7 citations · 15 across the 20 of their papers we have counts for
22 papers
The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs
Zhiliang Chen, Alfred Wei Lun Leong, Shao Yong Ong +6
Co-optimizing data and model configurations for training LLMs presents a classic chicken-and-egg dilemma: The best training data configuration (e.g., data mixture) for a downstream…
The Reward Model Selection Crisis in Personalized Alignment
Fady Rezk, Yuangang Pan, Chuan-Sheng Foo +4
Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking tran…
Incentivizing Time-Aware Fairness in Data Sharing
Jiangwei Chen, Kieu Thao Nguyen Pham, Rachael Hwee Ling Sim +4
In collaborative data sharing and machine learning, multiple parties aggregate their data resources to train a machine learning model with better model performance. However, as the…
Box-Level Class-Balanced Sampling for Active Object Detection
Jingyi Liao, Xun Xu, Chuan-Sheng Foo +1
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-lev…
WaterDrum: Watermarking for Data-centric Unlearning Metric
Xinyang Lu, Xinyuan Niu, Gregory Kang Ruey Lau +7
Large language model (LLM) unlearning is critical in real-world applications where it is necessary to efficiently remove the influence of private, copyrighted, or harmful data from…
CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
Cheng Chen, Jiacheng Wei, Tianrun Chen +8
Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-in…
Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space
Zhiliang Chen, Xinyuan Niu, Chuan-Sheng Foo +1
Large language models (LLMs) are used in chatbots or AI assistants to hold conversations with a human user. In such applications, the quality (e.g., user engagement, safety) of a c…
Confidence Elicitation: A New Attack Vector for Large Language Models
Brian Formento, Chuan Sheng Foo, See-Kiong Ng
A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billion…
DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks
Zhiliang Chen, Gregory Kang Ruey Lau, Chuan-Sheng Foo +1
The performance of an LLM depends heavily on the relevance of its training data to the downstream evaluation task. However, in practice, the data involved in an unseen evaluation t…
Data Distribution Valuation
Xinyi Xu, Shuaiqi Wang, Chuan-Sheng Foo +2
Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a…
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
Yongyi Su, Yushu Li, Nanqing Liu +4
Test-time adaptation (TTA) updates the model weights during the inference stage using testing data to enhance generalization. However, this practice exposes TTA to adversarial risk…
Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs
Gregory Kang Ruey Lau, Xinyuan Niu, Hieu Dao +3
Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by larg…
Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation
Mohamed Ragab, Peiliang Gong, Emadeldeen Eldele +6
Source-free domain adaptation (SFDA) aims to adapt a model pre-trained on a labeled source domain to an unlabeled target domain without access to source data, preserving the source…
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
Jingtan Wang, Xiaoqiang Lin, Rui Qiao +2
The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting model…
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
Wenyu Zhang, Li Shen, Chuan-Sheng Foo
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. While the source model is a key…
REACTO: Reconstructing Articulated Objects from a Single Video
Chaoyue Song, Jiacheng Wei, Chuan-Sheng Foo +2
In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video. Existing works employing dynamic neural radiance fields have advanced…
SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Brian Formento, Wenjie Feng, Chuan Sheng Foo +2
Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has ex…
Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong +2
Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this wor…
Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
Cheng Chen, Xiaofeng Yang, Fan Yang +5
Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the bac…
COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection
Jingyi Liao, Xun Xu, Manh Cuong Nguyen +2
Existing approaches towards anomaly detection~(AD) often rely on a substantial amount of anomaly-free data to train representation and density models. However, large anomaly-free d…
Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction
Kennard Yanting Chan, Fayao Liu, Guosheng Lin +2
Pixel-aligned implicit models, such as PIFu, PIFuHD, and ICON, are used for single-view clothed human reconstruction. These models need to be trained using a sampling training sche…
Source Attribution for Large Language Model-Generated Data
Jingtan Wang, Xinyang Lu, Zitong Zhao +4
The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP…