Zobrazeno 1 - 10
of 5 984
pro vyhledávání: '"Hwang, Sung In"'
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in training da
Externí odkaz:
http://arxiv.org/abs/2412.02186
As Large Language Models (LLMs) are increasingly deployed in specialized domains with continuously evolving knowledge, the need for timely and precise knowledge injection has become essential. Fine-tuning with paraphrased data is a common approach to
Externí odkaz:
http://arxiv.org/abs/2411.00686
Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should rethink that the
Externí odkaz:
http://arxiv.org/abs/2410.22375
Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up complex tools,
Externí odkaz:
http://arxiv.org/abs/2410.02958
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents, overlooking
Externí odkaz:
http://arxiv.org/abs/2410.02729
Autor:
Lee, Seanie, Seong, Haebin, Lee, Dong Bok, Kang, Minki, Chen, Xiaoyin, Wagner, Dominik, Bengio, Yoshua, Lee, Juho, Hwang, Sung Ju
Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models with billions
Externí odkaz:
http://arxiv.org/abs/2410.01524
Large Language Models (LLMs) excel in various language tasks but they often generate incorrect information, a phenomenon known as "hallucinations". Retrieval-Augmented Generation (RAG) aims to mitigate this by using document retrieval for accurate re
Externí odkaz:
http://arxiv.org/abs/2407.12325
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024
Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have been explored
Externí odkaz:
http://arxiv.org/abs/2407.00256
Information retrieval models that aim to search for the documents relevant to the given query have shown many successes, which have been applied to diverse tasks. However, the query provided by the user is oftentimes very short, which challenges the
Externí odkaz:
http://arxiv.org/abs/2406.16013
The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow quadratically, hinderin
Externí odkaz:
http://arxiv.org/abs/2406.17808