198 citations · 214 across the 10 of their papers we have counts for
10 papers
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories
Shizhe Diao, Tianyang Xu, Ruijia Xu +2
Pre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain. Although continued pre-training…
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
Rui Yang, Yong Lin, Xiaoteng Ma +3
Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalizatio…
ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification
Chunyu Lei, C. L. Philip Chen, Jifeng Guo +1
Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been pr…
Hashtag-Guided Low-Resource Tweet Classification
Shizhe Diao, Sedrick Scott Keh, Liangming Pan +3
Social media classification tasks (e.g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous.…
Learning in POMDPs is Sample-Efficient with Hindsight Observability
Jonathan N. Lee, Alekh Agarwal, Christoph Dann +1
POMDPs capture a broad class of decision making problems, but hardness results suggest that learning is intractable even in simple settings due to the inherent partial observabilit…
History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
Tong Zhang, Yong Liu, Boyang Li +5
With the evolution of pre-trained language models, current open-domain dialogue systems have achieved great progress in conducting one-session conversations. In contrast, Multi-Ses…