Tianhao Liu

Yuxin Jia, Youfang Lin, Jing Yu et al.

Due to the recurrent structure of RNN, the long information propagation path poses limitations in capturing long-term dependencies, gradient explosion/vanishing issues, and inefficient sequential execution. Based on this, we propose a novel paradigm called Parallel Gated Network (PGN) as the new successor to RNN. PGN directly captures information from previous time steps through the designed Historical Information Extraction (HIE) layer and leverages gated mechanisms to select and fuse it with the current time step information. This reduces the information propagation path to $\mathcal{O}(1)$, effectively addressing the limitations of RNN. To enhance PGN's performance in long-range time series forecasting tasks, we propose a novel temporal modeling framework called Temporal PGN (TPGN). TPGN incorporates two branches to comprehensively capture the semantic information of time series. One branch utilizes PGN to capture long-term periodic patterns while preserving their local characteristics. The other branch employs patches to capture short-term information and aggregate the global representation of the series. TPGN achieves a theoretical complexity of $\mathcal{O}(\sqrt{L})$, ensuring efficiency in its operations. Experimental results on five benchmark datasets demonstrate the state-of-the-art (SOTA) performance and high efficiency of TPGN, further confirming the effectiveness of PGN as the new successor to RNN in long-range time series forecasting. The code is available in this repository: \url{https://github.com/Water2sea/TPGN}.

Shenghe Zheng, Minyu Zhang, Tianhao Liu et al.

With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most existing model merging methods are designed for classification or text generation, and when applied to image generation, they suffer from content drift due to error accumulation across multiple diffusion steps. For image-oriented methods, training-based approaches are computationally expensive and unsuitable for edge deployment, while training-free ones use uniform fusion strategies that ignore inter-adapter differences, leading to detail degradation. We find that since different adapters are specialized for generating different types of content, the contribution of each diffusion step carries different significance for each adapter. Accordingly, we propose a frequency-domain importance-driven dynamic LoRA switch method. Furthermore, we observe that maintaining semantic consistency across adapters effectively mitigates detail loss; thus, we design an automatic Generation Alignment mechanism to align generation intents at the semantic level. Experiments demonstrate that our FREE-Switch (Frequency-based Efficient and Dynamic LoRA Switch) framework efficiently combines adapters for different objects and styles, substantially reducing the training cost of high-quality customized generation.

Tianhao Liu, Daniel Andrés Díaz-Pachón, J. Sunil Rao

Supervised No Free Lunch Theorems (NFLTs) are well studied, yet unsupervised NFLTs remain underexplored. For elliptical distributions, we prove that there exist two equally optimal, scientifically meaningful bump-hunting strategies that are exact opposites, with no universal winner. Specifically, peeling $k$ orthogonal dimensions from $\mathbb{R}^d$ ($d \ge k$), retaining an inter-quantile region of probability $1-α$ per peeled dimension, maximizes total variance and Frobenius norm when the $k$ smallest principal components (called pettiest components) are selected, and minimizes them when the selected dimensions are the $k$ leading principal components. These optima inspire PRIM-based bump-hunting algorithms either by minimizing variance or by minimizing volume, thereby motivating an NFLT. We test our results on the Fashion-MNIST database, showing that peeling the largest principal components captures multiplicity, while peeling the smallest principal components isolates popular styles.

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.