Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Sohn, Sungryull"'
Autor:
Liu, Anthony Z., Wang, Xinhe, Sansom, Jacob, Fu, Yao, Choi, Jongwook, Sohn, Sungryull, Kim, Jaekyeom, Lee, Honglak
Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making, but often struggle with complex, long-horizon planning tasks. Recent techniques have sought to structure LLM outputs using control fl
Externí odkaz:
http://arxiv.org/abs/2411.13826
In this paper, we introduce Auto-Intent, a method to adapt a pre-trained large language model (LLM) as an agent for a target domain without direct fine-tuning, where we empirically focus on web navigation tasks. Our approach first discovers the under
Externí odkaz:
http://arxiv.org/abs/2410.22552
Autor:
Fu, Yao, Kim, Dong-Ki, Kim, Jaekyeom, Sohn, Sungryull, Logeswaran, Lajanugen, Bae, Kyunghoon, Lee, Honglak
The primary limitation of large language models (LLMs) is their restricted understanding of the world. This poses significant difficulties for LLM-based agents, particularly in domains where pre-trained LLMs lack sufficient knowledge. In this paper,
Externí odkaz:
http://arxiv.org/abs/2403.08978
Autor:
Sohn, Sungryull, Lyu, Yiwei, Liu, Anthony, Logeswaran, Lajanugen, Kim, Dong-Ki, Shim, Dongsub, Lee, Honglak
Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained language models (PLMs), they exhibit limitations regarding transparency and
Externí odkaz:
http://arxiv.org/abs/2312.04668
Autor:
Logeswaran, Lajanugen, Sohn, Sungryull, Lyu, Yiwei, Liu, Anthony Zhe, Kim, Dong-Ki, Shim, Dongsub, Lee, Moontae, Lee, Honglak
One of the fundamental skills required for an agent acting in an environment to complete tasks is the ability to understand what actions are plausible at any given point. This work explores a novel use of code representations to reason about action p
Externí odkaz:
http://arxiv.org/abs/2311.09601
Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating interpretable prompts and being compatible with black-box foundation
Externí odkaz:
http://arxiv.org/abs/2310.16730
Autor:
Zhang, Zheyuan, Storks, Shane, Hu, Fengyuan, Sohn, Sungryull, Lee, Moontae, Lee, Honglak, Chai, Joyce
Pre-trained language models (PLMs) have shown impressive performance in various language tasks. However, they are prone to spurious correlations, and often generate illusory information. In real-world applications, PLMs should justify decisions with
Externí odkaz:
http://arxiv.org/abs/2310.18364
Planning is an important capability of artificial agents that perform long-horizon tasks in real-world environments. In this work, we explore the use of pre-trained language models (PLMs) to reason about plan sequences from text instructions in embod
Externí odkaz:
http://arxiv.org/abs/2303.09031
This work explores the problem of generating task graphs of real-world activities. Different from prior formulations, we consider a setting where text transcripts of instructional videos performing a real-world activity (e.g., making coffee) are prov
Externí odkaz:
http://arxiv.org/abs/2302.09173
Autor:
Jang, Yunseok, Sohn, Sungryull, Logeswaran, Lajanugen, Luo, Tiange, Lee, Moontae, Lee, Honglak
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a dirty pan needs to be washed before it can be used for cooking). In this work, we aim to model the causal dependencies between such subtasks from instructional videos describing t
Externí odkaz:
http://arxiv.org/abs/2302.08672