Tianhao Liu

Canzong Zhou, Can Zhou, Hongqiu Zhu et al.

Zinc electrolysis is one of the key processes in zinc smelting, and maintaining stable operation of zinc electrolysis is an important factor in ensuring production efficiency and product quality. However, poor contact between the zinc electrolysis cathode and the anode is a common problem that leads to reduced production efficiency and damage to the electrolysis cell. Therefore, online monitoring of the contact status of the plates is crucial for ensuring production quality and efficiency. To address this issue, we propose an end-to-end network, the Frequency-masked Multimodal Autoencoder (FM-AE). This method takes the cell voltage signal and infrared image information as input, and through automatic encoding, fuses the two features together and predicts the poor contact status of the plates through a cascaded detector. Experimental results show that the proposed method maintains high accuracy (86.2%) while having good robustness and generalization ability, effectively detecting poor contact status of the zinc electrolysis cell, providing strong support for production practice.

Yuxin Yang, Haoran Zhang, Mingxuan Li et al.

Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly Low-Rank Adaptation (LoRA), have become essential for adapting Large Language Models (LLMs) to downstream tasks. While the recent FlyLoRA framework successfully leverages bio-inspired sparse random projections to mitigate parameter interference, it relies on a static, magnitude-based routing mechanism that is agnostic to input context. In this paper, we propose NeuroLoRA, a novel Mixture-of-Experts (MoE) based LoRA framework inspired by biological neuromodulation -- the dynamic regulation of neuronal excitability based on context. NeuroLoRA retains the computational efficiency of frozen random projections while introducing a lightweight, learnable neuromodulation gate that contextually rescales the projection space prior to expert selection. We further propose a Contrastive Orthogonality Loss to explicitly enforce separation between expert subspaces, enhancing both task decoupling and continual learning capacity. Extensive experiments on MMLU, GSM8K, and ScienceQA demonstrate that NeuroLoRA consistently outperforms FlyLoRA and other strong baselines across single-task adaptation, multi-task model merging, and sequential continual learning scenarios, while maintaining comparable parameter efficiency.

Changmao Li, Tianhao Liu, Jinho D. Choi

This paper analyzes challenges in cloze-style reading comprehension on multiparty dialogue and suggests two new tasks for more comprehensive predictions of personal entities in daily conversations. We first demonstrate that there are substantial limitations to the evaluation methods of previous work, namely that randomized assignment of samples to training and test data substantially decreases the complexity of cloze-style reading comprehension. According to our analysis, replacing the random data split with a chronological data split reduces test accuracy on previous single-variable passage completion task from 72\% to 34\%, that leaves much more room to improve. Our proposed tasks extend the previous single-variable passage completion task by replacing more character mentions with variables. Several deep learning models are developed to validate these three tasks. A thorough error analysis is provided to understand the challenges and guide the future direction of this research.