Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Shi, Yunxiao"'
Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize information on behalf of users during dynamic dialogues. Despite their pote
Externí odkaz:
http://arxiv.org/abs/2409.00636
Modeling feature interactions is crucial for click-through rate (CTR) prediction, particularly when it comes to high-order explicit interactions. Traditional methods struggle with this task because they often predefine a maximum interaction order, wh
Externí odkaz:
http://arxiv.org/abs/2408.08713
Autor:
Letourneau, Pierre-David, Singh, Manish Kumar, Cheng, Hsin-Pai, Han, Shizhong, Shi, Yunxiao, Jones, Dalton, Langston, Matthew Harper, Cai, Hong, Porikli, Fatih
We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying framework designed to replace the conventional self-attention mechanism in transformer models. Notably, several recent alternative attention mechanisms, including Hyena
Externí odkaz:
http://arxiv.org/abs/2407.11306
Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Originating from the simple 'retrieve-then-read' approach, the RAG framewor
Externí odkaz:
http://arxiv.org/abs/2407.10670
Autor:
Xu, Wujiang, Wu, Qitian, Liang, Zujie, Han, Jiaojiao, Ning, Xuying, Shi, Yunxiao, Lin, Wenfang, Zhang, Yongfeng
Sequential Recommendation (SR) task involves predicting the next item a user is likely to interact with, given their past interactions. The SR models examine the sequence of a user's actions to discern more complex behavioral patterns and temporal dy
Externí odkaz:
http://arxiv.org/abs/2405.17890
Retrieval-augmented generation (RAG) for language models significantly improves language understanding systems. The basic retrieval-then-read pipeline of response generation has evolved into a more extended process due to the integration of various c
Externí odkaz:
http://arxiv.org/abs/2405.06683
Autor:
YU, Zeng, Shi, Yunxiao
Visible-infrared person re-identification (VI-reID) aims at matching cross-modality pedestrian images captured by disjoint visible or infrared cameras. Existing methods alleviate the cross-modality discrepancies via designing different kinds of netwo
Externí odkaz:
http://arxiv.org/abs/2404.07930
Autor:
Yasarla, Rajeev, Singh, Manish Kumar, Cai, Hong, Shi, Yunxiao, Jeong, Jisoo, Zhu, Yinhao, Han, Shizhong, Garrepalli, Risheek, Porikli, Fatih
In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training. More specific
Externí odkaz:
http://arxiv.org/abs/2403.12953
In this paper, we introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion without requiring iterative spatial propagations. Specifically, we first enhance a baseline convolutional depth completio
Externí odkaz:
http://arxiv.org/abs/2403.12202
Social recommendation systems face the problem of social influence bias, which can lead to an overemphasis on recommending items that friends have interacted with. Addressing this problem is crucial, and existing methods often rely on techniques such
Externí odkaz:
http://arxiv.org/abs/2403.03578