8 citations · 10 across the 7 of their papers we have counts for
7 papers
EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?
Xinyan Chen, Jiaxin Ge, Hongming Dai +6
Empathy is fundamental to human interactions, yet it remains unclear whether embodied agents can provide human-like empathetic support. Existing works have studied agents' tasks so…
Training Task Experts through Retrieval Based Distillation
Jiaxin Ge, Xueying Jia, Vijay Viswanathan +2
One of the most reliable ways to create deployable models for specialized tasks is to obtain an adequate amount of high-quality task-specific data. However, for specialized tasks,…
A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation
Chenxuan Li, Jiaming Liu, Guanqun Wang +8
Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal informa…
Learning from Mistakes: Iterative Prompt Relabeling for Text-to-Image Diffusion Model Training
Xinyan Chen, Jiaxin Ge, Tianjun Zhang +2
Diffusion models have shown impressive performance in many domains. However, the model's capability to follow natural language instructions (e.g., spatial relationships between obj…
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
Tianhua Zhang, Jiaxin Ge, Hongyin Luo +7
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLE…
Entailment as Robust Self-Learner
Jiaxin Ge, Hongyin Luo, Yoon Kim +1
Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits…
Chain of Thought Prompt Tuning in Vision Language Models
Jiaxin Ge, Hongyin Luo, Siyuan Qian +3
Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most re…