Zobrazeno 1 - 10
of 210
pro vyhledávání: '"Wang, Xiyao"'
Autor:
Wang, Xiyao, Song, Linfeng, Tian, Ye, Yu, Dian, Peng, Baolin, Mi, Haitao, Huang, Furong, Yu, Dong
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to distill high-quality behaviors from MCTS, improving their reasoning perfo
Externí odkaz:
http://arxiv.org/abs/2410.06508
Autor:
Xiong, Tianyi, Wang, Xiyao, Guo, Dong, Ye, Qinghao, Fan, Haoqi, Gu, Quanquan, Huang, Heng, Li, Chunyuan
We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks. LLaVA-Critic is trained using a high-quality critic instruction-following
Externí odkaz:
http://arxiv.org/abs/2410.02712
Emotion is an important factor to consider when designing visualizations as it can impact the amount of trust viewers place in a visualization, how well they can retrieve information and understand the underlying data, and how much they engage with o
Externí odkaz:
http://arxiv.org/abs/2407.18427
Autor:
Zhou, Yuhang, Zhu, Jing, Xu, Paiheng, Liu, Xiaoyu, Wang, Xiyao, Koutra, Danai, Ai, Wei, Huang, Furong
Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of capabilities from
Externí odkaz:
http://arxiv.org/abs/2406.13114
Autor:
Liu, Zeyuan, Huan, Ziyu, Wang, Xiyao, Lyu, Jiafei, Tao, Jian, Li, Xiu, Huang, Furong, Xu, Huazhe
Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful guidance in
Externí odkaz:
http://arxiv.org/abs/2406.07381
Autor:
Wang, Xiyao, Chen, Jiuhai, Wang, Zhaoyang, Zhou, Yuhang, Zhou, Yiyang, Yao, Huaxiu, Zhou, Tianyi, Goldstein, Tom, Bhatia, Parminder, Huang, Furong, Xiao, Cao
Large vision-language models (LVLMs) have achieved impressive results in various visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there is still significant room for improvement in the ali
Externí odkaz:
http://arxiv.org/abs/2405.15973
Autor:
Zhou, Yiyang, Fan, Zhiyuan, Cheng, Dongjie, Yang, Sihan, Chen, Zhaorun, Cui, Chenhang, Wang, Xiyao, Li, Yun, Zhang, Linjun, Yao, Huaxiu
Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination phenomenon, wh
Externí odkaz:
http://arxiv.org/abs/2405.14622
Autor:
Zheng, Ruijie, Liang, Yongyuan, Wang, Xiyao, Ma, Shuang, Daumé III, Hal, Xu, Huazhe, Langford, John, Palanisamy, Praveen, Basu, Kalyan Shankar, Huang, Furong
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a
Externí odkaz:
http://arxiv.org/abs/2402.06187
Emojis, which encapsulate semantics beyond mere words or phrases, have become prevalent in social network communications. This has spurred increasing scholarly interest in exploring their attributes and functionalities. However, emoji-related researc
Externí odkaz:
http://arxiv.org/abs/2402.01681
Autor:
Wang, Xiyao, Zhou, Yuhang, Liu, Xiaoyu, Lu, Hongjin, Xu, Yuancheng, He, Feihong, Yoon, Jaehong, Lu, Taixi, Bertasius, Gedas, Bansal, Mohit, Yao, Huaxiu, Huang, Furong
Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image,
Externí odkaz:
http://arxiv.org/abs/2401.10529