Zobrazeno 1 - 10
of 270
pro vyhledávání: '"Jiang Ziyan"'
Autor:
Chen, Jiacheng, Liang, Tianhao, Siu, Sherman, Wang, Zhengqing, Wang, Kai, Wang, Yubo, Ni, Yuansheng, Zhu, Wang, Jiang, Ziyan, Lyu, Bohan, Jiang, Dongfu, He, Xuan, Liu, Yuan, Hu, Hexiang, Yue, Xiang, Chen, Wenhu
We present MEGA-Bench, an evaluation suite that scales multimodal evaluation to over 500 real-world tasks, to address the highly heterogeneous daily use cases of end users. Our objective is to optimize for a set of high-quality data samples that cove
Externí odkaz:
http://arxiv.org/abs/2410.10563
Embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering. Recently, there has been a surge of interest in developing universal text embedding models that can generalize
Externí odkaz:
http://arxiv.org/abs/2410.05160
Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on extensive hu
Externí odkaz:
http://arxiv.org/abs/2409.06903
In traditional RAG framework, the basic retrieval units are normally short. The common retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design forces the retriever to search over a large corpus to find the `needle' unit. I
Externí odkaz:
http://arxiv.org/abs/2406.15319
Autor:
He, Xuan, Jiang, Dongfu, Zhang, Ge, Ku, Max, Soni, Achint, Siu, Sherman, Chen, Haonan, Chandra, Abhranil, Jiang, Ziyan, Arulraj, Aaran, Wang, Kai, Do, Quy Duc, Ni, Yuansheng, Lyu, Bohan, Narsupalli, Yaswanth, Fan, Rongqi, Lyu, Zhiheng, Lin, Yuchen, Chen, Wenhu
The recent years have witnessed great advances in video generation. However, the development of automatic video metrics is lagging significantly behind. None of the existing metric is able to provide reliable scores over generated videos. The main ba
Externí odkaz:
http://arxiv.org/abs/2406.15252
Autor:
Wang, Yubo, Ma, Xueguang, Zhang, Ge, Ni, Yuansheng, Chandra, Abhranil, Guo, Shiguang, Ren, Weiming, Arulraj, Aaran, He, Xuan, Jiang, Ziyan, Li, Tianle, Ku, Max, Wang, Kai, Zhuang, Alex, Fan, Rongqi, Yue, Xiang, Chen, Wenhu
In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in language comprehension and reasoning across diverse domains. However,
Externí odkaz:
http://arxiv.org/abs/2406.01574
Autor:
Zhang, Zheng, Yang, Fan, Jiang, Ziyan, Chen, Zheng, Zhao, Zhengyang, Ma, Chengyuan, Zhao, Liang, Liu, Yang
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inpu
Externí odkaz:
http://arxiv.org/abs/2404.01430
Autor:
Wang, Yancheng, Jiang, Ziyan, Chen, Zheng, Yang, Fan, Zhou, Yingxue, Cho, Eunah, Fan, Xing, Huang, Xiaojiang, Lu, Yanbin, Yang, Yingzhen
While the recommendation system (RS) has advanced significantly through deep learning, current RS approaches usually train and fine-tune models on task-specific datasets, limiting their generalizability to new recommendation tasks and their ability t
Externí odkaz:
http://arxiv.org/abs/2308.14296
Autor:
Markowitz, Elan, Jiang, Ziyan, Yang, Fan, Fan, Xing, Chen, Tony, Steeg, Greg Ver, Galstyan, Aram
Recommender systems have found significant commercial success but still struggle with integrating new users. Since users often interact with content in different domains, it is possible to leverage a user's interactions in previous domains to improve
Externí odkaz:
http://arxiv.org/abs/2306.06302
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
Autor:
Chen, Zheng, Jiang, Ziyan, Yang, Fan, Cho, Eunah, Fan, Xing, Huang, Xiaojiang, Lu, Yanbin, Galstyan, Aram
Conversational AI systems such as Alexa need to understand defective queries to ensure robust conversational understanding and reduce user friction. These defective queries often arise from user ambiguities, mistakes, or errors in automatic speech re
Externí odkaz:
http://arxiv.org/abs/2305.14449