435 citations · 503 across the 62 of their papers we have counts for
34 papers · 1 filter
Outcome-Guided On-Policy Self-Distillation
ZheXu Wang, Mao-Lin Luo, Yankun Hong +6
On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiable Rewards (RLVR). However,…
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to for…
DC-Merge: Improving Model Merging with Directional Consistency
Han-Chen Zhang, Zi-Hao Zhou, Mao-Lin Luo +3
Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowled…
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Hao Gu, Mao-Lin Luo, Zi-Hao Zhou +3
Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continu…
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
Wei Tang, Yin-Fang Yang, Weijia Zhang +1
Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to addre…
Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
Xiaofeng Cao, Mingwei Xu, Xin Yu +8
Learning with high-resource data has demonstrated substantial success in artificial intelligence (AI); however, the costs associated with data annotation and model training remain…
Tuning the Right Foundation Models is What you Need for Partial Label Learning
Kuang He, Wei Tang, Tong Wei +1
Partial label learning (PLL) seeks to train generalizable classifiers from datasets with inexact supervision, a common challenge in real-world applications. Existing studies have d…
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
Zi-Hao Zhou, Jun-Jie Wang, Tong Wei +1
Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. How…
Realistic Evaluation of Deep Partial-Label Learning Algorithms
Wei Wang, Dong-Dong Wu, Jindong Wang +3
Partial-label learning (PLL) is a weakly supervised learning problem in which each example is associated with multiple candidate labels and only one is the true label. In recent ye…
Multi-Instance Partial-Label Learning with Margin Adjustment
Wei Tang, Yin-Fang Yang, Zhaofei Wang +2
Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label s…
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Zi-Hao Zhou, Siyuan Fang, Zi-Jing Zhou +3
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-ar…
Vision-Language Models are Strong Noisy Label Detectors
Tong Wei, Hao-Tian Li, Chun-Shu Li +3
Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled da…
Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learning
Wei Tang, Weijia Zhang, Min-Ling Zhang
Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing…
Towards Few-Shot Learning in the Open World: A Review and Beyond
Hui Xue, Yuexuan An, Yongchun Qin +5
Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, under…
Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning
Kai Gan, Tong Wei, Min-Ling Zhang
While long-tailed semi-supervised learning (LTSSL) has attracted growing attention in many real-world classification tasks, existing LTSSL algorithms typically assume that labeled…
EAT: Towards Long-Tailed Out-of-Distribution Detection
Tong Wei, Bo-Lin Wang, Min-Ling Zhang
Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-…
Binary Classification with Confidence Difference
Wei Wang, Lei Feng, Yuchen Jiang +3
Recently, learning with soft labels has been shown to achieve better performance than learning with hard labels in terms of model generalization, calibration, and robustness. Howev…
Robust Representation Learning for Unreliable Partial Label Learning
Yu Shi, Dong-Dong Wu, Xin Geng +1
Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. How…
Partial-Label Regression
Xin Cheng, Deng-Bao Wang, Lei Feng +2
Partial-label learning is a popular weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels. Previous studies on partial…
Complementary Classifier Induced Partial Label Learning
Yuheng Jia, Chongjie Si, Min-ling Zhang
In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate…
Rethinking the Value of Labels for Instance-Dependent Label Noise Learning
Hanwen Deng, Weijia Zhang, Min-Ling Zhang
Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-depende…
Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning
Wei Tang, Weijia Zhang, Min-Ling Zhang
In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and sever…
Complementary to Multiple Labels: A Correlation-Aware Correction Approach
Yi Gao, Miao Xu, Min-Ling Zhang
\textit{Complementary label learning} (CLL) requires annotators to give \emph{irrelevant} labels instead of relevant labels for instances. Currently, CLL has shown its promising pe…
Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision
Wei Tang, Weijia Zhang, Min-Ling Zhang
Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-wor…