8 papers
IKNO: Infinite-order Kernel Neural Operators
Pengyuan Zhu, Ivor W. Tsang, Yueming Lyu
Neural operators have achieved significant success in modern scientific computing due to their flexibility and strong generalization capabilities. Existing models, however, primari…
LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions
Xin He, Junxi Shen, Yuchen Mou +4
Classical models of opinion dynamics assume human participants with bounded rationality and limited coordination. The rise of LLM-based agents introduces a qualitative shift: agent…
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
Kim Yong Tan, Yueming Lyu, Ivor Tsang +1
Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-box reward functions. However, e…
Riemannian Momentum Tracking: Distributed Optimization with Momentum on Compact Submanifolds
Jun Chen, Tianyi Zhu, Haishan Ye +5
Gradient descent with momentum has been widely applied in various signal processing and machine learning tasks, demonstrating a notable empirical advantage over standard gradient d…
Numerical Sensitivity and Robustness: Exploring the Flaws of Mathematical Reasoning in Large Language Models
Zhishen Sun, Guang Dai, Ivor Tsang +1
LLMs have made significant progress in the field of mathematical reasoning, but whether they have true the mathematical understanding ability is still controversial. To explore thi…
FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed
Sizhe Dang, Yangyang Guo, Yanjun Zhao +4
Fine-tuning large language models (LLMs) often faces GPU memory bottlenecks: the backward pass of first-order optimizers like Adam increases memory usage to more than 10 times the…