Zobrazeno 1 - 10
of 472
pro vyhledávání: '"YANG Zhuoran"'
Publikováno v:
Zhongguo shipin weisheng zazhi, Vol 35, Iss 2, Pp 259-265 (2023)
Food supervision sampling is an important technical support of food safety supervision. It is the difficult and key point to make correct food classification and make correct judgment according to relevant standards. This paper summarizes the problem
Externí odkaz:
https://doaj.org/article/360eb674bf694443be5edf1a5c119128
In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically explains h
Externí odkaz:
http://arxiv.org/abs/2409.10559
Chain-of-Thought (CoT) prompting and its variants have gained popularity as effective methods for solving multi-step reasoning problems using pretrained large language models (LLMs). In this work, we analyze CoT prompting from a statistical estimatio
Externí odkaz:
http://arxiv.org/abs/2408.14511
Diffusion models have revolutionized various application domains, including computer vision and audio generation. Despite the state-of-the-art performance, diffusion models are known for their slow sample generation due to the extensive number of ste
Externí odkaz:
http://arxiv.org/abs/2406.16213
In this work, from a theoretical lens, we aim to understand why large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. To this end, consider a hierarchical reinforcement learning (RL) model where
Externí odkaz:
http://arxiv.org/abs/2405.19883
Autor:
Li, Chuanhao, Yang, Runhan, Li, Tiankai, Bafarassat, Milad, Sharifi, Kourosh, Bergemann, Dirk, Yang, Zhuoran
Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments is hampere
Externí odkaz:
http://arxiv.org/abs/2405.16376
Offline Reinforcement Learning (RL) has shown promising results in learning a task-specific policy from a fixed dataset. However, successful offline RL often relies heavily on the coverage and quality of the given dataset. In scenarios where the data
Externí odkaz:
http://arxiv.org/abs/2404.19346
We study infinite-horizon average-reward Markov decision processes (AMDPs) in the context of general function approximation. Specifically, we propose a novel algorithmic framework named Local-fitted Optimization with OPtimism (LOOP), which incorporat
Externí odkaz:
http://arxiv.org/abs/2404.12648
This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear functional
Externí odkaz:
http://arxiv.org/abs/2404.12312
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In these applications, conditional diffusion models incorporate various con
Externí odkaz:
http://arxiv.org/abs/2403.11968