Zobrazeno 21 - 30
of 1 415
pro vyhledávání: '"Li, Jiachen"'
Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications. However, collecting massive and annotated real-world human datasets has been a laborious task, esp
Externí odkaz:
http://arxiv.org/abs/2403.06041
Offline learning has become widely used due to its ability to derive effective policies from offline datasets gathered by expert demonstrators without interacting with the environment directly. Recent research has explored various ways to enhance off
Externí odkaz:
http://arxiv.org/abs/2402.18617
Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. While modeling pairwise relations has been widely studied in multi-agent interacting systems, the a
Externí odkaz:
http://arxiv.org/abs/2401.12275
We present an efficient particle-particle random phase approximation (ppRPA) approach that predicts accurate excitation energies of point defects, including the nitrogen-vacancy (NV$^-$) and the silicon-vacancy (SiV$^0$) centers in diamond and the di
Externí odkaz:
http://arxiv.org/abs/2401.10483
Publikováno v:
GLIndA Workshop NeurIPS 2022
Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data. In this paper, we propose and demonstrat
Externí odkaz:
http://arxiv.org/abs/2401.05610
Publikováno v:
IEEE Robotics and Automation Letters, Date: FEBRUARY 2024 , Volume: 9, Issue: 2, ISSN: 2377-3766, pp1452-1459
Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have been devoted
Externí odkaz:
http://arxiv.org/abs/2401.03599
Autor:
Yao, Bingsheng, Chen, Guiming, Zou, Ruishi, Lu, Yuxuan, Li, Jiachen, Zhang, Shao, Sang, Yisi, Liu, Sijia, Hendler, James, Wang, Dakuo
While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can not we design and leverage multiple prompts together to further improv
Externí odkaz:
http://arxiv.org/abs/2311.09782
Autor:
Li, Jiachen, Henschel, Roberto, Goel, Vidit, Ohanyan, Marianna, Navasardyan, Shant, Shi, Humphrey
Conventional video matting outputs one alpha matte for all instances appearing in a video frame so that individual instances are not distinguished. While video instance segmentation provides time-consistent instance masks, results are unsatisfactory
Externí odkaz:
http://arxiv.org/abs/2311.04212
Autor:
Li, Jiachen, Gong, Xiaojin
This work aims to adapt large-scale pre-trained vision-language models, such as contrastive language-image pretraining (CLIP), to enhance the performance of object reidentification (Re-ID) across various supervision settings. Although prompt learning
Externí odkaz:
http://arxiv.org/abs/2310.17218
We present a machine learning (ML) framework for predicting Green's functions of molecular systems, from which photoemission spectra and quasiparticle energies at quantum many-body level can be obtained. Kernel ridge regression is adopted to predict
Externí odkaz:
http://arxiv.org/abs/2310.09911