19 citations · 21 across the 20 of their papers we have counts for
23 papers
Rethinking Learning from Label Proportions via Moment Matching
Tianhao Ma, Wei Wang, Yivan Zhang +4
Learning from label proportions (LLP) is a weakly supervised setting where training data are grouped into bags with only bag-level label proportions observed, and the goal is to le…
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
Bing Wang, Changchun Li, Xin-Qiang Cai +4
Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgetting, particu…
ARM: Attention with Routed-Memory for Learnable Sparse Control
Qiuhao Zeng, Jerry Huang, Peng Lu +7
Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computa…
DenMark: Robust Semantic Watermarking for Diffusion Language Models
Tianhao Ma, Weihao Xuan, Dong-Dong Wu +5
Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic wat…
Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions
Wei Wang, Gang Niu, Masashi Sugiyama
Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often not met in rea…
CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
Ruijiang Dong, Zesheng Ye, Jianzhong Qi +4
Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by ins…
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
Tongtong Fang, Nan Lu, Gang Niu +2
Importance weighting (IW) is a golden solver for joint distribution shift, where the joint distributions differ between the training and test data. To solve this problem, IW estima…
Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
Tan-Ha Mai, Chao-Kai Chiang, Han-Hwa Shih +3
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain…
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
Bing Wang, Ximing Li, Changchun Li +3
Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key…
Are Multimodal Large Language Models Good Annotators for Image Tagging?
Ming-Kun Xie, Jia-Hao Xiao, Zhiqiang Kou +3
Image tagging, a fundamental vision task, traditionally relies on human-annotated datasets to train multi-label classifiers, which incurs significant labor and costs. While Multimo…
Understanding Negative Learning in Large Language Model Fine-tuning
Yue Wang, Qizhou Wang, Zizhuo Zhang +3
Negative learning has never been more important than it is today, particularly in large language model (LLM) fine-tuning, where it underpins machine unlearning, preference- and rew…
From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
Zhikang Chen, Sen Cui, Deheng Ye +5
Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstr…
Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective
Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai +8
Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised seriou…
Rethinking Consistent Multi-Label Classification Under Inexact Supervision
Wei Wang, Tianhao Ma, Ming-Kun Xie +2
Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation…
Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
Wei Wang, Dong-Dong Wu, Ming Li +3
Positive-unlabeled (PU) learning is a weakly supervised binary classification problem, in which the goal is to learn a binary classifier from only positive and unlabeled data, with…
What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?
Ming-Kun Xie, Jia-Hao Xiao, Gang Niu +4
Large Vision-Language Models (LVLMs), empowered by the success of Large Language Models (LLMs), have achieved impressive performance across domains. Despite the great advances in L…
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…
In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement
Zhen-Yu Zhang, Jiandong Zhang, Huaxiu Yao +2
Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely…
Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning
Jia-Hao Xiao, Ming-Kun Xie, Heng-Bo Fan +3
Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlik…
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
Ming-Kun Xie, Jia-Hao Xiao, Pei Peng +3
The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurre…
Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
Zhen-Yu Zhang, Siwei Han, Huaxiu Yao +2
To improve the ability of the large language model (LLMs) to tackle complex reasoning problems, chain-of-thoughts (CoT) methods were proposed to guide LLMs to reason step-by-step,…
Direct Distillation between Different Domains
Jialiang Tang, Shuo Chen, Gang Niu +4
Knowledge Distillation (KD) aims to learn a compact student network using knowledge from a large pre-trained teacher network, where both networks are trained on data from the same…
Multi-Label Knowledge Distillation
Penghui Yang, Ming-Kun Xie, Chen-Chen Zong +4
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, whi…