Author name cluster

Hao Shen

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.

12 papers

2 author rows

AAAI Conference 2026 Conference Paper

CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking

Zhiqiang Hao
Chuanyi Li
Ye Fan
Jun Cai
Xiao Fu
Shangqi Wang
Hao Shen
Jiao Yin

We propose Contextual History for Adaptive and Simple Exploitation (CHASE), a novel multi-turn method for Large Language Model (LLM) jailbreaking. Rather than directly attack an LLM that may be difficult to jailbreak, CHASE first collects jailbroken histories from an easy-to-jailbreak LLM and then transfers them to the target LLM. Through this history transfer process, CHASE misleads the target LLM into thinking that it is responsible for producing the jailbroken histories and increases the chances of successful jailbreaking by prompting it to continue the conversation. Extensive evaluations on mainstream LLMs show that CHASE consistently achieves higher attack success rates and demands fewer computational resources compared to existing methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Uzair Akbar
Niki Kilbertus
Hao Shen
Krikamol Muandet
Bo Dai

The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i. i. d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i. i. d. setting, but for generalization across interventions as well. Specifically, we argue that when the outcome generating mechanism is invariant to our choice of DA, then such augmentations can effectively be thought of as interventions on the treatment generating mechanism itself. This can potentially help to reduce bias in causal effect estimation arising from hidden confounders. In the presence of such unobserved confounding we typically make use of instrumental variables (IVs)—sources of treatment randomization that are conditionally independent of the outcome. However, IVs may not be as readily available as DA for many applications, which is the main motivation behind this work. By appropriately regularizing IV based estimators, we introduce the concept of IV-like (IVL) regression for mitigating confounding bias and improving predictive performance across interventions even when certain IV properties are relaxed. Finally, we cast parameterized DA as an IVL regression problem and show that when used in composition can simulate a worst-case application of such DA, further improving performance on causal estimation and generalization tasks beyond what simple DA may offer. This is shown both theoretically for the population case and via simulation experiments for the finite sample case using a simple linear example. We also present real data experiments to support our case.

PDF Details

IROS Conference 2025 Conference Paper

Cross-Level Fusion: Integrating Object Lists with Raw Sensor Data for 3D Object Tracking

Xiangzhong Liu
Xihao Wang
Hao Shen

Smart sensors and Vehicle-To-Everything (V2X) modules are commonly utilized in automotive perception systems, which primarily provide processed object lists rather than raw data. However, high-level fusion approaches suffer from significant information loss and representational misalignment due to the inherently abstract and sparse nature of these high-level outputs. We propose a novel cross-level fusion paradigm that enables bidirectional information flow between object lists and raw vision features within an end-to-end Transformer framework for 3D object detection and tracking. Our approach extracts inherent positional and dimensional cues from object lists to generate two outputs: structured query features that are fused with the initial learnable queries in the Transformer decoder, and soft Gaussian attention masks that guide feature extraction. This integrated mechanism not only improves tracking accuracy by synergistically combining object priors with fine-grained vision data but also promotes hardware economy and AI model sustainability by adapting legacy sensors to evolving sensor setups. To overcome the lack of dedicated datasets, we develop a pseudo object list generation pipeline that simulates realistic sensor tracking behavior. Experiments on the nuScenes dataset demonstrate significant performance gains over vision-only baselines and robust generalization across diverse noise levels, validating the efficacy of our cross-level fusion strategy. The code is available at: https://github.com/CesarLiu/DNF.git.

Details

IJCAI Conference 2025 Conference Paper

Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review

Di Wu
Xian Wei
Guang Chen
Hao Shen
Bo Jin

Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-solving. This survey provides a systematic examination of how EMAS can benefit from these generative capabilities. We propose a taxonomy that categorizes EMAS by system architectures and embodiment modalities, emphasizing how collaboration spans both physical and virtual contexts. Central building blocks, perception, planning, communication, and feedback, are then analyzed to illustrate how generative techniques bolster system robustness and flexibility. Through concrete examples, we demonstrate the transformative effects of integrating foundation models into embodied, multi-agent frameworks. Finally, we discuss challenges and future directions, underlining the significant promise of EMAS to reshape the landscape of AI-driven collaboration.

PDF Details DOI

IROS Conference 2025 Conference Paper

Lywal-X: A Novel Wheel-claw Quadruped Robot

Hao Shen
Yuxuan Yang
Yiliang Wang
Xintian Zuo
Hongwei Zhu
Jianming Wang
Xuan Xiao

This paper introduces a wheel-claw quadruped robot named Lywal-X, which is capable of omnidirectional movement as well as grasping actions. Firstly, the mechanical structure of Lywal-X is designed with a three-degree-of-freedom leg transformation mechanism and a two-degree-of-freedom wheel-claw structure. Then, movement strategies for different modes such as climbing and grasping are developed. Finally, the mobility performance of Lywal-X is analyzed, and physical experiments are conducted to verify the robot’s ability to pick up and transport target objects in both single-claw and double-claw modes.

Details

AAAI Conference 2023 Conference Paper

Adaptive Dynamic Filtering Network for Image Denoising

Hao Shen
Zhong-Qiu Zhao
Wandi Zhang

In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing high-frequency information (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual information in filter generation. To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. Specifically, we design a spatially enhanced kernel generation (SEKG) module to improve dynamic convolution, enabling the learning of spatial context information with a very low computational complexity. Based on the SEKG module, we propose a dynamic convolution block (DCB) and a multi-scale dynamic convolution block (MDCB). The former enhances the high-frequency information via dynamic convolution and preserves low-frequency information via skip connections. The latter utilizes shared adaptive dynamic kernels and the idea of dilated convolution to achieve efficient multi-scale feature extraction. The proposed multi-dimension feature integration (MFI) mechanism further fuses the multi-scale features, providing precise and contextually enriched feature representations. Finally, we build an efficient denoising network with the proposed DCB and MDCB, named ADFNet. It achieves better performance with low computational complexity on real-world and synthetic Gaussian noisy datasets. The source code is available at https://github.com/it-hao/ADFNet.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Towards a Unified Framework of Contrastive Learning for Disentangled Representations

Stefan Matthes
Zhiwei Han
Hao Shen

Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual contrastive losses, such as noise-contrastive estimation (NCE) and InfoNCE, and rely on specific assumptions about the data generating process. This paper extends the theoretical guarantees for disentanglement to a broader family of contrastive methods, while also relaxing the assumptions about the data distribution. Specifically, we prove identifiability of the true latents for four contrastive losses studied in this paper, without imposing common independence assumptions. The theoretical findings are validated on several benchmark datasets. Finally, practical limitations of these methods are also investigated.

PDF Details

NeurIPS Conference 2021 Conference Paper

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

Jinxin Liu
Hao Shen
Donglin Wang
Yachen Kang
Qiangxing Tian

Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure is often time-consuming, limiting the rollout in some potentially expensive target environments. The intuitive approach of training in another interaction-rich environment disrupts the reproducibility of trained skills in the target environment due to the dynamics shifts and thus inhibits direct transferring. Assuming free access to a source environment, we propose an unsupervised domain adaptation method to identify and acquire skills across dynamics. Particularly, we introduce a KL regularized objective to encourage emergence of skills, rewarding the agent for both discovering skills and aligning its behaviors respecting dynamics shifts. This suggests that both dynamics (source and target) shape the reward to facilitate the learning of adaptive skills. We also conduct empirical experiments to demonstrate that our method can effectively learn skills that can be smoothly deployed in target.

PDF Details

ICRA Conference 2020 Conference Paper

3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning

Mi Tian
Qiong Nie
Hao Shen

Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control. Recently end-to-end approaches based on convolutional neural network have been much studied to achieve or even exceed 3D-geometry based traditional methods. In this work, we propose a compact network for absolute camera pose regression. Inspired from those traditional methods, a 3D scene geometry-aware constraint is also introduced by exploiting all available information including motion, depth and image contents. We add this constraint as a regularization term to our proposed network by defining a pixel-level photometric loss and an image-level structural similarity loss. To benchmark our method, different challenging scenes including indoor and outdoor environment are tested with our proposed approach and state-of-the-arts. And the experimental results demonstrate significant performance improvement of our method on both prediction accuracy and convergence efficiency.

Details

AAAI Conference 2020 Conference Paper

A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing

Yinglu Liu
Hailin Shi
Hao Shen
Yue Si
Xiaobo Wang
Tao Mei

Face parsing has recently attracted increasing interest due to its numerous application potentials, such as facial make up and facial image generation. In this paper, we make contributions on face parsing task from two aspects. First, we develop a high-efﬁciency framework for pixel-level face parsing annotating and construct a new large-scale Landmark guided face Parsing dataset (LaPa). It consists of more than 22, 000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with an 11-category pixel-level label map and 106-point landmarks. The dataset is publicly accessible to the community for boosting the advance of face parsing. 1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a threebranch network with elaborately developed loss functions to fully exploit the boundary information. Extensive experiments on our LaPa benchmark and the public Helen dataset show the superiority of our proposed method.

PDF Details

EWRL Workshop 2018 Workshop Paper

Neural Value Function Approximation in Continuous State Reinforcement Learning Problems

Martin Gottwald
Mingpan Guo
Hao Shen

Recent development of Deep Reinforcement Learning (DRL) has demonstrated superior performance of neural networks in solving challenging problems with large or continuous state spaces. In this work, we focus on the problem of minimising the expected one step Temporal Difference (TD) error with neural function approximator for a continuous state space, from a smooth optimisation perspective. An approximate Newton’s algorithm is proposed. Effectiveness of the algorithm is demonstrated on both finite and continuous state space benchmarks. We show that, in order to benefit from the second order approximate Newton’s algorithm, gradient of the TD target needs to be considered for training.

PDF Details

RLDM Conference 2015 Conference Abstract

Reinforcement Learning with Preferences

Johannes Feldmaier
Hao Shen
Klaus Diepold

In this work, we propose a framework of learning with preferences, which combines some neu- rophysiological findings, prospect theory, and the classic reinforcement learning mechanism. Specifically, we extend the state representation of reinforcement learning with a multi-dimensional preference model controlled by an external state. This external state is designed to be independent from the reinforcement learning process so that it can be controlled by an external process simulating the knowledge and experience of an agent while preserving all major properties of reinforcement learning. Finally, numerical experiments show that our proposed method is capable to learn different preferences in a manner sensitive to the agent’s level of experience.

PDF Details