healthcare data during the deployment phase. DataCook operates by "cooking" the raw data before distribution, enabling the development of models that perform normally on this processed data. However, during the deployment phase, the original test data must be also "cooked" through DataCook to ensure normal model performance. This process grants copyright holders control over authorization during the deployment phase. The mechanism behind DataCook is by crafting anti-adversarial examples (AntiAdv), which are designed to enhance model confidence, as opposed to standard adversarial examples (Adv) that aim to confuse models. Similar to Adv, AntiAdv introduces imperceptible perturbations, ensuring that the data processed by DataCook remains easily understandable. We conducted extensive experiments on MedMNIST datasets, encompassing both 2D/3D data and the high-resolution variants. The outcomes indicate that DataCook effectively meets its objectives, preventing models trained on AntiAdv from analyzing unauthorized data effectively, without compromising the validity and accuracy of the data in legitimate scenarios. Code and data are available at https://github.com/MedMNIST/DataCook.

Rui Zhu, Bingchen Zhao, Jingen Liu et al.

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative (pos/neg) pairs is one of its keys. In this paper, we attempt to devise a feature-level data manipulation, differing from data augmentation, to enhance the generic contrastive self-supervised learning. To this end, we first design a visualization scheme for pos/neg score (Pos/neg score indicates cosine similarity of pos/neg pair.) distribution, which enables us to analyze, interpret and understand the learning process. To our knowledge, this is the first attempt of its kind. More importantly, leveraging this tool, we gain some significant observations, which inspire our novel Feature Transformation proposals including the extrapolation of positives. This operation creates harder positives to boost the learning because hard positives enable the model to be more view-invariant. Besides, we propose the interpolation among negatives, which provides diversified negatives and makes the model more discriminative. It is the first attempt to deal with both challenges simultaneously. Experiment results show that our proposed Feature Transformation can improve at least 6.0% accuracy on ImageNet-100 over MoCo baseline, and about 2.0% accuracy on ImageNet-1K over the MoCoV2 baseline. Transferring to the downstream tasks successfully demonstrate our model is less task-bias. Visualization tools and codes https://github.com/DTennant/CL-Visualizing-Feature-Transformation .

Liguang Zhou, Jun Cen, Xingchao Wang et al.

Scene recognition is a fundamental task in robotic perception. For human beings, scene recognition is reasonable because they have abundant object knowledge of the real world. The idea of transferring prior object knowledge from humans to scene recognition is significant but still less exploited. In this paper, we propose to utilize meaningful object representations for indoor scene representation. First, we utilize an improved object model (IOM) as a baseline that enriches the object knowledge by introducing a scene parsing algorithm pretrained on the ADE20K dataset with rich object categories related to the indoor scene. To analyze the object co-occurrences and pairwise object relations, we formulate the IOM from a Bayesian perspective as the Bayesian object relation model (BORM). Meanwhile, we incorporate the proposed BORM with the PlacesCNN model as the combined Bayesian object relation model (CBORM) for scene recognition and significantly outperforms the state-of-the-art methods on the reduced Places365 dataset, and SUN RGB-D dataset without retraining, showing the excellent generalization ability of the proposed method. Code can be found at https://github.com/hszhoushen/borm.

Pengcheng Chen, Yue Hu, Wenhao Li et al.

In modern dense 3D reconstruction, feed-forward systems (e.g., VGGT, pi3) focus on end-to-end matching and geometry prediction but do not explicitly output the novel view synthesis (NVS). Neural rendering-based approaches offer high-fidelity NVS and detailed geometry from posed images, yet they typically assume fixed camera poses and can be sensitive to pose errors. As a result, it remains non-trivial to obtain a single framework that can offer accurate poses, reliable depth, high-quality rendering, and accurate 3D surfaces from casually captured views. We present NeVStereo, a NeRF-driven NVS-stereo architecture that aims to jointly deliver camera poses, multi-view depth, novel view synthesis, and surface reconstruction from multi-view RGB-only inputs. NeVStereo combines NeRF-based NVS for stereo-friendly renderings, confidence-guided multi-view depth estimation, NeRF-coupled bundle adjustment for pose refinement, and an iterative refinement stage that updates both depth and the radiance field to improve geometric consistency. This design mitigated the common NeRF-based issues such as surface stacking, artifacts, and pose-depth coupling. Across indoor, outdoor, tabletop, and aerial benchmarks, our experiments indicate that NeVStereo achieves consistently strong zero-shot performance, with up to 36% lower depth error, 10.4% improved pose accuracy, 4.5% higher NVS fidelity, and state-of-the-art mesh quality (F1 91.93%, Chamfer 4.35 mm) compared to existing prestigious methods.

Rui Zhu, Yingwei Pan, Yehao Li et al.

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning. Despite this progress, mask strategy still suffers from two inherent limitations: (a) training-inference discrepancy and (b) fuzzy relations between mask reconstruction & generative diffusion process, resulting in sub-optimal training of DiT. In this work, we address these limitations by novelly unleashing the self-supervised discrimination knowledge to boost DiT training. Technically, we frame our DiT in a teacher-student manner. The teacher-student discriminative pairs are built on the diffusion noises along the same Probability Flow Ordinary Differential Equation (PF-ODE). Instead of applying mask reconstruction loss over both DiT encoder and decoder, we decouple DiT encoder and decoder to separately tackle discriminative and generative objectives. In particular, by encoding discriminative pairs with student and teacher DiT encoders, a new discriminative loss is designed to encourage the inter-image alignment in the self-supervised embedding space. After that, student samples are fed into student DiT decoder to perform the typical generative diffusion task. Extensive experiments are conducted on ImageNet dataset, and our method achieves a competitive balance between training cost and generative capacity.

Zexin Lin, Yebin Zhong, Hanwen Wan et al.

Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods' decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.

Yixuan Deng, Tongrun Wu, Donghao Wu et al.

As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In practice, many deployments are only partially decoupled: middleware moves messages, but shared context and feedback semantics are implicit, causing interface drift, cross-module interference, and brittle recovery at scale. We present ANCHOR, a modular framework that makes decoupling and robustness explicit system-level primitives. ANCHOR separates (i) Canonical Records, an evolvable contract for the standardized shared state, from (ii) a communication bus for many-to-many dissemination and feedback-oriented coordination, forming an inspectable end-to-end loop. We validate closed-loop feasibility on a de-identified workflow instantiation, characterize latency distributions under varying payload sizes and publish rates, and demonstrate automatic stream resumption after hard crashes and restarts even with shared-memory loss. Overall, ANCHOR turns ad-hoc integration glue into explicit contracts, enabling controlled degradation under load and self-healing recovery for scalable deployment of closed-loop AI systems.

Yang Zhang, Chenwei Wang, Ouyang Lu et al.

Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially when the robot's embodiment or the task itself differs from the pre-training data. This discrepancy leads to a significant mismatch in action distributions, demanding extensive data and compute for effective fine-tuning. To address this challenge, we introduce \textbf{Align-Then-stEer (\texttt{ATE})}, a novel, data-efficient, and plug-and-play adaptation framework. \texttt{ATE} first aligns disparate action spaces by constructing a unified latent space, where a variational autoencoder constrained by reverse KL divergence embeds adaptation actions into modes of the pre-training action latent distribution. Subsequently, it steers the diffusion- or flow-based VLA's generation process during fine-tuning via a guidance mechanism that pushes the model's output distribution towards the target domain. We conduct extensive experiments on cross-embodiment and cross-task manipulation in both simulation and real world. Compared to direct fine-tuning of representative VLAs, our method improves the average multi-task success rate by up to \textbf{9.8\%} in simulation and achieves a striking \textbf{32\% success rate gain} in a real-world cross-embodiment setting. Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.

Hanwen Wan, Mengkang Li, Donghao Wu et al.

Developing bipedal robots capable of traversing diverse real-world terrains presents a fundamental robotics challenge, as existing methods using predefined height maps and static environments fail to address the complexity of unstructured landscapes. To bridge this gap, we propose GenTe, a framework for generating physically realistic and adaptable terrains to train generalizable locomotion policies. GenTe constructs an atomic terrain library that includes both geometric and physical terrains, enabling curriculum training for reinforcement learning-based locomotion policies. By leveraging function-calling techniques and reasoning capabilities of Vision-Language Models (VLMs), GenTe generates complex, contextually relevant terrains from textual and graphical inputs. The framework introduces realistic force modeling for terrain interactions, capturing effects such as soil sinkage and hydrodynamic resistance. To the best of our knowledge, GenTe is the first framework that systemically generates simulation environments for legged robot locomotion control. Additionally, we introduce a benchmark of 100 generated terrains. Experiments demonstrate improved generalization and robustness in bipedal robot locomotion.

Hualie Jiang, Laiyan Ding, Zhenglong Sun et al.

As a flexible passive 3D sensing means, unsupervised learning of depth from monocular videos is becoming an important research topic. It utilizes the photometric errors between the target view and the synthesized views from its adjacent source views as the loss instead of the difference from the ground truth. Occlusion and scene dynamics in real-world scenes still adversely affect the learning, despite significant progress made recently. In this paper, we show that deliberately manipulating photometric errors can efficiently deal with these difficulties better. We first propose an outlier masking technique that considers the occluded or dynamic pixels as statistical outliers in the photometric error map. With the outlier masking, the network learns the depth of objects that move in the opposite direction to the camera more accurately. To the best of our knowledge, such cases have not been seriously considered in the previous works, even though they pose a high risk in applications like autonomous driving. We also propose an efficient weighted multi-scale scheme to reduce the artifacts in the predicted depth maps. Extensive experiments on the KITTI dataset and additional experiments on the Cityscapes dataset have verified the proposed approach's effectiveness on depth or ego-motion estimation. Furthermore, for the first time, we evaluate the predicted depth on the regions of dynamic objects and static background separately for both supervised and unsupervised methods. The evaluation further verifies the effectiveness of our proposed technical approach and provides some interesting observations that might inspire future research in this direction.

Zhihao Li, Zhenglong Sun, Jionglong SU et al.

In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods approximate long-horizon tasks as Markov decision processes and only consider current observation (images or other sensor information) as input state. However, such approximation ignores the fact that skill-sequence also plays a crucial role in long-horizon tasks. In this paper, we take both the observation and skill sequences into account and propose a skill-sequence-dependent hierarchical policy for solving a typical long-horizon task. The proposed policy consists of a high-level skill policy (utilizing skill sequences) and a low-level parameter policy (responding to observation) with corresponding training methods, which makes the learning much more sample-efficient. Experiments in simulation demonstrate that our approach successfully solves a long-horizon task and is significantly faster than Proximal Policy Optimization (PPO) and the task schema methods.

Yingbai Hu, Jian Li, Yongquan Chen et al.

The outbreak of novel coronavirus pneumonia (COVID-19) has caused mortality and morbidity worldwide. Oropharyngeal-swab (OP-swab) sampling is widely used for the diagnosis of COVID-19 in the world. To avoid the clinical staff from being affected by the virus, we developed a 9-degree-of-freedom (DOF) rigid-flexible coupling (RFC) robot to assist the COVID-19 OP-swab sampling. This robot is composed of a visual system, UR5 robot arm, micro-pneumatic actuator and force-sensing system. The robot is expected to reduce risk and free up the clinical staff from the long-term repetitive sampling work. Compared with a rigid sampling robot, the developed force-sensing RFC robot can facilitate OP-swab sampling procedures in a safer and softer way. In addition, a varying-parameter zeroing neural network-based optimization method is also proposed for motion planning of the 9-DOF redundant manipulator. The developed robot system is validated by OP-swab sampling on both oral cavity phantoms and volunteers.

Fang Wan, Zheng Wang, Brooke Franchuk et al.

We describe a fluidic actuator design that replaces the sealed chamber of a hydraulic cylinder using a soft actuator to provide compliant linear compression with a large force ($\geq$100 N) at a low operation pressure ($\leq$50 kPa) for a lower-limb wearable. The external shells constrain the deformation of the soft actuator under fluidic pressurization. This enables us to use latex party balloons as a quick and cheap alternative for initial design investigation. We found that the forces exerted by the soft material deformation are well-captured by the rigid shells, removing the necessity of explicitly describing the mechanics of the soft material deformation and its interaction with the rigid structure. One can use the classical Force, Pressure and Area formula factored with an efficiency parameter to characterize the actuator performance. Furthermore, we proposed an engineering design of the hybrid actuator using a customized soft actuator placed inside a single shell cavity with an open end for the compression force. Our results show that the proposed design can generate a very high force within a short stroke distance. At a low input pressure of 50 kPa, the exerted block force is approaching only about 3\% less than the classical equation predicted. The actuator is fitted to a new gait augmentation design for correcting knee alignment, which is usually challenging for actuators made from the purely soft material.

Hualie Jiang, Laiyan Ding, Zhenglong Sun et al.

Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one. It achieves this by using the photometric errors between the target view and the synthesized views from its adjacent source views as the loss. Despite significant progress, the learning still suffers from occlusion and scene dynamics. This paper shows that carefully manipulating photometric errors can tackle these difficulties better. The primary improvement is achieved by a statistical technique that can mask out the invisible or nonstationary pixels in the photometric error map and thus prevents misleading the networks. With this outlier masking approach, the depth of objects moving in the opposite direction to the camera can be estimated more accurately. To the best of our knowledge, such scenarios have not been seriously considered in the previous works, even though they pose a higher risk in applications like autonomous driving. We also propose an efficient weighted multi-scale scheme to reduce the artifacts in the predicted depth maps. Extensive experiments on the KITTI dataset show the effectiveness of the proposed approaches. The overall system achieves state-of-theart performance on both depth and ego-motion estimation.