Author name cluster

Hao Hu

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.

18 papers

2 author rows

AAAI Conference 2026 Conference Paper

Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation

Hao Hu
Yifan Feng
Ruoxue Li
Rundong Xue
Xingliang Hou
Zhiqiang Tian
Yue Gao
Shaoyi Du

Retrieval-Augmented Generation (RAG) enhances the response quality and domain-specific performance of large language models (LLMs) by incorporating external knowledge to combat hallucinations. In recent research, graph structures have been integrated into RAG to enhance the capture of semantic relations between entities. However, it primarily focuses on low-order pairwise entity relations, limiting the high-order associations among multiple entities. Hypergraph-enhanced approaches address this limitation by modeling multi-entity interactions via hyperedges, but they are typically constrained to inter-chunk entity-level representations, overlooking the global thematic organization and alignment across chunks. Drawing inspiration from the top-down cognitive process of human reasoning, we propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations. Furthermore, we design a cognitive-inspired two-stage retrieval strategy that first activates query-relevant thematic content from the theme hypergraph, and then guides fine-grained recall and diffusion in the entity hypergraph, achieving semantic alignment and consistent generation from global themes to local details. Our extensive experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Role Hypergraph Contrastive Learning for Multivariate Time-Series Analysis

Rundong Xue
Hao Hu
Zhitao Zeng
Xiangmin Han
Zhiqiang Tian
Shaoyi Du
Yue Gao

Multivariate Time-Series (MTS) analysis is crucial across various domains. Considering the spatial and temporal consistency of MTS, existing methods leverage graph structures with temporal augmentation and contrastive learning to achieve robust learning of spatial dependencies and temporal patterns. Given the inherent high-order correlations in MTS, hypergraphs present a promising approach. However, two key challenges limit their further development: 1) Feature-based perspectives capture limited spatial information, while structural perspectives encode richer spatial consistency and evolution dependency; 2) Various semantic patterns (e.g., synergy, inhibition) entangle in sensor correlations, leading to semantic ambiguity. The underlying reason is that conventional hypergraph structures cannot distinguish specific semantic roles within or across hyperedges. Thus, we propose Role Hypergraph Contrastive Learning for MTS analysis. Specifically, we introduce the concept of role to generalize hypergraphs to Role Hypergraphs, enabling precise modeling of sensor correlations by assigning each vertex-hyperedge pair with a semantic role. Building on this structure, we design a role hypergraph contrastive learning paradigm to comprehensively capture the spatial and temporal dependencies: From a structural perspective, role hypergraph structural contrasting captures spatial short-term consistency and long-term evolution; from a feature perspective, alignment of complementary role information ensures sensor-level temporal consistency. Experiments on classification and forecasting tasks demonstrate the effectiveness and interpretability of our method.

PDF Details DOI

IROS Conference 2025 Conference Paper

A Two-Stage Swarm Planning Framework for Efficient Multi-Drone Waypoint Traversal

Kailun Cui
Fenghua He 0001
Ning Hao
Hao Hu

The multi-drone waypoint traversal has significant potential for aerial robot swarms in various applications. However, it still faces challenges including low time efficiency, susceptibility to local minima, poor resilience to external disturbances, high computational complexity, and high communication burden. To address these issues, we propose a two-stage swarm planning framework by integrating an offline global trajectory generator and an online distributed local trajectory planner. This approach not only ensures time-optimality but also enhances resistance to external disturbances. Specifically, a complementary progress constraint (CPC)-based global trajectory planning method is first presented to generate globally optimal reference trajectories. Then, by taking these trajectories as global guidance, a local planner is designed to guarantee collision-free traversal. In the local planner, we present a distributed local re-planning algorithm by embedding the positional constraints constructed by Voronoi diagrams into the model predictive contouring control (MPCC). The drones only exchange their position information, significantly reducing the communication load. Additionally, the Voronoi-based spatial constraints allow the swarms to eliminate the collision risk caused by asynchronous communication. To reduce onboard computational resource requirements, the local planner adopts the real-time iteration (RTI) technique, executing the optimization only once per control cycle. Both simulation and real-world experiments demonstrate that our approach outperforms state-of-the-art methods in terms of waypoint tracking accuracy, safety, and global time optimality.

Details

NeurIPS Conference 2025 Conference Paper

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

Runpeng Xie
Quanwei Wang
Hao Hu
Zherui Zhou
Ni Mu
Xiyun Li
Yiqin Yang
Shuang Xu

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely degrading algorithmic performance. To address these limitations, we present a novel method named DAIL (Distributional Aligned Learning), featuring two key components: distributional policy and semantic alignment. Specifically, we provide theoretical results that the value distribution estimation mechanism enhances task differentiability. Meanwhile, the semantic alignment module captures the correspondence between trajectories and linguistic instructions. Extensive experimental results on both structured and visual observation benchmarks demonstrate that DAIL effectively resolves instruction ambiguities, achieving superior performance to baseline methods. Our implementation is available at https: //github. com/RunpengXie/Distributional-Aligned-Learning.

PDF Details

EAAI Journal 2025 Journal Article

Domain adaptation based automatic identification method of vortex induced vibration of long-span bridges without prior information

Chunfeng Wan
Jiale Hou
Guangcai Zhang
Shuai Gao
Youliang Ding
Sugong Cao
Hao Hu
Songtao Xue

Machine learning algorithms can sensitively capture the characteristics of vortex induced vibration (VIV) of the girder in long span bridge from the extensive historical data accumulated by structural health monitoring (SHM) system over several years. These algorithms have gradually become a promising method of VIV identification. However, the algorithms proposed by previous researchers require historical VIV data to select the threshold or parameters to identify VIV. Most long-span bridges have not recorded a significant amount of VIV data since VIV is rare, or the bridge were not equipped with SHM system before. This study proposes an adaptive VIV identification method based on domain adaptation methods, which can identify VIV in real-time or in historical monitoring datasets of the target bridge without prior VIV information or parameter settings. The strong generalization ability of the proposed method is verified on the SHM dataset of two long-span suspension bridges in China. It is found that the VIV recognition accuracy of the balanced distribution adaptation (BDA) based VIV identification method is higher than that of other algorithms. In this study, the BDA based algorithm is also applied to the 8 months monitoring datasets of a long span bridge and successfully identifies more than 20 VIV events of the main girder, which has shown the stability and accuracy of the proposed algorithm.

Details DOI

EAAI Journal 2025 Journal Article

Low-light Underwater Image Enhancement with Retinex-guided Mamba network

Jiaquan Yan
Yijian Wang
Hao Hu
Long Yao

Low-light underwater image Enhancement remains a challenging problem, even with advanced deep-learning methods, due to serious illumination degeneration. To address this issue, we present a Retinex-guided Mamba network for low-light Underwater Image Enhancement (RM-UIE), featuring dual pathways dedicated to correction reflectance and illumination maps. Concretely, we first design a Multi-scale Retinex Estimator (MRE) to transform the input image into two intermediary spaces, each approximating the desired reflectance and illumination maps. Then, we develop a 8-Direction Mamba Block (8D-MB) to refine reflectance and illumination maps. The core operator in the 8D-MB is a novel eight-direction Mamba scanning mechanism that can more efficiently extract the spatial relationship of images. Finally, extensive qualitative and quantitative experiments on mainstream datasets demonstrate that the proposed method significantly outperforms existing methods in both illumination and detail restoration. Additionally, the RM-UIE outperforms the mainstream methods, achieving a Peak Signal-to-Noise Ratio (PSNR) of 27. 4237 and a Structural Similarity Index Measure (SSIM) of 0. 8915 on the Underwater Image Enhancement Benchmark (UIEB) dataset, which further validates its effectiveness and generalizability. The code is available at: https: //github. com/WYJGR/RMUIE/.

Details DOI

EAAI Journal 2025 Journal Article

Spatial-temporal modeling for multi-scale wind speed predictions in rail transit networks: A graph neural network-based methodology

Yujie Huang
Zhipeng Zhang
Wenqiang Zhao
Hao Hu

The operation safety and efficiency of rail transit network are vulnerable to strong winds. An essential requirement exists for employing field monitoring data to estimate wind speed trends and make subsequent emergency decisions in time. However, the current warning systems primarily focus on wind speeds at individual monitoring spots or single lines, while the spatial dependency of wind patterns within a larger space context is ignored. To bridge this research gap, this study proposes a pioneering network-scale wind speed prediction approach based on spatial-temporal graph neural networks. First, a simulated wind stress vector field is devised, leveraging time-lagged cross correlation, to enhance the input wind sensors graph. This novel approach improves upon the traditional predefined graph structure, which relies solely on geographical distances. Second, diffusion convolution recurrent neural network is applied to model the spatial-temporal wind diffusion patterns and predict future wind speed. By carrying out comparison analysis on two real-world railroad datasets with different spatial and temporal granularity, the proposed model demonstrates its applicability in multi-scale wind predictions, significantly outperforming widely used baselines, particularly in multi-step ahead predictions. In addition, ablation study is conducted to assess and interpret the contributions of each component within the model. The proposed method in this study, along with obtained prediction results, is expected to support the network dispatching and delay assessment during extreme weather conditions, thereby enhancing the effectiveness of wind warning systems and strengthening rail safety management.

Details DOI

ICRA Conference 2024 Conference Paper

Active Implicit Reconstruction Using One-Shot View Planning

Hao Hu
Sicong Pan
Liren Jin
Marija Popovic
Maren Bennewitz

Active object reconstruction using autonomous robots is gaining great interest. A primary goal in this task is to maximize the information of the object to be reconstructed, given limited on-board resources. Previous view planning methods exhibit inefficiency since they rely on an iterative paradigm based on explicit representations, consisting of (1) planning a path to the next-best view only; and (2) requiring a considerable number of less-gain views in terms of surface coverage. To address these limitations, we propose to integrate implicit representations into the One-Shot View Planning (OSVP). The key idea behind our approach is to use implicit representations to obtain the small missing surface areas instead of observing them with extra views. Therefore, we design a deep neural network, named OSVP, to directly predict a set of views given a dense point cloud refined from an initial sparse observation. To train our OSVP network, we generate supervision labels using dense point clouds refined by implicit representations and set covering optimization problems. Simulated experiments show that our method achieves sufficient reconstruction quality, outperforming several baselines under limited view and movement budgets. We further demonstrate the applicability of our approach in a real-world object reconstruction scenario.

Details

ICRA Conference 2024 Conference Paper

How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF?

Sicong Pan
Liren Jin
Hao Hu
Marija Popovic
Maren Bennewitz

Neural Radiance Fields (NeRFs) are gaining significant interest for online active object reconstruction due to their exceptional memory efficiency and requirement for only posed RGB inputs. Previous NeRF-based view planning methods exhibit computational inefficiency since they rely on an iterative paradigm, consisting of (1) retraining the NeRF when new images arrive; and (2) planning a path to the next best view only. To address these limitations, we propose a non-iterative pipeline based on the Prediction of the Required number of Views (PRV). The key idea behind our approach is that the required number of views to reconstruct an object depends on its complexity. Therefore, we design a deep neural network, named PRVNet, to predict the required number of views, allowing us to tailor the data acquisition based on the object complexity and plan a globally shortest path. To train our PRVNet, we generate supervision labels using the ShapeNet dataset. Simulated experiments show that our PRV-based view planning method outperforms baselines, achieving good reconstruction quality while significantly reducing movement cost and planning time. We further justify the generalization ability of our approach in a real-world experiment.

Details

ICML Conference 2024 Conference Paper

Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents

Zhihan Liu
Hao Hu
Shenao Zhang
Hongyi Guo
Shuqi Ke
Boyi Liu 0001
Zhaoran Wang 0001

Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it is unclear how to complete a given task provably within a minimum number of interactions with the external environment, e. g. , through an internal mechanism of reasoning. To this end, we propose the first framework with provable regret guarantees to orchestrate reasoning and acting, which we call reason for future, act for now ( RAFA ). Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon ( reason for future ). At each step, the LLM agent takes the initial action of the planned trajectory ( act for now ), stores the collected feedback in the memory buffer, and reinvokes the reasoning routine to replan the future trajectory from the new state. The key idea is to cast reasoning in LLMs as learning and planning in Bayesian adaptive Markov decision processes (MDPs). Correspondingly, we prompt LLMs with the memory buffer to estimate the unknown environment (learning) and generate an optimal trajectory for multiple future steps that maximize a value function (planning). The learning and planning subroutines are performed in an in-context manner to emulate the actor-critic update for MDPs. Our theoretical analysis establishes a $\sqrt{T}$ regret, while our experimental validation demonstrates superior empirical performance.

Details

AAAI Conference 2023 Conference Paper

Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery

Yiqin Yang
Hao Hu
Wenzhe Li
Siyuan Li
Jun Yang
Qianchuan Zhao
Chongjie Zhang

Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works have shown that extracting primitive skills from the recurring and temporally extended structures in the logged data yields better learning. However, these methods suffer greatly when the primitives have limited representation ability to recover the original policy space, especially in offline settings. In this paper, we give a quantitative characterization of the performance of offline hierarchical learning and highlight the importance of learning lossless primitives. To this end, we propose to use a flow-based structure as the representation for low-level policies. This allows us to represent the behaviors in the dataset faithfully while keeping the expression ability to recover the whole policy space. We show that such lossless primitives can drastically improve the performance of hierarchical policies. The experimental results and extensive ablation studies on the standard D4RL benchmark show that our method has a good representation ability for policies and achieves superior performance in most tasks.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

Zhihan Liu
Miao Lu
Wei Xiong
Han Zhong
Hao Hu
Shenao Zhang
Sirui Zheng
Zhuoran Yang

In reinforcement learning (RL), balancing exploration and exploitation is crucial for achieving an optimal policy in a sample-efficient way. To this end, existing sample- efficient algorithms typically consist of three components: estimation, planning, and exploration. However, to cope with general function approximators, most of them involve impractical algorithmic components to incentivize exploration, such as data-dependent level-set constraints or complicated sampling procedures. To address this challenge, we propose an easy-to-implement RL framework called Maximize to Explore (MEX), which only needs to optimize unconstrainedly a single objective that integrates the estimation and planning components while balancing exploration and exploitation automatically. Theoretically, we prove that the MEX achieves a sublinear regret with general function approximators and is extendable to the zero-sum Markov game setting. Meanwhile, we adapt deep RL baselines to design practical versions of MEX in both the model-based and model-free settings, which outperform baselines in various MuJoCo environments with sparse reward by a stable margin. Compared with existing sample-efficient algorithms with general function approximators, MEX achieves similar sample efficiency while also enjoying a lower computational cost and is more compatible with modern deep RL methods.

PDF Details

NeurIPS Conference 2023 Conference Paper

Unsupervised Behavior Extraction via Random Intent Priors

Hao Hu
Yiqin Yang
Jianing Ye
Ziqing Mai
Chongjie Zhang

Reward-free data is abundant and contains rich prior knowledge of human behaviors, but it is not well exploited by offline reinforcement learning (RL) algorithms. In this paper, we propose UBER, an unsupervised approach to extract useful behaviors from offline reward-free datasets via diversified rewards. UBER assigns different pseudo-rewards sampled from a given prior distribution to different agents to extract a diverse set of behaviors, and reuse them as candidate policies to facilitate the learning of new tasks. Perhaps surprisingly, we show that rewards generated from random neural networks are sufficient to extract diverse and useful behaviors, some even close to expert ones. We provide both empirical and theoretical evidences to justify the use of random priors for the reward function. Experiments on multiple benchmarks showcase UBER's ability to learn effective and diverse behavior sets that enhance sample efficiency for online RL, outperforming existing baselines. By reducing reliance on human supervision, UBER broadens the applicability of RL to real-world scenarios with abundant reward-free data.

PDF Details

IROS Conference 2022 Conference Paper

A polynomial time approximation scheme for the scheduling problem in the AGV system

Xinrui Li
Chaoyang Wang
Hao Hu
Yanxue Liang

Logistics warehouses face the challenge of fulfilling large bulk pick orders limit in a given time, as the information of logistics orders is different and timeliness. Therefore, in automated warehouses, it is imperative to improve the efficiency and intelligence of order picking by robotic systems. However, the existing automated guided vehicle (AGV) system has only a few fixed functions (such as order sorting and transportation, etc.), which cannot be changed in time according to actual needs. Meanwhile, the scheduling algorithm has only mass heuristics results and a few approximate algorithm results. In this paper, we build a new AGV system, including two kinds of shelves and four kinds of stations, where the system can add new station types according to the actual situation. We establish the equivalent relationship between the order group picking task in this system and the multi-stage hybrid flow shop scheduling problem, without considering the order group transfer process between stations. Furthermore, we propose a polynomial time approximation scheme (PTAS) for the scheduling problem in this system which has been proved to be strongly NP-hard [13].

Details

AAAI Conference 2022 Conference Paper

Optimizing Binary Decision Diagrams with MaxSAT for Classification

Hao Hu
Marie-José Huguet
Mohamed Siala

The growing interest in explainable artificial intelligence (XAI) for critical decision making motivates the need for interpretable machine learning (ML) models. In fact, due to their structure (especially with small sizes), these models are inherently understandable by humans. Recently, several exact methods for computing such models are proposed to overcome weaknesses of traditional heuristic methods by providing more compact models or better prediction quality. Despite their compressed representation of Boolean functions, Binary decision diagrams (BDDs) did not gain enough interest as other interpretable ML models. In this paper, we first propose SAT-based models for learning optimal BDDs (in terms of the number of features) that classify all input examples. Then, we lift the encoding to a MaxSAT model to learn optimal BDDs in limited depths, that maximize the number of examples correctly classified. Finally, we tackle the fragmentation problem by introducing a method to merge compatible subtrees for the BDDs found via the MaxSAT model. Our empirical study shows clear benefits of the proposed approach in terms of prediction quality and interpretability (i. e. , lighter size) compared to the state-of-the-art approaches.

PDF Details

NeurIPS Conference 2021 Conference Paper

On the Estimation Bias in Double Q-Learning

Zhizhou Ren
Guangxiang Zhu
Hao Hu
Beining Han
Jianglun Chen
Chongjie Zhang

Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation. Its variants in the deep Q-learning paradigm have shown great promise in producing reliable value prediction and improving learning performance. However, as shown by prior work, double Q-learning is not fully unbiased and suffers from underestimation bias. In this paper, we show that such underestimation bias may lead to multiple non-optimal fixed points under an approximate Bellman operator. To address the concerns of converging to non-optimal stationary solutions, we propose a simple but effective approach as a partial fix for the underestimation bias in double Q-learning. This approach leverages an approximate dynamic programming to bound the target value. We extensively evaluate our proposed method in the Atari benchmark tasks and demonstrate its significant improvement over baseline algorithms.

PDF Details

IJCAI Conference 2020 Conference Paper

Learning Optimal Decision Trees with MaxSAT and its Integration in AdaBoost

Hao Hu
Mohamed Siala
Emmanuel Hebrard
Marie-José Huguet

Recently, several exact methods to compute decision trees have been introduced. On the one hand, these approaches can find optimal trees for various objective functions including total size, depth or accuracy on the training set and therefore. On the other hand, these methods are not yet widely used in practice and classic heuristics are often still the methods of choice. In this paper we show how the SAT model proposed by [Narodytska et. al 2018] can be lifted to a MaxSAT approach, making it much more practically relevant. In particular, it scales to much larger data sets; the objective function can easily be adapted to take into account combinations of size, depth and accuracy on the training set; and the fine-grained control of the objective function it offers makes it particularly well suited for boosting. Our experiments show promising results. In particular, we show that the prediction quality of our approach often exceeds state of the art heuristics. We also show that the MaxSAT formulation is well adapted for boosting using the well-known AdaBoost Algorithm.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Learning to Adaptively Scale Recurrent Neural Networks

Hao Hu
Liqiang Wang
Guo-Jun Qi

Recent advancements in recurrent neural network (RNN) research have demonstrated the superiority of utilizing multiscale structures in learning temporal representations of time series. Currently, most of multiscale RNNs use fixed scales, which do not comply with the nature of dynamical temporal patterns among sequences. In this paper, we propose Adaptively Scaled Recurrent Neural Networks (ASRNN), a simple but efficient way to handle this problem. Instead of using predefined scales, ASRNNs are able to learn and adjust scales based on different temporal contexts, making them more flexible in modeling multiscale patterns. Compared with other multiscale RNNs, ASRNNs are bestowed upon dynamical scaling capabilities with much simpler structures, and are easy to be integrated with various RNN cells. The experiments on multiple sequence modeling tasks indicate AS- RNNs can efficiently adapt scales based on different sequence contexts and yield better performances than baselines without dynamical scaling abilities.

PDF Details