Yitao Liang

Affiliations

University of California, Los Angeles

papers

235

total citations

papers (10)

ProAgent: Building Proactive Cooperative Agents with Large Language Models

AAAI 2024arXiv

120

citations

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

CVPR 2023arXiv

citations

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

ICML 2024arXiv

citations

Neural-Symbolic Recursive Machine for Systematic Generalization

ICLR 2024arXiv

citations

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

CVPR 2025arXiv

citations

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

NEURIPS 2023

citations

Open-World Skill Discovery from Unsegmented Demonstration Videos

ICCV 2025

citations

Yitao Liang

Affiliations

papers (10)

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Neural-Symbolic Recursive Machine for Systematic Generalization

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

Tractable Transformers for Flexible Conditional Generation

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

Open-World Skill Discovery from Unsegmented Demonstration Videos

papers (10)

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Neural-Symbolic Recursive Machine for Systematic Generalization

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

Tractable Transformers for Flexible Conditional Generation

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

Open-World Skill Discovery from Unsegmented Demonstration Videos