9 papers
OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies
Kelin Yu, Haode Zhang, Harish Ravichandar +2
Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success signific…
Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
Nanxi Li, Xiang Wang, Yuanjie Chen +3
While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become…
Robust Reward Alignment via Hypothesis Space Batch Cutting
Zhixian Xie, Haode Zhang, Yizhe Feng +1
Reward design in reinforcement learning and optimal control is challenging. Preference-based alignment addresses this by enabling agents to learn rewards from ranked trajectory pai…
Minimizing PLM-Based Few-Shot Intent Detectors
Haode Zhang, Albert Y. S. Lam, Xiao-Ming Wu
Recent research has demonstrated the feasibility of training efficient intent detectors based on pre-trained language model~(PLM) with limited labeled data. However, deploying thes…
Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
Haode Zhang, Haowen Liang, Liming Zhan +2
We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount…
Asymmetric feature interaction for interpreting model predictions
Xiaolei Lu, Jianghong Ma, Haode Zhang
In natural language processing (NLP), deep neural networks (DNNs) could model complex interactions between context and have achieved impressive results on a range of NLP tasks. Pri…
New Intent Discovery with Pre-training and Contrastive Learning
Yuwei Zhang, Haode Zhang, Li-Ming Zhan +2
New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and servi…
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization
Haode Zhang, Haowen Liang, Yuwei Zhang +4
It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language…
Effectiveness of Pre-training for Few-shot Intent Classification
Haode Zhang, Yuwei Zhang, Li-Ming Zhan +4
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a…