Ruilin Tong

Ruilin Tong, Dong Gong

Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation. When problems arrive sequentially, accumulating reusable experience across them can further improve performance. Existing memory-based methods either store whole-solution templates that generalize poorly to novel problems or use heuristic step-level selection that is not optimized for final-answer correctness. Learning selection policies requires large-scale training data and fixed action spaces, making such approaches unsuitable for test-time settings where memory expands incrementally and only limited supervision is available. We propose MILES (Modular Instruction Memory with LEarnable Selection for self-improving LLM reasoning), a framework that dynamically expands step-wise memory and applies correctness-optimized memory composition under realistic test-time constraints. MILES maintains modular memory units consisting of asymmetric pairs of sub-goal embeddings and sub-instructions, each associated with a learnable selection head. This memory structure enables a coarse-to-fine retrieval mechanism: The coarse level enables memory expansion and collects supervision for training selection heads from confident samples, while the fine stage applies learned selection heads to rerank coarse-level candidates and guide reasoning for uncertain samples. MILES consistently matches or outperforms prior methods while achieving superior accuracy-efficiency tradeoffs. Extensive experiments demonstrate its effectiveness, robustness, and transferability.

Ruilin Tong

We propose a general method for growing neural network with shared parameter by matching trained network to new input. By leveraging Hoeffding's inequality, we provide a theoretical base for improving performance by adding subnetwork to existing network. With the theoretical base of adding new subnetwork, we implement a matching method to apply trained subnetwork of existing network to new input. Our method has shown the ability to improve performance with higher parameter efficiency. It can also be applied to trans-task case and realize transfer learning by changing the combination of subnetworks without training on new task.

Renyu Wang, Ruilin Tong, Yu Ting Yeung et al.

This paper describes system setup of our submission to speaker diarisation track (Track 4) of VoxCeleb Speaker Recognition Challenge 2020. Our diarisation system consists of a well-trained neural network based speech enhancement model as pre-processing front-end of input speech signals. We replace conventional energy-based voice activity detection (VAD) with a neural network based VAD. The neural network based VAD provides more accurate annotation of speech segments containing only background music, noise, and other interference, which is crucial to diarisation performance. We apply agglomerative hierarchical clustering (AHC) of x-vectors and variational Bayesian hidden Markov model (VB-HMM) based iterative clustering for speaker clustering. Experimental results demonstrate that our proposed system achieves substantial improvements over the baseline system, yielding diarisation error rate (DER) of 10.45%, and Jacard error rate (JER) of 22.46% on the evaluation set.