论文列表 2026-05-08

1

通过残差潜在动作学习基于视觉特征的世界模型 Learning Visual Feature-Based World Models via Residual Latent Action

Xinyu Zhang, Zhengtong Xu, Yutian Tao 等6人

2

TriP：一种基于三角形拼图的鲁棒平移平均方法 TriP: A Triangle Puzzle Approach to Robust Translation Averaging

Zhekai Fan, Wanze Li, Jinxin Wang 等4人

3

PISTO：面向随机轨迹优化的近端推断 PISTO: Proximal Inference for Stochastic Trajectory Optimization

Hongzhe Yu, Zinuo Chang, Yongxin Chen

4

基于稀疏拓扑地图引导的掌上型全向视觉无人机探索 Palm-sized Omnidirectional Vision-Based UAV Exploration with Sparse Topological Map Guidance

Zirui Wang, Xinjia Luo, Haotian Sun 等6人

5

基于共收缩的可变气动阻尼：与可变刚度执行器的动态同构 Variable Aerodynamic Damping via Co-Contraction: A Dynamic Isomorphism with Variable Stiffness Actuators

Antonio Franchi

6

BioProVLA-Agent：一种经济实惠、协议驱动、视觉增强、基于VLA的具身多智能体系统，具备闭环推理能力，用于生物实验室操作 BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation

Zhaohui Du, Zhe Wang, Hongmei Fei 等10人

7

AT-VLA：自适应触觉注入以增强视觉-语言-动作模型中的反馈反应 AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models

Xiaoqi Li, Muhe Cai, Jiadong Xu 等8人

8

CSR：具有大规模缓存状态表示的无限时域实时策略 CSR: Infinite-Horizon Real-Time Policies with Massive Cached State Representations

Robin Karlsson, Go Suzui

9

使用视觉对齐的4D雷达的天气鲁棒场景语义 Weather-Robust Scene Semantics with Vision-Aligned 4D Radar

Kali Hamilton, Christoffer Heckman

10

MORPH-U: 基于仿真的高不确定性环境下V2X赋能自动驾驶的多目标弹性运动规划 MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via Simulation

Shih-Yu Lai

11

通过基于锚点的适应逃离机器人操作中的多样性陷阱 Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

Yanzhe Chen, Kevin Yuchen Ma, Qi Lv 等7人

12

PathPainter：将图像生成模型的泛化能力迁移到具身导航 PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation

Yijin Wang, Yuru Tian, Xijie Huang 等8人

13

未来是兼容的吗？诊断世界行动模型中的动态一致性 Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models

Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo 等4人

14

基于搜索的笔记本电脑翻新机器人软件的健壮性测试 Search-based Robustness Testing of Laptop Refurbishing Robotic Software

Erblin Isaku, Hassan Sartaj, Shaukat Ali 等5人

15

如何利用失败演示数据？：使用注意力机制中的分布差异进行模仿学习的有效数据选择 How to utilize failure demo data?: Effective data selection for imitation learning using distribution differences in attention mechanism

Kana Miyamoto, Kanata Suzuki, Tetsuya Ogata

16

MemCompiler：编译，不要注入——用于具身智能体的状态条件记忆 MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents

Xin Ding, Xinrui Wang, Yifan Yang 等12人

17

BrickCraft: 结合情境化手动引导的视觉运动技能组合用于长周期互锁积木组装 BrickCraft: Visuomotor Skill Composition with Situated Manual Guidance for Long-Horizon Interlocking Brick Assembly

Jichuan Yu, Bowei Li, Zhenran Tang 等7人

18

在运行设计域内运行：基于视觉-语言模型的零样本感知 Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models

Berkehan Ünal, Dierend Hauke, Fazlija Dren 等4人

19

PhySPRING：基于图神经网络的物理信息孪生结构保持约简 PhySPRING: Structure-Preserving Reduction of Physics-Informed Twins via GNN

Yixiong Jing, Xingyuan Chen, Guangming Wang 等6人

20

连续POMDP规划中MCTS的有限时间分析 Finite-Time Analysis of MCTS in Continuous POMDP Planning

Da Kong, Vadim Indelman