42 citations · 91 across the 20 of their papers we have counts for
20 papers
Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models
Song-Lin Lv, Rui Zhu, Tong Wei +2
Semi-supervised learning (SSL) alleviates the cost of data labeling process by exploiting unlabeled data and has achieved promising results. Meanwhile, with the development of larg…
Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
Lin-Han Jia, Wen-Chao Hu, Jie-Jing Shao +2
The current Neuro-Symbolic (NeSy) Learning paradigm suffers from an over-reliance on labeled data, so if we completely disregard labels, it leads to less symbol information, a larg…
Robust Semi-Supervised Learning in Open Environments
Lan-Zhe Guo, Lin-Han Jia, Jie-Jing Shao +1
Semi-supervised learning (SSL) aims to improve performance by exploiting unlabeled data when labels are scarce. Conventional SSL studies typically assume close environments where i…
You Only Submit One Image to Find the Most Suitable Generative Model
Zhi Zhou, Lan-Zhe Guo, Peng-Xiao Song +1
Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model…
Fully Test-time Adaptation for Tabular Data
Zhi Zhou, Kun-Yang Yu, Lan-Zhe Guo +1
Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still stru…
ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
Jie-Jing Shao, Bo-Wen Zhang, Xiao-Wen Yang +8
Travel planning stands out among real-world applications of \emph{Language Agents} because it couples significant practical demand with a rigorous constraint-satisfaction challenge…
Enabling Small Models for Zero-Shot Selection and Reuse through Model Label Learning
Jia Zhang, Zhi Zhou, Lan-Zhe Guo +1
Vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot ability in image classification tasks by aligning text and images but suffer inferior performance com…
Offline Imitation Learning with Model-based Reverse Augmentation
Jie-Jing Shao, Hao-Sen Shi, Lan-Zhe Guo +1
In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent,…
LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model
Zhi Zhou, Jiang-Xin Shi, Peng-Xiao Song +4
Large language models (LLMs), including both proprietary and open-source models, have showcased remarkable capabilities in addressing a wide range of downstream tasks. Nonetheless,…
VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu +4
Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, including mathematical reasoning. However, the current evaluation mostly focuses on carefu…
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
Zhi Zhou, Ming Yang, Jiang-Xin Shi +2
Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few…
Learning Contrastive Feature Representations for Facial Action Unit Detection
Ziqiao Shang, Bin Liu, Fengmao Lv +3
For the Facial Action Unit (AU) detection task, accurately capturing the subtle facial differences between distinct AUs is essential for reliable detection. Additionally, AU detect…
Interactive Reweighting for Mitigating Label Quality Issues
Weikai Yang, Yukai Guo, Jing Wu +4
Label quality issues, such as noisy labels and imbalanced class distributions, have negative effects on model performance. Automatic reweighting methods identify problematic sample…
Investigating the Limitation of CLIP Models: The Worst-Performing Categories
Jie-Jing Shao, Jiang-Xin Shi, Xiao-Wen Yang +2
Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks.…
USB: A Unified Semi-supervised Learning Benchmark for Classification
Yidong Wang, Hao Chen, Yue Fan +19
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation pro…
LAMDA-SSL: Semi-Supervised Learning in Python
Lin-Han Jia, Lan-Zhe Guo, Zhi Zhou +1
LAMDA-SSL is open-sourced on GitHub and its detailed usage documentation is available at https://ygzwqzd.github.io/LAMDA-SSL/. This documentation introduces LAMDA-SSL in detail fro…
Transfer and Share: Semi-Supervised Learning from Long-Tailed Data
Tong Wei, Qian-Yu Liu, Jiang-Xin Shi +2
Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost…
Robust Deep Semi-Supervised Learning: A Brief Introduction
Lan-Zhe Guo, Zhi Zhou, Yu-Feng Li
Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning performance by leveraging unlabeled data when labels are insufficient. Recently, SSL…
Weakly Supervised Learning Meets Ride-Sharing User Experience Enhancement
Lan-Zhe Guo, Feng Kuang, Zhang-Xun Liu +3
Weakly supervised learning aims at coping with scarce labeled data. Previous weakly supervised studies typically assume that there is only one kind of weak supervision in data. In…
Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness
Lan-Zhe Guo, Yu-Feng Li, Ming Li +3
Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data w…