Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches to solve such compositional tasks remains a challenge. In this work, we aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. First, we propose a new suite of benchmark specifically aimed at compositional tasks, MultiRavens, which allows defining custom task combinations through task modules that are inspired by industrial tasks and exemplify the difficulties in vision-based learning and planning methods. Second, we propose a vision-based end-to-end system architecture, Sequence-Conditioned Transporter Networks, which augments Goal-Conditioned Transporter Networks with sequence-conditioning and weighted sampling and can efficiently learn to solve multi-task long horizon problems. Our analysis suggests that not only the new framework significantly improves pick-and-place performance on novel 10 multi-task benchmark problems, but also the multi-task learning with weighted sampling can vastly improve learning and agent performances on individual tasks.
HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes
Beijing Institute of Technology（北京理工大学）；Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Peking University（北京大学）；Yangtze Delta Region Academy of Beijing Institute of Technology（北京理工大学长三角研究院）
Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making
School of Artificial Intelligence, Beihang University（北航人工智能学院）；Department of Computing Science and Amii, University of Alberta（阿尔伯塔大学计算机科学系和Amii）；Edmonton Research Center, Huawei Canada（华为加拿大埃德蒙顿研究中心）；Hangzhou International Innovation Institute, Beihang University（杭州国际创新院，北航）；School of Artificial Intelligence and Computer Science, North China University of Technology（北中国技术大学人工智能与计算机科学学院）；Research Institute of Multiple Agents and Embodied Intelligence, Peng Cheng Laboratory（鹏城实验室多智能体与具身智能研究院）
SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks
Kuaishou Technology, Beijing, China（快手科技，北京，中国）；Beijing University of Posts and Telecommunications, Beijing, China（北京邮电大学，北京，中国）；Independent Researcher（独立研究员）
STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations
Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA；Merck \& Co., Inc., Cambridge, MA, USA；Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA；Kempner Institute for the Study of Natural；Artificial Intelligence, Harvard University, Allston, MA, USA；Broad Institute of MIT
Asymptotic Analysis of Conditioned Stochastic Gradient Descent
École Polytechnique（巴黎综合理工学院）；Institut Polytechnique de Paris（巴黎理工学院）；ENSAI（法国国立统计与信息分析学院）；École Nationale de la Statistique et de l’Analyse de l’Information（法国国立统计与信息分析学院）
RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design
AI for Good, Microsoft Redmond（微软红mond AI for Good）；Google DeepMind（谷歌DeepMind）；Google Research（谷歌研究）；Institute for Protein Design University of Washington（蛋白质设计研究所华盛顿大学）；Microsoft Research New England（微软新英格兰研究）；Department of Biochemistry Institute for Protein Design University of Washington（生物化学系蛋白质设计研究所华盛顿大学）
