454 citations · 2.5k across the 132 of their papers we have counts for
135 papers
Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
Chubin Zhang, Zhenglin Wan, Xingrui Yu +4
An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from…
Inferring Urban Mobility Interactions from Aggregated Dynamics
Yi Wang, Jing Li, Jinliang Deng +5
Real-time urban governance depends not only on knowing where people are, but on how they move between places, directional flows that could be conventionally resolved by tracking in…
Unsupervised Adaptation of PDE Foundation Models
Ziye Song, Zhao Wei, Xin Yu +2
Pretrained partial differential equation (PDE) foundation models can generalize across different equations, but adapting them to unseen PDE systems typically requires dense solutio…
Olaf-World: Orienting Latent Actions for Video World Modeling
Yuxin Jiang, Yuchao Gu, Ivor W. Tsang +1
Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control interfaces from unlabeled video, lear…
Collaborative Group-Aware Hashing for Fast Recommender Systems
Yan Zhang, Li Deng, Lixin Duan +2
The fast online recommendation is critical for applications with large-scale databases; meanwhile, it is challenging to provide accurate recommendations in sparse scenarios. Hash t…
Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
Ponhvoan Srey, Yaxin Shi, Hangwei Qian +2
Fully Test-Time Adaptation (FTTA) addresses domain shifts without access to source data and training protocols of the pre-trained models. Traditional strategies that align source a…
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…
Evolutionary Computation as Natural Generative AI
Yaxin Shi, Abhishek Gupta, Ying Wu +7
Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning…
RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model Merging
Xin He, Junxi Shen, Zhenheng Tang +4
Model merging via Mixture-of-Experts (MoE) has emerged as a scalable solution for consolidating multiple task-specific models into a unified sparse architecture, where each expert…
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning
Fei Zhang, Tianfei Zhou, Jiangchao Yao +3
Prompt tuning (PT), as an emerging resource-efficient fine-tuning paradigm, has showcased remarkable effectiveness in improving the task-specific transferability of vision-language…
Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
Heyang Zhao, Xingrui Yu, David M. Bossens +2
Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to lea…
Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking
Jun Chen, Lina Liu, Tianyi Zhu +4
This paper considers the problem of decentralized optimization on compact submanifolds, where a finite sum of smooth (possibly non-convex) local functions is minimized by agent…
Multi-Modal Dataset Distillation in the Wild
Zhuohang Dang, Minnan Luo, Chengyou Jia +3
Recent multi-modal models have shown remarkable versatility in real-world applications. However, their rapid development encounters two critical data challenges. First, the trainin…
Training-Free Dataset Pruning for Instance Segmentation
Yalun Dai, Lingao Xiao, Ivor W. Tsang +1
Existing dataset pruning techniques primarily focus on classification tasks, limiting their applicability to more complex and practical tasks like instance segmentation. Instance s…
Coherence-guided Preference Disentanglement for Cross-domain Recommendations
Zongyi Xiang, Yan Zhang, Lixin Duan +2
Discovering user preferences across different domains is pivotal in cross-domain recommendation systems, particularly when platforms lack comprehensive user-item interactive data.…
Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation
Yueming Lyu, Kim Yong Tan, Yew Soon Ong +1
Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc. However, how to perform user-preferred tar…
Diversified Batch Selection for Training Acceleration
Feng Hong, Yueming Lyu, Jiangchao Yao +3
The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption. To save cost, a prevalent research line,…
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
Hao Di, Haishan Ye, Yueling Zhang +3
Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods.…
Multisize Dataset Condensation
Yang He, Lingao Xiao, Joey Tianyi Zhou +1
While dataset condensation effectively enhances training efficiency, its application in on-device scenarios brings unique challenges. 1) Due to the fluctuating computational resour…
Collaborative Knowledge Infusion for Low-resource Stance Detection
Ming Yan, Joey Tianyi Zhou, Ivor W. Tsang
Stance detection is the view towards a specific target by a given context (\textit{e.g.} tweets, commercial reviews). Target-related knowledge is often needed to assist stance dete…
Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer
Yanjun Zhao, Sizhe Dang, Haishan Ye +3
Fine-tuning large language models (LLMs) with classic first-order optimizers entails prohibitive GPU memory due to the backpropagation process. Recent works have turned to zeroth-o…
Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
Jinliang Deng, Feiyang Ye, Du Yin +3
Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis, characterized by extensive input sequences, as opposed to the shorter spans typical…
Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
Tuan-Anh Vu, Duc Thanh Nguyen, Qing Guo +4
Text-to-image diffusion techniques have shown exceptional capabilities in producing high-quality, dense visual predictions from open-vocabulary text. This indicates a strong correl…
Co-guiding for Multi-intent Spoken Language Understanding
Bowen Xing, Ivor W. Tsang
Recent graph-based models for multi-intent SLU have obtained promising results through modeling the guidance from the prediction of intents to the decoding of slot filling. However…