Publications
按研究方向整理论文成果
本页与中文官方主页的研究方向保持一致，按具身智能操控、多智能体集群协同、 目标重识别三个方向展示论文成果。作者列表中加粗显示吕凯老师，* 表示通讯作者。
论文列表
官方主页Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos
方向：具身智能操控。关键词：视觉强化学习、视频预训练、局部运动。
Bidirectional Transition Consistency between Multi-Domain Observations for Visual Reinforcement Learning Generalization
方向：具身智能操控。关键词：视觉强化学习、泛化、多域观测。
Learning Robust Representations via Bidirectional Transition for Visual Reinforcement Learning
方向：具身智能操控。关键词：鲁棒表征、双向转移、视觉强化学习。
From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training
方向：具身智能操控。关键词：强化学习预训练、时序相关、视觉表征。
How to Learn Domain-Invariant Representations for Visual Reinforcement Learning: An Information-Theoretical Perspective
方向：具身智能操控。关键词：域不变表征、信息论、视觉强化学习。
What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction
方向：具身智能操控。关键词：策略一致性、截断回报预测、泛化。
Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation
方向：具身智能操控。关键词：视觉导航、类别图、时空注意力。
Agent-Centric Relation Graph for Object Visual Navigation
方向：具身智能操控。关键词：目标视觉导航、关系图、智能体中心建模。
Skill-based Hierarchical Reinforcement Learning for Target Visual Navigation
方向：具身智能操控。关键词：层次强化学习、技能学习、视觉导航。
Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning
方向：多智能体集群协同。关键词：角色归纳偏置、跨任务泛化、多智能体强化学习。
Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution
方向：多智能体集群协同。关键词：主动推理、去中心化执行、协作决策。
From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination
方向：多智能体集群协同。关键词：关系模式、持续多智能体协同、任务特定决策。
CoDe: Communication Delay-Tolerant Multi-Agent Collaboration via Dual Alignment of Intent and Timeliness
方向：多智能体集群协同。关键词：通信延迟容忍、意图对齐、时效性对齐。
Off-policy Conservative Distributional Reinforcement Learning with Safety Constraints
方向：多智能体集群协同。关键词：安全约束、分布式强化学习、离策略学习。
Enhancing Off-policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation
方向：多智能体集群协同。关键词：约束强化学习、自适应集成估计、离策略学习。
Offline Reinforcement Learning with Diffusion-Based Behavior Cloning Term
方向：多智能体集群协同。关键词：离线强化学习、扩散模型、行为克隆。
Lexicographic Actor-Critic Deep Reinforcement Learning for Urban Autonomous Driving
方向：多智能体集群协同。关键词：自动驾驶、字典序策略、深度强化学习。
A Lightweight and Style-Robust Neural Network for Autonomous Driving in End Side Devices
方向：多智能体集群协同。关键词：自动驾驶、端侧设备、轻量级网络。
Let Confidence Speak: Combining Small and Large Models via Pseudo Labeling for Unsupervised Domain Adaptation
方向：目标重识别。关键词：无监督域适应、伪标签、小模型与大模型协同。
Infer the Whole from a Glimpse of a Part: Keypoint-based Knowledge Graph for Vehicle Re-identification
方向：目标重识别。关键词：车辆重识别、关键点知识图谱、局部到整体推理。
Style Variable and Irrelevant Learning for Generalizable Person Re-identification
方向：目标重识别。关键词：泛化行人重识别、风格变量、无关信息学习。
Spatially-Regularized Features for Vehicle Re-identification: An Explanation of Where Deep Models Should Focus
方向：目标重识别。关键词：车辆重识别、空间正则化、模型可解释性。
Generalization between Different Viewpoints with A Feature Selection Method for Vehicle Re-identification
方向：目标重识别。关键词：车辆重识别、跨视角泛化、特征选择。
Pose-Based View Synthesis for Vehicles: A Perspective Aware Method
方向：目标重识别。关键词：车辆重识别、姿态建模、视角合成。
Improving Driver Gaze Prediction with Reinforced Attention
方向：目标重识别。关键词：驾驶员视线预测、强化注意力、多媒体理解。
Combining Pose Invariant and Discriminative Features for Vehicle Reidentification
方向：目标重识别。关键词：车辆重识别、姿态不变特征、判别性特征。
Vehicle Re-Identification with Location and Time Stamps
方向：目标重识别。关键词：车辆重识别、位置与时间戳、竞赛方案。