Shaoning Zeng

Rajesh Kumar, Waqar Ali, Junaid Ahmed et al.

Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support generated claims. We present AutoResearch, an execution-grounded multi-agent framework for reliable research workflow automation. AutoResearch couples sandboxed Python/PyTorch execution, iterative code repair, citation verification, claim-support auditing, decision control, and structured \LaTeX{} artifact generation. The system treats runtime errors, citation-verification failures, and review-agent feedback as practical filtering signals for generated research artifacts. In controlled evaluations on HumanEval, MBPP, a SciCode subset, citation-validation tasks, claim-support auditing, and small end-to-end workflow stress tests, AutoResearch improves execution success, citation validity, local claim support, and workflow completion relative to directly comparable baselines. Code-oriented agents are reported separately as partial comparisons. AutoResearch is intended as a reliability-oriented research assistant, not as a fully autonomous scientist or a standalone manuscript-quality benchmark. Source Code: https://github.com/raja21068/AutoResearch

Haoran Sun, Zekun Zhang, Shaoning Zeng

One of the key factors influencing the reasoning capabilities of LLM-based agents is their ability to leverage long-term memory. Integrating long-term memory mechanisms allows agents to make informed decisions grounded in historical interactions. While recent advances have significantly improved the storage and retrieval components, by encoding memory into dense vectors for similarity search or organizing memory as structured knowledge graphs most existing approaches fall short in memory updating. In particular, they lack mechanisms for dynamically refining preference memory representations in response to evolving user behaviors and contexts. To address this gap, we propose a Preference-Aware Memory Update Mechanism (PAMU) that enables dynamic and personalized memory refinement. By integrating sliding window averages (SW) with exponential moving averages (EMA), PAMU constructs a fused preference-aware representation that captures both short-term fluctuations and long-term user tendencies. We conduct experiments on five task scenarios of the LoCoMo dataset, and the results show that our mechanism can significantly improve the output quality of LLM in five baselines, validating its effectiveness in long-term conversations.

Haoran Sun, Zekun Zhang, Shaoning Zeng

Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning. However, achieving high-quality alignment with human intent and safety norms without human annotations remains a fundamental challenge. In this work, we propose an Uncertainty-Driven Adaptive Self-Alignment (UDASA) framework designed to improve LLM alignment in a fully automated manner. UDASA first generates multiple responses for each input and quantifies output uncertainty across three dimensions: semantics, factuality, and value alignment. Based on these uncertainty scores, the framework constructs preference pairs and categorizes training samples into three stages, conservative, moderate, and exploratory, according to their uncertainty difference. The model is then optimized progressively across these stages. In addition, we conduct a series of preliminary studies to validate the core design assumptions and provide strong empirical motivation for the proposed framework. Experimental results show that UDASA outperforms existing alignment methods across multiple tasks, including harmlessness, helpfulness, truthfulness, and controlled sentiment generation, significantly improving model performance.

Haoran Sun, Zekun Zhang, Shaoning Zeng

The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference optimization, improve user alignment yet fail to enhance the model's domain cognition. To bridge this gap, we propose a novel Dual-Phase Self-Evolution (DPSE) framework that jointly optimizes user preference adaptation and domain-specific competence. DPSE introduces a Censor module to extract multi-dimensional interaction signals and estimate satisfaction scores, which guide structured data expansion via topic-aware and preference-driven strategies. These expanded datasets support a two-stage fine-tuning pipeline: supervised domain grounding followed by frequency-aware preference optimization. Experiments across general NLP benchmarks and long-term dialogue tasks demonstrate that DPSE consistently outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines. Ablation studies validate the contribution of each module. In this way, our framework provides an autonomous path toward continual self-evolution of LLMs.

Yaguan Qian, Qiqi Shao, Tengteng Yao et al.

Adversarial training is wildly considered as one of the most effective way to defend against adversarial examples. However, existing adversarial training methods consume unbearable time, due to the fact that they need to generate adversarial examples in the large input space. To speed up adversarial training, we propose a novel adversarial training method that does not need to generate real adversarial examples. By adding perturbations to logits to generate Endogenous Adversarial Examples (EAEs) -- the adversarial examples in the latent space, the time consuming gradient calculation can be avoided. Extensive experiments are conducted on CIFAR-10 and ImageNet, and the results show that comparing to state-of-the-art methods, our EAE adversarial training not only shortens the training time, but also enhances the robustness of the model and has less impact on the accuracy of clean examples than the existing methods.

Yaguan Qian, Jiamin Wang, Bin Wang et al.

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted more attention. Many algorithms have been proposed to craft powerful adversarial examples. However, most of these algorithms modified the global or local region of pixels without taking network explanations into account. Hence, the perturbations are redundant, which are easily detected by human eyes. In this paper, we propose a novel method to generate local region perturbations. The main idea is to find a contributing feature region (CFR) of an image by simulating the human attention mechanism and then add perturbations to CFR. Furthermore, a soft mask matrix is designed on the basis of an activation map to finely represent the contributions of each pixel in CFR. With this soft mask, we develop a new loss function with inverse temperature to search for optimal perturbations in CFR. Due to the network explanations, the perturbations added to CFR are more effective than those added to other regions. Extensive experiments conducted on CIFAR-10 and ILSVRC2012 demonstrate the effectiveness of the proposed method, including attack success rate, imperceptibility, and transferability.

Shaoning Zeng, Bob Zhang

In the generator of typical Generative Adversarial Networks (GANs), a noise is inputted to generate fake samples via a series of convolutional operations. However, current noise generation models merely relies on the information from the pixel space, which increases the difficulty to approach the target distribution. Fortunately, the long proven wavelet transformation is able to decompose multiple spectral information from the images. In this work, we propose a novel multi-channel wavelet-based filtering method for GANs, to cope with this problem. When embedding a wavelet deconvolution layer in the generator, the resultant GAN, called WaveletGAN, takes advantage of the wavelet deconvolution to learn a filtering with multiple channels, which can efficiently homogenize the generated noise via an averaging operation, so as to generate high-fidelity samples. We conducted benchmark experiments on the Fashion-MNIST, KMNIST and SVHN datasets through an open GAN benchmark tool. The results show that WaveletGAN has excellent performance in generating high-fidelity samples, thanks to the smallest FIDs obtained on these datasets.

Jianhang Zhou, Shaoning Zeng, Bob Zhang

The two-stage strategy has been widely used in image classification. However, these methods barely take the classification criteria of the first stage into consideration in the second prediction stage. In this paper, we propose a novel two-stage representation method (TSR), and convert it to a Single-Teacher Single-Student (STSS) problem in our two-stage image classification framework. We seek the nearest neighbours of the test sample to choose candidate target classes. Meanwhile, the first stage classifier is formulated as the teacher, which holds the classification scores. The samples of the candidate classes are utilized to learn a student classifier based on L2-minimization in the second stage. The student will be supervised by the teacher classifier, which approves the student only if it obtains a higher score. In actuality, the proposed framework generates a stronger classifier by staging two weaker classifiers in a novel way. The experiments conducted on several face and object databases show that our proposed framework is effective and outperforms multiple popular classification methods.

Shaoning Zeng, Bob Zhang, Yanghao Zhang et al.

Deep convolutional neural networks provide a powerful feature learning capability for image classification. The deep image features can be utilized to deal with many image understanding tasks like image classification and object recognition. However, the robustness obtained in one dataset can be hardly reproduced in the other domain, which leads to inefficient models far from state-of-the-art. We propose a deep collaborative weight-based classification (DeepCWC) method to resolve this problem, by providing a novel option to fully take advantage of deep features in classic machine learning. It firstly performs the L2-norm based collaborative representation on the original images, as well as the deep features extracted by deep CNN models. Then, two distance vectors, obtained based on the pair of linear representations, are fused together via a novel collaborative weight. This collaborative weight enables deep and classic representations to weigh each other. We observed the complementarity between two representations in a series of experiments on 10 facial and object datasets. The proposed DeepCWC produces very promising classification results, and outperforms many other benchmark methods, especially the ones claimed for Fashion-MNIST. The code is going to be published in our public repository.