Profiles2020-2023
Tong Zhang
The Hong Kong University of Science and Technology
21Papers
14Last author
32Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers21
- Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled DataAuthor 3 of 3EMNLP Findings 2023 · 63 citations
- Corruption-Robust Offline Reinforcement Learning with General Function ApproximationAuthor 4 of 4NeurIPS 2023 · 37 citations
- Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models' MemoriesAuthor 5 of 5ACL 2023 · 17 citations
- Hashtag-Guided Low-Resource Tweet ClassificationAuthor 6 of 6WWW 2023 · 8 citations
- Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov GameAuthor 6 of 6ICLR 2023 · 2 citations
- Doolittle: Benchmarks and Corpora for Academic Writing FormalizationAuthor 8 of 8EMNLP 2023 · 1 citation
- Exploring Geometric Consistency for Monocular 3D Object DetectionAuthor 5 of 5CVPR 2022 · 34 citations
- Rare and Zero-shot Word Sense Disambiguation using Z-ReweightingAuthor 4 of 4ACL 2022 · 12 citations
- Error Compensated Distributed SGD Can Be AcceleratedAuthor 3 of 3NeurIPS 2021 · 65 citations
- DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural NetworksAuthor 4 of 4KDD 2021 · 63 citations
- TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text GenerationAuthor 5 of 6ACL Findings 2021 · 26 citations
- Few-Shot Human Motion Transfer by Personalized Geometry and Texture ModelingAuthor 4 of 4CVPR 2021
- Involution: Inverting the Inherence of Convolution for Visual RecognitionAuthor 7 of 8CVPR 2021
- Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain AdaptationAuthor 6 of 7ACL 2021
- Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax ProblemsAuthor 4 of 4NeurIPS 2020 · 152 citations
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONASAuthor 6 of 6NeurIPS 2020 · 148 citations
- ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram RepresentationsAuthor 4 of 6EMNLP Findings 2020 · 140 citations
- Improving Chinese Word Segmentation with Wordhood Memory NetworksAuthor 4 of 5ACL 2020 · 95 citations
- Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed KnowledgeAuthor 6 of 7ACL 2020 · 50 citations
- Improving Constituency Parsing with Span AttentionAuthor 4 of 5EMNLP Findings 2020 · 40 citations
- Decentralized Accelerated Proximal Gradient DescentAuthor 4 of 4NeurIPS 2020 · 37 citations
