Yue Hu

AAAI Conference 2026 Conference Paper

Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents

• Qihao Wang
• Yue Hu
• Mingzhe Lu
• Jiayue Wu
• Yanbing Liu
• Yuanmin Tang

The ability of Large Language Models (LLMs) to use ex ternal tools unlocks powerful real-world interactions, mak ing rigorous evaluation essential. However, current bench marks primarily report final accuracy, revealing what mod els can do but obscuring the cognitive bottlenecks that define their true capability boundaries. To move from simple per formance scoring to a diagnostic tool, we introduce a frame workgroundedinCognitive LoadTheory.Ourframeworkde constructs task complexity into two quantifiable components: Intrinsic Load, the inherent structural complexity of the solu tion path, formalized with a novel Tool Interaction Graph; and Extraneous Load, the difficulty arising from ambiguous task presentation. To enable controlled experiments, we construct ToolLoad-Bench, the first benchmark with parametrically ad justable cognitive load. Our evaluation reveals distinct per formance cliffs as cognitive load increases, allowing us to precisely map each model’s capability boundary. We validate that our framework’s predictions are highly calibrated with empirical results, establishing a principled methodology for understanding an agent’s limits and a practical foundation for building more efficient systems.

JBHI Journal 2026 Journal Article

HCA-Net: Hierarchical Contextual Attention Network for Lightweight and Accurate Polyp Segmentation

• Chengcheng Li
• Huiying Xu
• Xinzhong Zhu
• Huiling Chen
• Xinwang Liu
• Yun Liu
• Chang Tang
• Zhendong Chen

Early detection of colorectal polyps is crucial for clinical screening and cancer prevention, where accurate and efficient automatic segmentation plays a pivotal role. However, colonoscopy images often suffer from low contrast, blurred boundaries, and scale variations, making segmentation challenging. Existing encoder-decoder networks (e. g. , U-Net) suffer from asymmetric supervision and feature redundancy, which in turn lead to semantic inconsistency and loss of fine details. While deeper or hybrid designs alleviate these issues, their high complexity and computational burden limit feasibility in real-time clinical practice. To address these challenges, we propose a lightweight segmentation framework, Hierarchical Contextual Attention Network (HCA-Net), consisting of the Redundancy-Suppressed Dual-Path Downsampling (RS-DPD) module and the Boundary-Aware Semantic Alignment Upsampling (BA-SAU) module, applied to the encoder and decoder, respectively. RS-DPD suppresses redundancy while preserving fine-grained details through a dual-path design, whereas BA-SAU leverages cross-layer contextual attention to enforce semantic consistency and enhance boundary sensitivity. Both modules are built upon our proposed Hierarchical Contextual Attention (HCA) mechanism, which combines convolutional projection with pooling-based compression to achieve efficient global modeling and accurate local boundary restoration. In addition, a composite boundary-aware loss function is designed to improve pixel-level accuracy, structural consistency, and robustness in low-contrast and boundary-ambiguous regions. Extensive experiments on public colorectal polyp datasets demonstrate that HCA-Net achieves state-of-the-art (SOTA) segmentation accuracy with significantly improved efficiency, while maintaining robustness under low-contrast and blurred-boundary conditions.

TMLR Journal 2026 Journal Article

Subspace based Federated Unlearning

• Guanghao Li
• Li Shen
• Yan Sun
• Yue Hu
• Han Hu
• Dacheng Tao

Federated learning (FL) enables collaborative machine learning among multiple clients while preserving user data privacy by preventing the exchange of local data. However, when users request to leave the FL system, the trained FL model may still retain information about their contributions. To comply with the right to be forgotten, federated unlearning has been proposed, which aims to remove a designated client's influence from the FL model. Existing federated unlearning methods typically rely on storing historical parameter updates, which may be impractical in resource-constrained FL settings. In this paper, we propose a Subspace-based Federated Unlearning method (SFU) that addresses this challenge without requiring additional storage. SFU updates the model via gradient ascent constrained within a subspace, specifically the orthogonal complement of the gradient descent directions derived from the remaining clients. By projecting the ascending gradient of the target client onto this subspace, SFU can mitigate the contribution of the target client while maintaining model performance on the remaining clients. SFU is communication-efficient, requiring only one round of local training per client to transmit gradient information to the server for model updates. Extensive empirical evaluations on multiple datasets demonstrate that SFU achieves competitive unlearning performance while preserving model utility. Compared to representative baseline methods, SFU consistently shows promising results under various experimental settings.

AAAI Conference 2026 Conference Paper

Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology

• Yatai Ji
• Zhengqiu Zhu
• Yong Zhao
• Beidan Liu
• Chen Gao
• Yihao Zhao
• Sihang Qiu
• Yue Hu

Aerial Visual Object Search (AVOS) tasks in urban environments require Unmanned Aerial Vehicles (UAVs) to autonomously search for and identify target objects based on visual inputs without external guidance. Existing approaches struggle in complex urban environments due to redundant semantic processing, similar object ambiguity, and the exploration-exploitation dilemma. To advance research and support the AVOS task, we introduce CityAVOS, the first benchmark dataset for autonomous search of static urban objects. It features 2,420 tasks of varying difficulty across six object categories, designed to rigorously evaluate UAV search strategies. To solve the AVOS task, we also propose PRPSearcher (Perception-Reasoning-Planning Searcher), a novel agentic method powered by multi-modal large language models (MLLMs) that enables a UAV agent to think and reason like humans on visual cues when searching for objects. Specifically, PRPSearcher constructs three specialized maps: an object-centric dynamic semantic map enhancing spatial perception, a 3D cognitive map based on semantic "attraction" values for target reasoning, and a 3D uncertainty map for balanced exploration-exploitation search. Moreover, we propose a denoising mechanism to mitigate interference from similar objects and design an Inspiration Promote Thought prompting mechanism for adaptive action planning. Experimental results on CityAVOS demonstrate that PRPSearcher surpasses existing baselines in both success rate and search efficiency (on average: +37.69% SR, +28.96% SPL, -30.69% MSS, and -46.40% NE). Our work paves the way for future advances in embodied visual target search.

NeurIPS Conference 2025 Conference Paper

BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation

• Zibo Zhou
• Yue Hu
• Lingkai Zhang
• Zonglin Li
• Siheng Chen

Zero-shot object navigation (ZSON) allows robots to find target objects in unfamiliar environments using natural language instructions, without relying on pre-built maps or task-specific training. Recent general-purpose models, such as large language models (LLMs) and vision-language models (VLMs), equip agents with semantic reasoning abilities to estimate target object locations in a zero-shot manner. However, these models often greedily select the next goal without maintaining a global understanding of the environment and are fundamentally limited in the spatial reasoning necessary for effective navigation. To overcome these limitations, we propose a novel 3D voxel-based belief map that estimates the target’s prior presence distribution within a voxelized 3D space. This approach enables agents to integrate semantic priors from LLMs and visual embeddings with hierarchical spatial structure, alongside real-time observations, to build a comprehensive 3D global posterior belief of the target’s location. Building on this 3D voxel map, we introduce BeliefMapNav, an efficient navigation system with two key advantages: i) grounding LLM semantic reasoning within the 3D hierarchical semantics voxel space for precise target position estimation, and ii) integrating sequential path planning to enable efficient global navigation decisions. Experiments on HM3D and HSSD benchmarks show that BeliefMapNav achieves state-of-the-art (SOTA) Success Rate (SR) and Success weighted by Path Length (SPL), with a notable 9. 7 SPL improvement over the previous best SR method, validating its effectiveness and efficiency.

AAAI Conference 2025 Conference Paper

Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL

• Yihe Zhou
• Yuxuan Zheng
• Yue Hu
• Kaixuan Chen
• Tongya Zheng
• Jie Song
• Mingli Song
• Shunyu Liu

Offline Multi-Agent Reinforcement Learning (MARL) aims to learn optimal joint policies from pre-collected datasets without further interaction with the environment. Despite the encouraging results achieved so far, we identify the policy mismatch problem that arises from employing diverse offline MARL datasets, a highly important ingredient for cooperative generalization yet largely overlooked by existing literature. Specifically, in the case that offline datasets exhibit various optimal joint policies, policy mismatch often occurs when individual actions from different optimal joint actions are combined in a way that results in a suboptimal joint action. In this paper, we introduce a novel Cooperative Policy Agreement (CPA) method, that not only mitigates the policy mismatch problem but also learns to generate diverse joint policies. CPA firstly introduces an autoregressive decision-making mechanism among agents during offline training. This mechanism enables agents to access the actions previously taken by other agents, thereby facilitating effective joint policy matching. Moreover, diverse joint policies can be directly obtained through sequential action sampling from the autoregressive model. Then we further incorporate a policy agreement mechanism to convert these autoregressive joint policies into decentralized policies with a non-autoregressive form, while still ensuring the diversity of the generated policies. This mechanism guarantees that the proposed CPA adheres to the Centralized Training with Decentralized Execution (CTDE) constraint. Experiments conducted on various benchmarks demonstrate that CPA yields superior performance to state-of-the-art competitors.

NeurIPS Conference 2025 Conference Paper

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

• Siyuan Huang
• Liliang Chen
• Pengfei Zhou
• Shengcong Chen
• Yue Liao
• Zhengkai Jiang
• Yue Hu
• Peng Gao

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.

IROS Conference 2025 Conference Paper

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

• Ziqing Zou
• Cong Wang
• Yue Hu
• Xiao Liu
• Bowen Xu
• Rong Xiong
• Changjie Fan
• Yingfeng Chen

The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such applications due to their inability to effectively handle these nonlinearities, while commonly used learning-based methods require extensive interactions with the environment, leading to inefficiency. To address these issues, we introduce EfficientTrack, a trajectory tracking method that integrates model-based learning to manage nonlinear dynamics and leverages closed-loop dynamics to improve learning efficiency, ultimately minimizing tracking errors. We validate our method through comprehensive experiments both in simulation and on a real-world excavator. Comparative experiments in simulation demonstrate that our method outperforms existing learning-based approaches, achieving the highest tracking precision and smoothness with the fewest interactions. Real-world experiments further show that our method remains effective under load conditions and possesses the ability for continual learning, highlighting its practical applicability. For implementation details and source code, please refer to https://github.com/ZiqingZou/EfficientTrack.

NeurIPS Conference 2025 Conference Paper

NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception

• CONGZHANG SHAO
• Quan Yuan
• Guiyang Luo
• Yue Hu
• Danni Wang
• Liu Yilin
• Rui Pan
• Bo Chen

Collaborative perception improves task performance by expanding the perception range through information sharing among agents. Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender. The experimental results demonstrate that NegoCollab significantly outperforms existing methods in common representation-based collaboration approaches. The mechanism of obtaining common representations through negotiation provides a more reliable and flexible option for common representations in heterogeneous collaborative perception.

NeurIPS Conference 2025 Conference Paper

RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models

• Chenxu Niu
• Jie Zhang
• Yanbing Liu
• Yunpeng Li
• Jinta Weng
• Yue Hu

Backdoor attacks pose a significant threat to large language models (LLMs) by embedding malicious triggers that manipulate model behavior. However, existing defenses primarily rely on prior knowledge of backdoor triggers or targets and offer only superficial mitigation strategies, thus struggling to fundamentally address the inherent reliance on unreliable features. To address these limitations, we propose a novel defense strategy, \textit{RepGuard}, that strengthens LLM resilience by adaptively separating abnormal features from useful semantic representations, rendering the defense agnostic to specific trigger patterns. Specifically, we first introduce a dual-perspective feature localization strategy that integrates local consistency and sample-wise deviation metrics to identify suspicious backdoor patterns. Based on this identification, an adaptive mask generation mechanism is applied to isolate backdoor-targeted shortcut features by decomposing hidden representations into independent spaces, while preserving task-relevant semantics. With a multi-objective optimization framework, our method can inherently mitigates backdoor attacks. Across \textit{Target Refusal} and \textit{Jailbreak} tasks under four types of attacks, RepGuard consistently reduced the attack success rate on poisoned data by nearly 80\% on average, while maintaining near-original task performance on clean data. Extensive experiments demonstrate that RepGuard provides a scalable and interpretable solution for safeguarding LLMs against sophisticated backdoor threats.

ICLR Conference 2025 Conference Paper

Self-Evolving Multi-Agent Collaboration Networks for Software Development

• Yue Hu
• Yuzhu Cai
• Yaxin Du
• Xinyu Zhu
• Xiangrui Liu
• Zijie Yu
• Yuchen Hou
• Shuo Tang

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose RSD-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in RSD-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level RSD-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities.

AAAI Conference 2024 Conference Paper

Context-I2W: Mapping Images to Context-Dependent Words for Accurate Zero-Shot Composed Image Retrieval

• Yuanmin Tang
• Jing Yu
• Keke Gai
• Jiamin Zhuang
• Gang Xiong
• Yue Hu
• Qi Wu

Different from the Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to learn a more accurate image representation that has adaptive attention to the reference image for various manipulation descriptions. In this paper, we propose a novel context-dependent mapping network, named Context-I2W, for adaptively converting description-relevant Image information into a pseudo-word token composed of the description for accurate ZS-CIR. Specifically, an Intent View Selector first dynamically learns a rotation rule to map the identical image to a task-specific manipulation view. Then a Visual Target Extractor further captures local information covering the main targets in ZS-CIR tasks under the guidance of multiple learnable queries. The two complementary modules work together to map an image to a context-dependent pseudo-word token without extra supervision. Our model shows strong generalization ability on four ZS-CIR tasks, including domain conversion, object composition, object manipulation, and attribute manipulation. It obtains consistent and significant performance boosts ranging from 1.88% to 3.60% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://anonymous.4open.science/r/Context-I2W-4224/.

NeurIPS Conference 2023 Conference Paper

Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow

• Sizhe Wei
• Yuxi Wei
• Yue Hu
• Yifan Lu
• Yiqi Zhong
• Siheng Chen
• Ya Zhang

Collaborative perception can substantially boost each agent's perception ability by facilitating communication among multiple agents. However, temporal asynchrony among agents is inevitable in the real world due to communication delays, interruptions, and clock misalignments. This issue causes information mismatch during multi-agent fusion, seriously shaking the foundation of collaboration. To address this issue, we propose CoBEVFlow, an asynchrony-robust collaborative perception system based on bird's eye view (BEV) flow. The key intuition of CoBEVFlow is to compensate motions to align asynchronous collaboration messages sent by multiple agents. To model the motion in a scene, we propose BEV flow, which is a collection of the motion vector corresponding to each spatial location. Based on BEV flow, asynchronous perceptual features can be reassigned to appropriate positions, mitigating the impact of asynchrony. CoBEVFlow has two advantages: (i) CoBEVFlow can handle asynchronous collaboration messages sent at irregular, continuous time stamps without discretization; and (ii) with BEV flow, CoBEVFlow only transports the original perceptual features, instead of generating new perceptual features, avoiding additional noises. To validate CoBEVFlow's efficacy, we create IRregular V2V(IRV2V), the first synthetic collaborative perception dataset with various temporal asynchronies that simulate different real-world scenarios. Extensive experiments conducted on both IRV2V and the real-world dataset DAIR-V2X show that CoBEVFlow consistently outperforms other baselines and is robust in extremely asynchronous settings. The code is available at https: //github. com/MediaBrain-SJTU/CoBEVFlow.

NeurIPS Conference 2023 Conference Paper

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

• Ping Guo
• Xiangpeng Wei
• Yue Hu
• Baosong Yang
• Dayiheng Liu
• Fei Huang
• Jun Xie

Expressing universal semantics common to all languages is helpful to understand the meanings of complex and culture-specific sentences. The research theme underlying this scenario focuses on learning universal representations across languages with the usage of massive parallel corpora. However, due to the sparsity and scarcity of parallel data, there is still a big challenge in learning authentic ``universals'' for any two languages. In this paper, we propose Emma-X: an EM-like Multilingual pre-training Algorithm, to learn Cross-lingual universals with the aid of excessive multilingual non-parallel data. Emma-X unifies the cross-lingual representation learning task and an extra semantic relation prediction task within an EM framework. Both the extra semantic classifier and the cross-lingual sentence encoder approximate the semantic relation of two sentences, and supervise each other until convergence. To evaluate Emma-X, we conduct experiments on xrete, a newly introduced benchmark containing 12 widely studied cross-lingual tasks that fully depend on sentence-level representations. Results reveal that Emma-X achieves state-of-the-art performance. Further geometric analysis of the built representation space with three requirements demonstrates the superiority of Emma-X over advanced models.

AAAI Conference 2023 Conference Paper

Learning to Know Myself: A Coarse-to-Fine Persona-Aware Training Framework for Personalized Dialogue Generation

• Yunpeng Li
• Yue Hu
• Yajing Sun
• Luxi Xing
• Ping Guo
• Yuqiang Xie
• Wei Peng

A critical challenge for open-domain dialogue agents is to generate persona-relevant and consistent responses. Due to the nature of persona sparsity in conversation scenarios, previous persona-based dialogue agents trained with Maximum Likelihood Estimation tend to overlook the given personas and generate responses irrelevant or inconsistent with personas. To address this problem, we propose a two-stage coarse-to-fine persona-aware training framework to improve the persona consistency of a dialogue agent progressively. Specifically, our framework first trains the dialogue agent to answer the constructed persona-aware questions, making it highly sensitive to the personas to generate persona-relevant responses. Then the dialogue agent is further trained with a contrastive learning paradigm by explicitly perceiving the difference between the consistent and the generated inconsistent responses, forcing it to pay more attention to the key persona information to generate consistent responses. By applying our proposed training framework to several representative baseline models, experimental results show significant boosts on both automatic and human evaluation metrics, especially the consistency of generated responses.

IJCAI Conference 2022 Conference Paper

Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation

• Wei Peng
• Yue Hu
• Luxi Xing
• Yuqiang Xie
• Yajing Sun
• Yunpeng Li

Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task. It requires the system to explore the cause of help-seeker's emotional distress and understand their psychological intention to provide supportive responses. However, existing methods mainly focus on the sequential contextual information, ignoring the hierarchical relationships with the global cause and local psychological intention behind conversations, thus leads to a weak ability of emotional support. In this paper, we propose a Global-to-Local Hierarchical Graph Network to capture the multi-source information (global cause, local intentions and dialog history) and model hierarchical relationships between them, which consists of a multi-source encoder, a hierarchical graph reasoner, and a global-guide decoder. Furthermore, a novel training objective is designed to monitor semantic information of the global cause. Experimental results on the emotional support conversation dataset, ESConv, confirm that the proposed GLHG has achieved the state-of-the-art performance on the automatic and human evaluations.

TIST Journal 2022 Journal Article

Detecting Extreme Traffic Events Via a Context Augmented Graph Autoencoder

• Yue Hu
• Ao Qu
• Dan Work

Accurate and timely detection of large events on urban transportation networks enables informed mobility management. This work tackles the problem of extreme event detection on large-scale transportation networks using origin-destination mobility data, which is now widely available. Such data is highly structured in time and space, but high dimensional and sparse. Current multivariate time series anomaly detection methods cannot fully address these challenges. To exploit the structure of mobility data, we formulate the event detection problem in a novel way, as detecting anomalies in a set of time-dependent directed weighted graphs. We further propose a Context augmented Graph Autoencoder (Con-GAE) model to solve the problem, which leverages graph embedding and context embedding techniques to capture the spatial and temporal patterns. Con-GAE adopts an autoencoder framework and detects anomalies via semi-supervised learning. The performance of the method is assessed on several city-scale travel-time datasets from Uber Movement, New York taxis, and Chicago taxis and compared to state-of-the-art approaches. The proposed Con-GAE can achieve an improvement in the area under the curve score as large as 0.15 over the second best method. We also discuss real-world traffic anomalies detected by Con-GAE.

NeurIPS Conference 2022 Conference Paper

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

• Yue Hu
• Shaoheng Fang
• Zixing Lei
• Yiqi Zhong
• Siheng Chen

Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence map, we propose Where2comm, a communication-efficient collaborative perception framework. Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication. To evaluate Where2comm, we consider 3D object detection in both real-world and simulation scenarios with two modalities (camera/LiDAR) and two agent types (cars/drones) on four datasets: OPV2V, V2X-Sim, DAIR-V2X, and our original CoPerception-UAVs. Where2comm consistently outperforms previous methods; for example, it achieves more than $100, 000 \times$ lower communication volume and still outperforms DiscoNet and V2X-ViT on OPV2V. Our code is available at~\url{https: //github. com/MediaBrain-SJTU/where2comm}.

AAAI Conference 2021 Conference Paper

A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition

• Yongxiu Xu
• Heyan Huang
• Chong Feng
• Yue Hu

In recent years, researchers have shown an increased interest in recognizing the overlapping entities that have nested structures. However, most existing models ignore the semantic correlation between words under different entity types. Considering words in sentence play different roles under different entity types, we argue that the correlation intensities of pairwise words in sentence for each entity type should be considered. In this paper, we treat named entity recognition as a multi-class classification of word pairs and design a simple neural model to handle this issue. Our model applies a supervised multi-head self-attention mechanism, where each head corresponds to one entity type, to construct the wordlevel correlations for each type. Our model can flexibly predict the span type by the correlation intensities of its head and tail under the corresponding type. In addition, we fuse entity boundary detection and entity classification by a multitask learning framework, which can capture the dependencies between these two tasks. To verify the performance of our model, we conduct extensive experiments on both nested and flat datasets. The experimental results show that our model can outperform the previous state-of-the-art methods on multiple tasks without any extra NLP tools or human annotations.

IJCAI Conference 2021 Conference Paper

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

• Jing Yu
• Yuan Chai
• Yujing Wang
• Yue Hu
• Qi Wu

Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional debiasing research mainly studies from the view of balancing data distribution or learning unbiased models and representations, ignoring the correlations among the biased classes. In this work, we analyze this problem from a novel cognition perspective: automatically building a hierarchical cognitive structure from the biased predictions and navigating that hierarchy to locate the relationships, making the tail relationships receive more attention in a coarse-to-fine mode. To this end, we propose a novel debiasing Cognition Tree (CogTree) loss for unbiased SGG. We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model. The CogTree distinguishes remarkably different relationships at first and then focuses on a small portion of easily confused ones. Then, we propose a debiasing loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships. The loss is model-agnostic and consistently boosting the performance of several state-of-the-art models. The code is available at: https: //github. com/CYVincent/Scene-Graph-Transformer-CogTree.

JAIR Journal 2021 Journal Article

Regarding Goal Bounding and Jump Point Search

• Yue Hu
• Daniel Harabor
• Long Qin
• Quanjun Yin

Jump Point Search (JPS) is a well known symmetry-breaking algorithm that can substantially improve performance for grid-based optimal pathfinding. When the input grid is static further speedups can be obtained by combining JPS with goal bounding techniques such as Geometric Containers (instantiated as Bounding Boxes) and Compressed Path Databases. Two such methods, JPS+BB and Two-Oracle Path PlannING (Topping), are currently among the fastest known approaches for computing shortest paths on grids. The principal drawback for these algorithms is the overhead costs: each one requires an all-pairs precomputation step, the running time and subsequent storage costs of which can be prohibitive. In this work we consider an alternative approach where we precompute and store goal bounding data only for grid cells which are also jump points. Since the number of jump points is usually much smaller than the total number of grid cells, we can save up to orders of magnitude in preprocessing time and space. Considerable precomputation savings do not necessarily mean performance degradation. For a second contribution we show how canonical orderings, partial expansion strategies and enhanced intermediate pruning can be leveraged to improve online query performance despite a reduction in preprocessed data. The combination of faster preprocessing and stronger online reasoning leads to three new and highly performant algorithms: JPS+BB+ and Two-Oracle Pathfinding Search (TOPS) based on search, and Topping+ based on path extraction. We give a theoretical analysis showing that each method is complete and optimal. We also report convincing gains in a comprehensive empirical evaluation that includes almost all current and cutting-edge algorithms for grid-based pathfinding.

AAAI Conference 2021 Conference Paper

Unsupervised Learning of Deterministic Dialogue Structure with Edge-Enhanced Graph Auto-Encoder

• Yajing Sun
• Yong Shan
• Chengguang Tang
• Yue Hu
• Yinpei Dai
• Jing Yu
• Jian Sun
• Fei Huang

It is important for task-oriented dialogue systems to discover the dialogue structure (i. e. the general dialogue flow) from dialogue corpora automatically. Previous work models dialogue structure by extracting latent states for each utterance first and then calculating the transition probabilities among states. These two-stage methods ignore the contextual information when calculating the probabilities, which makes the transitions between the states ambiguous. This paper proposes a conversational graph (CG) to represent deterministic dialogue structure where nodes and edges represent the utterance and context information respectively. An unsupervised Edge- Enhanced Graph Auto-Encoder (EGAE) architecture is designed to model local-contextual and global-structural information for conversational graph learning. Furthermore, a selfsupervised objective is introduced with the response selection task to guide the unsupervised learning of the dialogue structure. Experimental results on several public datasets demonstrate that the novel model outperforms several alternatives in aggregating utterances with similar semantics. The effectiveness of the learned dialogue structured is also verified by more than 5% joint accuracy improvement in the downstream task of low resource dialogue state tracking.

IJCAI Conference 2020 Conference Paper

DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue

• Xiaoze Jiang
• Jing Yu
• Yajing Sun
• Zengchang Qin
• Zihao Zhu
• Yue Hu
• Qi Wu

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1. 0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is available at https: //github. com/JXZe/DAM.

AAAI Conference 2020 Conference Paper

DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue

• Xiaoze Jiang
• Jing Yu
• Zengchang Qin
• Yingying Zhuang
• Xingxing Zhang
• Yue Hu
• Qi Wu

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects, relationships or semantics. The key challenge in Visual Dialogue task is thus to learn a more comprehensive and semantic-rich image representation which may have adaptive attentions on the image for variant questions. In this research, we propose a novel model to depict an image from both visual and semantic perspectives. Specifically, the visual view helps capture the appearance-level information, including objects and their relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Futhermore, on top of such multiview image features, we propose a feature selection framework which is able to adaptively capture question-relevant information hierarchically in fine-grained level. The proposed method achieved state-of-the-art results on benchmark Visual Dialogue datasets. More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values. It gives us insights in understanding of human cognition in Visual Dialogue.

IJCAI Conference 2020 Conference Paper

Graph Neural Architecture Search

• Yang Gao
• Hong Yang
• Peng Zhang
• Chuan Zhou
• Yue Hu

Graph neural networks (GNNs) emerged recently as a powerful tool for analyzing non-Euclidean data such as social network data. Despite their success, the design of graph neural networks requires heavy manual work and domain knowledge. In this paper, we present a graph neural architecture search method (GraphNAS) that enables automatic design of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and trains the recurrent network with policy gradient to maximize the expected accuracy of the generated architectures on a validation data set. Furthermore, to improve the search efficiency of GraphNAS on big networks, GraphNAS restricts the search space from an entire architecture space to a sequential concatenation of the best search results built on each single architecture layer. Experiments on real-world datasets demonstrate that GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of validation set accuracy. Moreover, in a transfer learning task we observe that graph neural architectures designed by GraphNAS, when transferred to new datasets, still gain improvement in terms of prediction accuracy.

AAAI Conference 2020 Conference Paper

History-Adaption Knowledge Incorporation Mechanism for Multi-Turn Dialogue System

• Yajing Sun
• Yue Hu
• Luxi Xing
• Jing Yu
• Yuqiang Xie

Keeping the conversation consistent and avoiding its repetition are two key factors to construct an intelligent multiturn knowledge-grounded dialogue system. Although some works tend to combine history with external knowledge such as personal background information to boost dialogue quality, they are prone to ignore the fact that incorporating the same knowledge multiple times into the conversation leads to repetition. The main reason is the lack of effective control over the use of knowledge on the conversation level. So we design a history-adaption knowledge incorporation mechanism to build an effective multi-turn dialogue model. Our proposed model addresses repetition by recurrently updating the knowledge from the conversation level and progressively incorporating it into the history step-by-step. And the knowledge-grounded history representation also enhances the conversation consistency. Experimental results show that our proposed model significantly outperforms several retrievalbased models on some benchmark datasets. The human evaluation demonstrates that our model can maintain conversation consistent and reduce conversation repetition.

IJCAI Conference 2020 Conference Paper

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

• Zihao Zhu
• Jing Yu
• Yujing Wang
• Yajing Sun
• Yue Hu
• Qi Wu

Fact-based Visual Question Answering (FVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. On top of the multi-layer graph representations, we propose a modality-aware heterogeneous graph convolutional network to capture evidence from different layers that is most relevant to the given question. Specifically, the intra-modal graph convolution selects evidence from each modality and cross-modal graph convolution aggregates relevant information across different graph layers. By stacking this process multiple times, our model performs iterative reasoning across three modalities and predicts the optimal answer by analyzing all question-oriented evidence. We achieve a new state-of-the-art performance on the FVQA task and demonstrate the effectiveness and interpretability of our model with extensive experiments.

IJCAI Conference 2019 Conference Paper

Robust Embedding with Multi-Level Structures for Link Prediction

• Zihan Wang
• Zhaochun Ren
• Chunyu He
• Peng Zhang
• Yue Hu

Knowledge Graph (KG) embedding has become crucial for the task of link prediction. Recent work applies encoder-decoder models to tackle this problem, where an encoder is formulated as a graph neural network (GNN) and a decoder is represented by an embedding method. These approaches enforce embedding techniques with structure information. Unfortunately, existing GNN-based frameworks still confront 3 severe problems: low representational power, stacking in a flat way, and poor robustness to noise. In this work, we propose a novel multi-level graph neural network (M-GNN) to address the above challenges. We first identify an injective aggregate scheme and design a powerful GNN layer using multi-layer perceptrons (MLPs). Then, we define graph coarsening schemes for various kinds of relations, and stack GNN layers on a series of coarsened graphs, so as to model hierarchical structures. Furthermore, attention mechanisms are adopted so that our approach can make predictions accurately even on the noisy knowledge graph. Results on WN18 and FB15k datasets show that our approach is effective in the standard link prediction task, significantly and consistently outperforming competitive baselines. Furthermore, robustness analysis on FB15k-237 dataset demonstrates that our proposed M-GNN is highly robust to sparsity and noise.

AAAI Conference 2019 Conference Paper

Translating with Bilingual Topic Knowledge for Neural Machine Translation

• Xiangpeng Wei
• Yue Hu
• Luxi Xing
• Yipeng Wang
• Li Gao

The dominant neural machine translation (NMT) models that based on the encoder-decoder architecture have recently achieved the state-of-the-art performance. Traditionally, the NMT models only depend on the representations learned during training for mapping a source sentence into the target domain. However, the learned representations often suffer from implicit and inadequately informed properties. In this paper, we propose a novel bilingual topic enhanced NMT (BLT- NMT) model to improve translation performance by incorporating bilingual topic knowledge into NMT. Specifically, the bilingual topic knowledge is included into the hidden states of both encoder and decoder, as well as the attention mechanism. With this new setting, the proposed BLT-NMT has access to the background knowledge implied in bilingual topics which is beyond the sequential context, and enables the attention mechanism to attend to topic-level attentions for generating accurate target words during translation. Experimental results show that the proposed model consistently outperforms the traditional RNNsearch and the previous topic-informed NMT on Chinese-English and English- German translation tasks. We also introduce the bilingual topic knowledge into the newly emerged Transformer base model on English-German translation and achieve a notable improvement.

IJCAI Conference 2018 Conference Paper

Active Discriminative Network Representation Learning

• Li Gao
• Hong Yang
• Chuan Zhou
• Jia Wu
• Shirui Pan
• Yue Hu

Most of current network representation models are learned in unsupervised fashions, which usually lack the capability of discrimination when applied to network analysis tasks, such as node classification. It is worth noting that label information is valuable for learning the discriminative network representations. However, labels of all training nodes are always difficult or expensive to obtain and manually labeling all nodes for training is inapplicable. Different sets of labeled nodes for model learning lead to different network representation results. In this paper, we propose a novel method, termed as ANRMAB, to learn the active discriminative network representations with a multi-armed bandit mechanism in active learning setting. Specifically, based on the networking data and the learned network representations, we design three active learning query strategies. By deriving an effective reward scheme that is closely related to the estimated performance measure of interest, ANRMAB uses a multi-armed bandit mechanism for adaptive decision making to select the most informative nodes for labeling. The updated labeled nodes are then used for further discriminative network representation learning. Experiments are conducted on three public data sets to verify the effectiveness of ANRMAB.

IJCAI Conference 2018 Conference Paper

Knowledge-Guided Agent-Tactic-Aware Learning for StarCraft Micromanagement

• Yue Hu
• Juntao Li
• Xi Li
• Gang Pan
• Mingliang Xu

As an important and challenging problem in artificial intelligence (AI) game playing, StarCraft micromanagement involves a dynamically adversarial game playing process with complex multi-agent control within a large action space. In this paper, we propose a novel knowledge-guided agent-tactic-aware learning scheme, that is, opponent-guided tactic learning (OGTL), to cope with this micromanagement problem. In principle, the proposed scheme takes a two-stage cascaded learning strategy which is capable of not only transferring the human tactic knowledge from the human-made opponent agents to our AI agents but also improving the adversarial ability. With the power of reinforcement learning, such a knowledge-guided agent-tactic-aware scheme has the ability to guide the AI agents to achieve high winning-rate performances while accelerating the policy exploration process in a tactic-interpretable fashion. Experimental results demonstrate the effectiveness of the proposed scheme against the state-of-the-art approaches in several benchmark combat scenarios.

IJCAI Conference 2018 Conference Paper

Recommendation with Multi-Source Heterogeneous Information

• Li Gao
• Hong Yang
• Jia Wu
• Chuan Zhou
• Weixue Lu
• Yue Hu

Network embedding has been recently used in social network recommendations by embedding low-dimensional representations of network items for recommendation. However, existing item recommendation models in social networks suffer from two limitations. First, these models partially use item information and mostly ignore important contextual information in social networks such as textual content and social tag information. Second, network embedding and item recommendations are learned in two independent steps without any interaction. To this end, we in this paper consider item recommendations based on heterogeneous information sources. Specifically, we combine item structure, textual content and tag information for recommendation. To model the multi-source heterogeneous information, we use two coupled neural networks to capture the deep network representations of items, based on which a new recommendation model Collaborative multi-source Deep Network Embedding (CDNE for short) is proposed to learn different latent representations. Experimental results on two real-world data sets demonstrate that CDNE can use network representation learning to boost the recommendation performance.

AAAI Conference 2018 Conference Paper

Social Recommendation with an Essential Preference Space

• Chun-Yi Liu
• Chuan Zhou
• Jia Wu
• Yue Hu
• Li Guo

Social recommendation, which aims to exploit social information to improve the quality of a recommender system, has attracted an increasing amount of attention in recent years. A large portion of existing social recommendation models are based on the tractable assumption that users consider the same factors to make decisions in both recommender systems and social networks. However, this assumption is not in concert with real-world situations, since users usually show different preferences in different scenarios. In this paper, we investigate how to exploit the differences between user preference in recommender systems and that in social networks, with the aim to further improve the social recommendation. In particular, we assume that the user preferences in different scenarios are results of different linear combinations from a more underlying user preference space. Based on this assumption, we propose a novel social recommendation framework, called social recommendation with an essential preferences space (SREPS), which simultaneously models the structural information in the social network, the rating and the consumption information in the recommender system under the capture of essential preference space. Experimental results on four real-world datasets demonstrate the superiority of the proposed SREPS model compared with seven stateof-the-art social recommendation methods.

AAAI Conference 2017 Conference Paper

Collaborative Dynamic Sparse Topic Regression with User Profile Evolution for Item Recommendation

• Li Gao
• Jia Wu
• Chuan Zhou
• Yue Hu

In many time-aware item recommender systems, modeling the accurate evolution of both user profiles and the contents of items over time is essential. However, most existing methods focus on learning users’ dynamic interests, where the contents of items are assumed to be stable over time. They thus fail to capture the dynamic changes in the item’s contents. In this paper, we present a novel method CDUE for time-aware item recommendation, which captures the evolution of both user’s interests and item’s contents information via topic dynamics. Specifically, we propose a dynamic sparse topic model to track the evolution of topics for changes in items’ contents over time and adapt a vector autoregressive model to profile users’ dynamic interests. The item’s topics and user’s interests and their evolutions are learned collaboratively and simultaneously into a unified learning framework. Experimental results on two real-world data sets demonstrate the quality and effectiveness of the proposed method and show that our method can be used to make better future recommendations.

AAAI Conference 2016 Conference Paper

On the Minimum Differentially Resolving Set Problem for Diffusion Source Inference in Networks

• Chuan Zhou
• Wei-Xue Lu
• Peng Zhang
• Jia Wu
• Yue Hu
• Li Guo

In this paper we theoretically study the minimum Differentially Resolving Set (DRS) problem derived from the classical sensor placement optimization problem in network source locating. A DRS of a graph G = (V, E) is defined as a subset S ⊆ V where any two elements in V can be distinguished by their different differential characteristic sets defined on S. The minimum DRS problem aims to find a DRS S in the graph G with minimum total weight v∈S w(v). In this paper we establish a group of Integer Linear Programming (ILP) models as the solution. By the weighted set cover theory, we propose an approximation algorithm with the Θ(ln n) approximability for the minimum DRS problem on general graphs, where n is the graph size.

IJCAI Conference 2016 Conference Paper

Semi-Data-Driven Network Coarsening

• Li Gao
• Jia Wu
• Hong Yang
• Zhi Qiao
• Chuan Zhou
• Yue Hu

Network coarsening refers to a new class of graph `zoom-out' operations by grouping similar nodes and edges together so that a smaller equivalent representation of the graph can be obtained for big network analysis. Existing network coarsening methods consider that network structures are static and thus cannot handle dynamic networks. On the other hand, data-driven approaches can infer dynamic network structures by using network information spreading data. However, existing data-driven approaches neglect static network structures that are potentially useful for inferring big networks. In this paper, we present a new semi-data-driven network coarsening model to learn coarsened networks by embedding both static network structure data and dynamic network information spreading data. We prove that the learning model is convex and the Accelerated Proximal Gradient algorithm is adapted to achieve the global optima. Experiments on both synthetic and real-world data sets demonstrate the quality and effectiveness of the proposed method.

IJCAI Conference 2013 Conference Paper

PPSGen: Learning to Generate Presentation Slides for Academic Papers

• Yue Hu
• Xiaojun Wan