Author name cluster

Yang Ding

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2025 Conference Paper

CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks

Wenfeng Song
Yang Ding
Fei Hou
Shuai Li
Aimin Hao
Xia Hou

As virtual experiences grow in popularity, the demand for realistic, personalized, and animatable human avatars increases. Traditional methods, relying on fixed templates, often produce costly avatars that lack expressiveness and realism. To overcome these challenges, we introduce Controllable Avatars generation via disentangled invertible networks (CtrlAvatar), a real-time framework for generating lifelike and customizable avatars. CtrlAvatar uses disentangled invertible networks to separate the deformation process into implicit body geometry and explicit texture components. This approach eliminates the need for repeated occupancy reconstruction, enabling detailed and coherent animations. The body geometry component ensures anatomical accuracy, while the texture component allows for complex, artifact-free clothing customization. This architecture ensures smooth integration between body movements and surface details. By optimizing transformations with position-varying offsets from the avatar’s initial Linear Blend Skinning vertices, CtrlAvatar achieves flexible, natural deformations that adapt to various scenarios. Extensive experiments show that CtrlAvatar outperforms other methods in quality, diversity, controllability, and cost-efficiency, marking a significant advancement in avatar generation.

PDF Details DOI

AIIM Journal 2025 Journal Article

Online continuous learning of users suicidal risk on social media

Lei Cao
Ling Feng
Yang Ding
Huijun Zhang
Xin Wang
Kaisheng Zeng
Yi Dai

Suicide is a tragedy for family and society. With social media becoming an integral part of people’s life nowadays, assessing suicidal risk based on one’s social media behavior has drawn increasing research attentions. The majority of the works trained a machine learning model to classify user’s suicidal risk severity level in a batch learning setting on the entire training data. This is not a timely and scalable solution in the context of social media where new data arrives sequentially in a stream form. In this study, we formulate and address the continuous suicidal risk assessment problem through a three-layered joint memory network, consisting of a short-term personal memory and long-term personal and global memories. Unlike existing methods that rely on static classification, our model supports real-time, continuous learning from users’ emotional and behavioral dynamics without the need for full retraining. This allows for personalized and adaptive risk tracking over time. We also present a way to continuously capture users’ personal features and integrate them in suicidal risk assessment. The performance on the constructed dataset containing 95 suicidal and 95 non-suicidal social media users shows that 96% of accuracy can be achieved with the proposed method.

Details DOI

NeurIPS Conference 2025 Conference Paper

PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning

Yizhen Zhang
Yang Ding
Shuoshuo Zhang
Xinchen Zhang
Haoling Li
Zhong-Zhi Li
Peijie Wang
Jie Wu

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models (VLMs) for multimodal reasoning tasks. However, most existing multimodal reinforcement learning approaches remain limited to spatial reasoning within single-image contexts, yet still struggle to generalize to more complex and real-world scenarios involving multi-image positional reasoning, where understanding the relationships across images is crucial. To address this challenge, we propose a general reinforcement learning approach PeRL tailored for interleaved multimodal tasks, and a multi-stage strategy designed to enhance the exploration-exploitation trade-off, thereby improving learning efficiency and task performance. Specifically, we introduce permutation of image sequences to simulate varied positional relationships to explore more spatial and positional diversity. Furthermore, we design a rollout filtering mechanism for resampling to focus on trajectories that contribute most to learning optimal behaviors to exploit learned policies effectively. We evaluate our model on 5 widely-used multi-image benchmarks and 3 single-image benchmarks. Our experiments confirm that PeRL trained model consistently surpasses R1-related and interleaved VLM baselines by a large margin, achieving state-of-the-art performance on multi-image benchmarks, while preserving comparable performance on single-image tasks.

PDF Details

IROS Conference 2024 Conference Paper

NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications

Li Cui
Yang Ding
Richard I. Hartley
Zirui Xie
Laurent Kneip
Zhenghua Yu

We propose a novel, vision-only object-level SLAM framework for automotive applications representing 3D shapes by implicit signed distance functions. Our key innovation consists of augmenting the standard neural representation by a normalizing flow network. As a result, achieving strong representation power on the specific class of road vehicles is made possible by compact networks with only 16-dimensional latent codes. Furthermore, the newly proposed architecture exhibits a significant performance improvement in the presence of only sparse and noisy data, which is demonstrated through comparative experiments on synthetic data. The module is embedded into the back-end of a stereo-vision based framework for joint, incremental shape optimization. The loss function is given by a combination of a sparse 3D point-based SDF loss, a sparse rendering loss, and a semantic mask-based silhouette-consistency term. We furthermore leverage semantic information to determine keypoint extraction density in the front-end. Finally, experimental results on real-world data reveal accurate and reliable performance comparable to alternative frameworks that make use of direct depth readings. The proposed method performs well with only sparse 3D points obtained from bundle adjustment, and eventually continues to deliver stable results even under exclusive use of the mask-consistency term.

Details

JBHI Journal 2023 Journal Article

Continuous Stress Detection Based on Social Media

Yang Ding
Ling Feng
Lei Cao
Yi Dai
Xin Wang
Huijun Zhang
Ningyun Li
Kaisheng Zeng

Leveraging social media for stress detection has been growing attention in recent years. Most relevant studies so far concentrated on training a stress detection model on the entire data in a closed environment, and did not continuously incorporate new information into the already established models but instead regularly reconstruct a new model from scratch. In this study, we formulate a social media based continuous stress detection task with two particular questions to be addressed: (1) when to adapt a learned stress detection model? and (2) how to adapt a learned stress detection model? We design a protocol to quantify the conditions that trigger model's adaptation, and develop a layer-inheritance based knowledge distillation method to continually adapt the learned stress detection model to incoming data, while retaining the knowledge gained previously. The experimental results on a constructed dataset containing 69 users on Tencent Weibo validate the effectiveness of the proposed adaptive layer-inheritance based knowledge distillation method, achieving 86. 32% and 91. 56% of accuracy in 3-label and 2-label continuous stress detection. Implications and further possible improvements are also discussed at the end of the article.

Details DOI

NeurIPS Conference 2023 Conference Paper

Model-enhanced Vector Index

Hailin Zhang
Yujing Wang
Qi Chen
Ruiheng Chang
Ting Zhang
Ziming Miao
Yingyan Hou
Yang Ding

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

PDF Details

TCS Journal 2021 Journal Article

A (2 + ϵ)k-vertex kernel for the dual coloring problem

Wenjun Li
Yang Ding
Yongjie Yang
Guozhen Rong

Given a graph G of n vertices and an integer k, the Dual Coloring problem determines if G is ( n − k ) -colorable, i. e. , if we can color vertices of G with at most n − k colors so that every vertex obtains exactly one color and every two adjacent vertices have different colors. We derive a kernelization for the Dual Coloring problem with respect to the parameter k. In particular, for any fixed ϵ > 0, our kernelization yields a kernel of at most ( 2 + ϵ ) k vertices, improving the currently best result 3 k − 3.

Details DOI

ICRA Conference 2011 Conference Paper

Granular lift forces predict vertical motion of a sand-swimming robot

Ryan D. Maladen
Paul Umbanhowar
Yang Ding
Andrew Masse
Daniel I. Goldman

Previously we modeled the undulatory subsurface locomotion of the sandfish lizard with a sand-swimming robot which displayed performance comparable to the organism. In this work we control the lift forces on the robot by varying its head shape and demonstrate that these granular forces predict the vertical motion of the robot. Inspired by the tapered head of the sandfish lizard, we drag a wedge shaped object horizontally and parallel to its lower face through a granular medium and show that by varying the angle of the upper leading surface of the wedge, α, the lift force can be varied from positive to negative. Testing the robot with these wedges as heads results in vertical motion in the same direction as the lift force in the drag experiments. As the robot moves forward, the force on its head normal to the body plane results in a net torque imbalance which pitches the robot causing it to rise or sink within the medium. Since repeatedly varying α for a wedge head to achieve a desired lift is impractical, we test robot heads that approximate a wedge head inclined at varying angles by changing the angle of the bottom and top surfaces of the wedge, and show that similar lift control is achieved. Our results provide principles for the construction of robots that will be able to follow arbitrary trajectories within complex substrates like sand, and also lend support to hypotheses that morphological adaptations of desert-dwelling organisms aid in their subsurface locomotion.

Details