Zobrazeno 1 - 10
of 2 045
pro vyhledávání: '"Liu, JiaJun"'
Real-time detection of out-of-context LLM outputs is crucial for enterprises looking to safely adopt RAG applications. In this work, we train lightweight models to discriminate LLM-generated text that is semantically out-of-context from retrieved tex
Externí odkaz:
http://arxiv.org/abs/2411.03920
Autor:
Zhang, Wenbo, Li, Yang, Qiao, Yanyuan, Huang, Siyuan, Liu, Jiajun, Dayoub, Feras, Ma, Xiao, Liu, Lingqiao
Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty
Externí odkaz:
http://arxiv.org/abs/2410.01220
Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(can
Externí odkaz:
http://arxiv.org/abs/2409.19865
Autor:
Liu, Jiajun, Wang, Yibing, Ma, Hanghang, Wu, Xiaoping, Ma, Xiaoqi, Wei, Xiaoming, Jiao, Jianbin, Wu, Enhua, Hu, Jie
Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient ac
Externí odkaz:
http://arxiv.org/abs/2408.15542
Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities. However, mainstream Vision-and-Language Navigation (VLN) tasks typically assume instructions perfectly align wi
Externí odkaz:
http://arxiv.org/abs/2407.21452
Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL thro
Externí odkaz:
http://arxiv.org/abs/2407.13163
Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain consistent per
Externí odkaz:
http://arxiv.org/abs/2407.08959
Autor:
Liu, Jiajun, Ke, Wenjun, Wang, Peng, Wang, Jiahao, Gao, Jinhua, Shang, Ziyu, Li, Guozheng, Xu, Zijie, Ji, Ke, Li, Yining
Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning f
Externí odkaz:
http://arxiv.org/abs/2407.05705
Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe ambiguity and limi
Externí odkaz:
http://arxiv.org/abs/2406.02208
Autor:
Cai, Chang, Chen, Guocai, Chen, Jiangyu, Fang, Rundong, Gao, Fei, Guo, Xiaoran, Guo, Jiheng, He, Tingyi, Jia, Chengjie, Jin, Gaojun, Jing, Yipin, Ju, Gaojun, Lei, Yang, Li, Jiayi, Li, Kaihang, Li, Meng, Li, Minhua, Li, Shengchao, Li, Siyin, Li, Tao, Lin, Qing, Liu, Jiajun, Liu, Minghao, Lv, Sheng, Luo, Guang, Ma, Jian, Shen, Chuanping, Song, Mingzhuo, Tong, Lijun, Wang, Xiaoyu, Wang, Wei, Wang, Xiaoping, Wang, Zihu, Wei, Yuehuan, Weng, Liming, Xiao, Xiang, Xie, Lingfeng, Xu, Dacheng, Yang, Jijun, Yang, Litao, Yang, Long, Ye, Jingqiang, Yu, Jiachen, Yue, Qian, Yue, Yuyong, Zhang, Bingwei, Zhang, Shuhao, Zhao, Yifei, Zhu, Chenhui
Publikováno v:
Physical Review D 110, 072011 (2024)
Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent Scattering experiment (RELICS), a proposed reactor neutrino program u
Externí odkaz:
http://arxiv.org/abs/2405.05554