Author name cluster

Yichen Wei

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.

7 papers

2 author rows

IROS Conference 2025 Conference Paper

λ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics

Ahmed Jaafar
Shreyas Sundara Raman
Sudarshan S. Harithas
Yichen Wei
Sofia Juliani
Anneke Wernerfelt
Benedict Quartey
Ifrah Idrees

Learning to execute long-horizon mobile manipulation tasks is crucial for advancing robotics in household and workplace settings. However, current approaches are typically data-inefficient, underscoring the need for improved models that require realistically sized benchmarks to evaluate their efficiency. To address this, we introduce the LAMBDA (λ) benchmark 1 ––Long-horizon Actions for Mobile-manipulation Benchmarking of Directed Activities––which evaluates the data efficiency of models on language-conditioned, long-horizon, multi-room, multi-floor, pick-and-place tasks using a dataset of manageable size, more feasible for collection. Our benchmark includes 571 human-collected demonstrations that provide realism and diversity in simulated and real-world settings. Unlike planner-generated data, these trajectories offer natural variability and replay-verifiability, ensuring robust learning and evaluation. We leverage λ to benchmark current end-to-end learning methods and a modular neuro-symbolic approach that combines foundation models with task and motion planning. We find that learning methods, even when pretrained, yield lower success rates, while a neuro-symbolic method performs significantly better and requires less data.

Details

AIJ Journal 2024 Journal Article

A neurosymbolic cognitive architecture framework for handling novelties in open worlds

Shivam Goel
Panagiotis Lymperopoulos
Ravenna Thielstrom
Evan Krause
Patrick Feeney
Pierrick Lorang
Sarah Schneider
Yichen Wei

“Open world” environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This runs counter to the “closed world” assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The types of environments AI agents can be deployed in are limited by the inability to handle the novelties that occur in open world environments. This paper presents a novel cognitive architecture framework to handle open-world novelties. This framework combines symbolic planning, counterfactual reasoning, reinforcement learning, and deep computer vision to detect and accommodate novelties. We introduce general algorithms for exploring open worlds using inference and machine learning methodologies to facilitate novelty accommodation. The ability to detect and accommodate novelties allows agents built on this framework to successfully complete tasks despite a variety of novel changes to the world. Both the framework components and the entire system are evaluated in Minecraft-like simulated environments. Our results indicate that agents are able to efficiently complete tasks while accommodating “concealed novelties” not shared with the architecture development team.

Details DOI

AAMAS Conference 2024 Conference Paper

NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds

Shivam Goel
Yichen Wei
Panagiotis Lymperopoulos
Klára Churá
Matthias Scheutz
Jivko Sinapov

As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the “open-world”. To this end, we introduce NovelGym1, a flexible and adaptable ecosystem designed to simulate gridworld environments, serving as a robust platform for benchmarking reinforcement learning (RL) and hybrid planning and learning agents in open-world contexts. The modular architecture of NovelGym facilitates rapid creation and modification of task environments, including multi-agent scenarios, with multiple environment transformations, thus providing a dynamic testbed for researchers to develop open-world AI agents.

PDF

YNICL Journal 2021 Journal Article

Fusion analysis of gray matter and white matter in subjective cognitive decline and mild cognitive impairment by multimodal CCA-joint ICA

Lingyan Liang
Zaili Chen
Yichen Wei
Fei Tang
Xiucheng Nong
Chong Li
Bihan Yu
Gaoxiong Duan

BACKGROUND: Previous multimodal neuroimaging studies analyzed each dataset independently in subjective cognitive decline (SCD) and mild cognitive impairment (MCI), missing the cross-information. Multi-modal fusion analysis can provide more integral and comprehensive information regarding the brain. There has been a paucity of research on fusion analysis of sMRI and DTI in SCD and MCI. MATERIALS AND METHODS: In the present study, we conducted fusion analysis of structural MRI and DTI by applying multimodal canonical correlation analysis with joint independent component analysis (mCCA-jICA) to capture the cross-information of gray matter (GM) and white matter (WM) in 62 SCD patients, 99 MCI patients, and 70 healthy controls (HCs). We further analyzed correlations between the mixing coefficients of mCCA-jICA and neuropsychological scores among the three groups. RESULTS: A set of joint-discriminative independent components of GM and fractional anisotropy (FA) exhibited significant links between SCD and HCs, as well as between MCI and HCs. The covariant abnormalities primarily involved the frontal lobe/middle temporal gyrus/calcarine sulcus-anterior thalamic radiation/superior longitudinal fasciculus in SCD, and middle temporal gyrus/ fusiform gyrus/caudate necleus-forceps minor/anterior thalamic radiation in MCI. There was no significant difference between SCD and MCI groups. CONCLUSIONS: The covariant GM-WM abnormalities in SCD and MCI were found in specific brain regions involved in cognitive processing, which confirms the simultaneous GM and WM changes underlying cognitive decline. These findings suggest that multimodal fusion analysis allows for a more comprehensive understanding of the association among different types of brain tissues and its crucial role in the neuropathological mechanism of SCD and MCI.

Details DOI

NeurIPS Conference 2021 Conference Paper

SOLQ: Segmenting Objects by Learning Queries

Bin Dong
Fangao Zeng
Tiancai Wang
Xiangyu Zhang
Yichen Wei

In this paper, we propose an end-to-end framework for instance segmentation. Based on the recently introduced DETR, our method, termed SOLQ, segments objects by learning unified queries. In SOLQ, each query represents one object and has multiple representations: class, location and mask. The object queries learned perform classification, box regression and mask encoding simultaneously in an unified vector form. During training phase, the mask vectors encoded are supervised by the compression coding of raw spatial masks. In inference time, mask vectors produced can be directly transformed to spatial masks by the inverse process of compression coding. Experimental results show that SOLQ can achieve state-of-the-art performance, surpassing most of existing approaches. Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR. We hope our SOLQ can serve as a strong baseline for the Transformer-based instance segmentation.

PDF Details

ICLR Conference 2020 Conference Paper

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization

Junjie Yan
Ruosi Wan
Xiangyu Zhang 0005
Wei Zhang 0016
Yichen Wei
Jian Sun 0001

Batch Normalization (BN) is one of the most widely used techniques in Deep Learning field. But its performance can awfully degrade with insufficient batch size. This weakness limits the usage of BN on many computer vision tasks like detection or segmentation, where batch size is usually small due to the constraint of memory consumption. Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption. In this paper, we reveal that there are two extra batch statistics involved in backward propagation of BN, on which has never been well discussed before. The extra batch statistics associated with gradients also can severely affect the training of deep neural network. Based on our analysis, we propose a novel normalization method, named Moving Average Batch Normalization (MABN). MABN can completely restore the performance of vanilla BN in small batch cases, without introducing any additional nonlinear operations in inference procedure. We prove the benefits of MABN by both theoretical analysis and experiments. Our experiments demonstrate the effectiveness of MABN in multiple computer vision tasks including ImageNet and COCO. The code has been released in https://github.com/megvii-model/MABN.

Details

IJCAI Conference 2016 Conference Paper

Model-Based Deep Hand Pose Estimation

Xingyi Zhou
Qingfu Wan
Wei Zhang
Xiangyang Xue
Yichen Wei

Previous learning based hand pose estimation methods does not fully exploit the prior information in hand model geometry. Instead, they usually rely a separate model fitting step to generate valid hand poses. Such a post processing is inconvenient and sub-optimal. In this work, we propose a model based deep learning approach that adopts a forward kinematics based layer to ensure the geometric validity of estimated poses. For the first time, we show that embedding such a non-linear generative process in deep learning is feasible for hand pose estimation. Our approach is verified on challenging public datasets and achieves state-of-the-art performance.

PDF Details