Zobrazeno 1 - 10
of 588
pro vyhledávání: '"Hoi, Steven"'
Autor:
Tiong, Anthony Meng Huat, Zhao, Junqi, Li, Boyang, Li, Junnan, Hoi, Steven C. H., Xiong, Caiming
Vision-language (VL) models, pretrained on colossal image-text datasets, have attained broad VL competence that is difficult to evaluate. A common belief is that a small number of VL skills underlie the variety of VL tests. In this paper, we perform
Externí odkaz:
http://arxiv.org/abs/2404.02415
Autor:
Pham, Quang, Do, Giang, Nguyen, Huy, Nguyen, TrungTin, Liu, Chenghao, Sartipi, Mina, Nguyen, Binh T., Ramasamy, Savitha, Li, Xiaoli, Hoi, Steven, Ho, Nhat
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, effective training of SMoE has proven to be challenging due to the representation coll
Externí odkaz:
http://arxiv.org/abs/2402.02526
Autor:
Yu, Xingtong, Fang, Yuan, Liu, Zemin, Wu, Yuxia, Wen, Zhihao, Bo, Jianyuan, Zhang, Xinming, Hoi, Steven C. H.
Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, where performance heavily relies on the availability of ample labeled data. This cons
Externí odkaz:
http://arxiv.org/abs/2402.01440
Autor:
Do, Giang, Le, Khiem, Pham, Quang, Nguyen, TrungTin, Doan, Thanh-Nam, Nguyen, Bint T., Liu, Chenghao, Ramasamy, Savitha, Li, Xiaoli, Hoi, Steven
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the collapsing
Externí odkaz:
http://arxiv.org/abs/2312.07035
With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt ChatGPT to generate a set of
Externí odkaz:
http://arxiv.org/abs/2310.18628
Automatic program repair (APR) is crucial to reduce manual debugging efforts for developers and improve software reliability. While conventional search-based techniques typically rely on heuristic rules or a redundancy assumption to mine fix patterns
Externí odkaz:
http://arxiv.org/abs/2309.06057
Autor:
Liu, Chenghao, Yang, Wenzhuo, Mittal, Himanshu, Singh, Manpreet, Sahoo, Doyen, Hoi, Steven C. H.
We introduce PyRCA, an open-source Python machine learning library of Root Cause Analysis (RCA) for Artificial Intelligence for IT Operations (AIOps). It provides a holistic framework to uncover the complicated metric causal dependencies and automati
Externí odkaz:
http://arxiv.org/abs/2306.11417
Dynamic Time Warping (DTW) has become the pragmatic choice for measuring distance between time series. However, it suffers from unavoidable quadratic time complexity when the optimal alignment matrix needs to be computed exactly. This hinders its use
Externí odkaz:
http://arxiv.org/abs/2306.00620
Autor:
Bui, Nghi D. Q., Le, Hung, Wang, Yue, Li, Junnan, Gotmare, Akhilesh Deepak, Hoi, Steven C. H.
Code intelligence plays a key role in transforming modern software engineering. Recently, deep learning-based models, especially Transformer-based large language models (LLMs), have demonstrated remarkable potential in tackling these tasks by leverag
Externí odkaz:
http://arxiv.org/abs/2306.00029
Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we intr
Externí odkaz:
http://arxiv.org/abs/2305.14720