With the rapid and continuous increase in academic publications, identifying high-quality research has become an increasingly pressing challenge. While recent methods leveraging Large Language Models (LLMs) for automated paper evaluation have shown great promise, they are often constrained by outdated domain knowledge and limited reasoning capabilities. In this work, we present PaperEval, a novel LLM-based framework for automated paper evaluation that addresses these limitations through two key components: 1) a domain-aware paper retrieval module that retrieves relevant concurrent work to support contextualized assessments of novelty and contributions, and 2) a latent reasoning mechanism that enables deep understanding of complex motivations and methodologies, along with comprehensive comparison against concurrently related work, to support more accurate and reliable evaluation. To guide the reasoning process, we introduce a progressive ranking optimization strategy that encourages the LLM to iteratively refine its predictions with an emphasis on relative comparison. Experiments on two datasets demonstrate that PaperEval consistently outperforms existing methods in both academic impact and paper quality evaluation. In addition, we deploy PaperEval in a real-world paper recommendation system for filtering high-quality papers, which has gained strong engagement on social media---amassing over 8,000 subscribers and attracting over 10,000 views for many filtered high-quality papers---demonstrating the practical effectiveness of PaperEval.

Yiyan Xu, Jinghao Zhang, Alireza Salemi, Xinting Hu, Wenjie Wang, Fuli Feng, Hamed Zamani, Xiangnan He, Tat-Seng Chua. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Personalized image generation has emerged as a promising direction in multimodal content creation. It aims to synthesize images tailored to individual style preferences (e.g. color schemes, character appearances, layout) and semantic intentions (e.g. emotion, action, scene contexts) by leveraging user-interacted history images and multimodal instructions. Despite notable progress, existing methods -- whether based on diffusion models, large language models, or Large Multimodal Models (LMMs) -- struggle to accurately capture and composite user style preferences and semantic intentions. In particular, the state-of-the-art LMM-based method suffers from the entanglement of visual features, leading to Guidance Collapse, where the generated images fail to preserve user-preferred styles or reflect the specified semantics.

Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload. However, these systems merely filter existing content and are constrained by its limited diversity, making it difficult to meet users' varied content needs. To address this limitation, personalized content generation has emerged as a promising direction with broad applications. Nevertheless, most existing research focuses on personalized text generation, with relatively little attention given to personalized image generation. The limited work in personalized image generation faces challenges in accurately capturing users' visual preferences and needs from noisy user-interacted images and complex multimodal instructions. Worse still, there is a lack of supervised data for training personalized image generation models.

With the explosion of user-generated content in recent years, efficient methods for organizing multimedia databases based on content and retrieving relevant items have become essential. Language-based audio retrieval seeks to find relevant audio clips based on natural language queries. However, there exists a scarcity of datasets specifically developed for this task. Moreover, the language annotations often carry biases, leading to unsatisfactory retrieval accuracy. In this work, we propose a novel framework for language-based audio retrieval that aims to: 1) utilize GPT-generated text to augment audio captions, thereby improving language diversity; 2) employ audio self-attention mechanisms to capture intricate acoustic features and temporal dependencies. Experiments conducted on two public datasets, containing both short- and long-term audios, demonstrate that our framework can achieve significant performance improvements compared with other methods. Specifically, the proposed framework can achieve a 27% increase in mean average precision (mAP) on the Clotho dataset, and a 31% improvement in mAP on the AudioCaps dataset compared with the baseline.

Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-defined Outfit Recommendation and Personalized Outfit Composition. However, both stages are constrained by existing fashion products, limiting their effectiveness in addressing users' diverse fashion needs. Recently, the advent of AI-generated content provides the opportunity for OR to transcend these limitations, showcasing the potential for personalized outfit generation and recommendation.

Recommender systems often grapple with noisy implicit feedback. Most studies alleviate the noise issues from data cleaning perspective such as data resampling and reweighting, but they are constrained by heuristic assumptions. Another denoising avenue is from model perspective, which proactively injects noises into user-item interactions and enhances the intrinsic denoising ability of models. However, this kind of denoising process poses significant challenges to the recommender model's representation capacity to capture noise patterns.

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, they suffer from intrinsic limitations such as the instability of GANs and the restricted representation ability of VAEs. Such limitations hinder the accurate modeling of the complex user interaction generation procedure, such as noisy interactions caused by various interference factors. In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner. To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis. In addition, we extend traditional DMs to tackle the unique challenges in recommendation: high resource costs for large-scale item prediction and temporal shifts of user preference. To this end, we propose two extensions of DiffRec: L-DiffRec clusters items for dimension compression and conducts the diffusion processes in the latent space; and T-DiffRec reweights user interactions based on the interaction timestamps to encode temporal information. We conduct extensive experiments on three datasets under multiple settings (e.g., clean training, noisy training, and temporal training). The empirical results validate the superiority of DiffRec with two extensions over competitive baselines.

The network traffic data is easily monitored and obtained by attackers. Attacks against different network traffic threaten the environment of the intranet. Deep learning methods have been widely used to classify network traffic for their high classification performance. The application of adversarial samples in computer vision confirms that deep learning methods are flawed, allowing existing methods to generate incorrect results with high confidence. In this paper, the adversarial samples are used on the network traffic classification model, causing the CNN model to produce incorrect classification results for network traffic. By training the classification model adversarially, we validate the training effect and improve the classification accuracy by means of the FGSM attack method. By using the adversarial samples to the network traffic data, our approach enables proactive defence against intranet eavesdropping before the attack occurs by influencing the attacker’s classification model to misclassify.