Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Yang, Yujiu"'
With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications, one major
Externí odkaz:
http://arxiv.org/abs/2405.16027
Autor:
Shi, Chufan, Yang, Cheng, Zhu, Xinyu, Wang, Jiahao, Wu, Taiqiang, Li, Siheng, Cai, Deng, Yang, Yujiu, Meng, Yu
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism. Ho
Externí odkaz:
http://arxiv.org/abs/2405.14507
Knowledge Graph Completion (KGC) has emerged as a promising solution to address the issue of incompleteness within Knowledge Graphs (KGs). Traditional KGC research primarily centers on triple classification and link prediction. Nevertheless, we conte
Externí odkaz:
http://arxiv.org/abs/2404.09897
Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making process. Mult
Externí odkaz:
http://arxiv.org/abs/2404.08978
The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to the complex
Externí odkaz:
http://arxiv.org/abs/2404.08964
While large language models (LLMs) have achieved impressive performance across diverse tasks, recent studies showcase that causal LLMs suffer from the "reversal curse". It is a typical example that the model knows "A's father is B", but is unable to
Externí odkaz:
http://arxiv.org/abs/2403.00758
The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark designed to asse
Externí odkaz:
http://arxiv.org/abs/2402.14809
Autor:
Zhang, Xinchen, Yang, Ling, Cai, Yaqi, Yu, Zhaochen, Wang, Kai-Ni, Xie, Jiake, Tian, Ye, Xu, Minkai, Tang, Yong, Yang, Yujiu, Cui, Bin
Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new training-fr
Externí odkaz:
http://arxiv.org/abs/2402.12908
Autor:
Ma, Chang, Zhang, Junlei, Zhu, Zhihao, Yang, Cheng, Yang, Yujiu, Jin, Yaohui, Lan, Zhenzhong, Kong, Lingpeng, He, Junxian
Evaluating large language models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A pri
Externí odkaz:
http://arxiv.org/abs/2401.13178
The recommendation has been playing a key role in many industries, e.g., e-commerce, streaming media, social media, etc. Recently, a new recommendation scenario, called Trigger-Induced Recommendation (TIR), where users are able to explicitly express
Externí odkaz:
http://arxiv.org/abs/2401.07769