RecGPT Technical Report

Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evolving and latent interests. As a result, it reinforces filter bubbles and long-tail phenomena, ultimately harming user experience and threatening the sustainability of the whole recommendation ecosystem. To address these challenges, we rethink the overall design paradigm of recommender systems and propose RecGPT, a next-generation framework that places user intent at the center of the recommendation pipeline. By integrating large language models (LLMs) into key stages of user interest mining, item retrieval, and explanation generation, RecGPT transforms log-fitting recommendation into an intent-centric process. To effectively align general-purpose LLMs to the above domain-specific recommendation tasks at scale, RecGPT incorporates a multi-stage training paradigm, which integrates reasoning-enhanced pre-alignment and self-training evolution, guided by a Human-LLM cooperative judge system. Currently, RecGPT has been fully deployed on the Taobao App. Online experiments demonstrate that RecGPT achieves consistent performance gains across stakeholders: users benefit from increased content diversity and satisfaction, merchants and the platform gain greater exposure and conversions. These comprehensive improvement results across all stakeholders validates that LLM-driven, intent-centric design can foster a more sustainable and mutually beneficial recommendation ecosystem.

AUV-Fusion: Cross-Modal Adversarial Fusion of User Interactions and Visual Perturbations Against VARS

Modern Visual-Aware Recommender Systems (VARS) exploit the integration of user interaction data and visual features to deliver personalized recommendations with high precision. However, their robustness against adversarial attacks remains largely underexplored, posing significant risks to system reliability and security. Existing attack strategies suffer from notable limitations: shilling attacks are costly and detectable, and visual-only perturbations often fail to align with user preferences. To address these challenges, we propose AUV-Fusion, a cross-modal adversarial attack framework that adopts high-order user preference modeling and cross-modal adversary generation. Specifically, we obtain robust user embeddings through multi-hop user-item interactions and transform them via an MLP into semantically aligned perturbations. These perturbations are injected onto the latent space of a pre-trained VAE within the diffusion model. By synergistically integrating genuine user interaction data with visually plausible perturbations, AUV-Fusion eliminates the need for injecting fake user profiles and effectively mitigates the challenge of insufficient user preference extraction inherent in traditional visual-only attacks. Comprehensive evaluations on diverse VARS architectures and real-world datasets demonstrate that AUV-Fusion significantly enhances the exposure of target (cold-start) items compared to conventional baseline methods. Moreover, AUV-Fusion maintains exceptional stealth under rigorous scrutiny.

Sustainability Evaluation Metrics for Recommender Systems

Sustainability-oriented evaluation metrics can help to assess the quality of recommender systems beyond wide-spread metrics such as accuracy, precision, recall, and satisfaction. Following the United Nations`s sustainable development goals (SDGs), such metrics can help to analyse the impact of recommender systems on environmental, social, and economic aspects. We discuss different basic sustainability evaluation metrics for recommender systems and analyze their applications.

LLM-based Content Classification Approach for GitHub Repositories by the README Files

GitHub is the world's most popular platform for storing, sharing, and managing code. Every GitHub repository has a README file associated with it. The README files should contain project-related information as per the recommendations of GitHub to support the usage and improvement of repositories. However, GitHub repository owners sometimes neglected these recommendations. This prevents a GitHub repository from reaching its full potential. This research posits that the comprehensiveness of a GitHub repository's README file significantly influences its adoption and utilization, with a lack of detail potentially hindering its full potential for widespread engagement and impact within the research community. Large Language Models (LLMs) have shown great performance in many text-based tasks including text classification, text generation, text summarization and text translation. In this study, an approach is developed to fine-tune LLMs for automatically classifying different sections of GitHub README files. Three encoder-only LLMs are utilized, including BERT, DistilBERT and RoBERTa. These pre-trained models are then fine-tuned based on a gold-standard dataset consisting of 4226 README file sections. This approach outperforms current state-of-the-art methods and has achieved an overall F1 score of 0.98. Moreover, we have also investigated the use of Parameter-Efficient Fine-Tuning (PEFT) techniques like Low-Rank Adaptation (LoRA) and shown an economical alternative to full fine-tuning without compromising much performance. The results demonstrate the potential of using LLMs in designing an automatic classifier for categorizing the content of GitHub README files. Consequently, this study contributes to the development of automated tools for GitHub repositories to improve their identifications and potential usages.

Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors

Advances in embedding models for text, image, audio, and video drive progress across multiple domains, including retrieval-augmented generation, recommendation systems, vehicle/person reidentification, and face recognition. Many applications in these domains require an efficient method to retrieve items that are close to a given query in the embedding space while satisfying a filter condition based on the item's attributes, a problem known as Filtered Approximate Nearest Neighbor Search (FANNS). In this work, we present a comprehensive survey and taxonomy of FANNS methods and analyze how they are benchmarked in the literature. By doing so, we identify a key challenge in the current FANNS landscape: the lack of diverse and realistic datasets, particularly ones derived from the latest transformer-based text embedding models. To address this, we introduce a novel dataset consisting of embedding vectors for the abstracts of over 2.7 million research articles from the arXiv repository, accompanied by 11 real-world attributes such as authors and categories. We benchmark a wide range of FANNS methods on our novel dataset and find that each method has distinct strengths and limitations; no single approach performs best across all scenarios. ACORN, for example, supports various filter types and performs reliably across dataset scales but is often outperformed by more specialized methods. SeRF shows excellent performance for range filtering on ordered attributes but cannot handle categorical attributes. Filtered-DiskANN and UNG excel on the medium-scale dataset but fail on the large-scale dataset, highlighting the challenge posed by transformer-based embeddings, which are often more than an order of magnitude larger than earlier embeddings. We conclude that no universally best method exists.

Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

We introduce a novel self-supervised multi-modal relational item representation learning framework designed to infer substitutable and complementary items. Existing approaches primarily focus on modeling item-item associations deduced from user behaviors using graph neural networks (GNNs) or leveraging item content information. However, these methods often overlook critical challenges, such as noisy user behavior data and data sparsity due to the long-tailed distribution of these behaviors. In this paper, we propose MMSC, a self-supervised multi-modal relational item representation learning framework to address these challenges. Specifically, MMSC consists of three main components: (1) a multi-modal item representation learning module that leverages a multi-modal foundational model and learns from item metadata, (2) a self-supervised behavior-based representation learning module that denoises and learns from user behavior data, and (3) a hierarchical representation aggregation mechanism that integrates item representations at both the semantic and task levels. Additionally, we leverage LLMs to generate augmented training data, further enhancing the denoising process during training. We conduct extensive experiments on five real-world datasets, showing that MMSC outperforms existing baselines by 26.1% for substitutable recommendation and 39.2% for complementary recommendation. In addition, we empirically show that MMSC is effective in modeling cold-start items.

PHAX: A Structured Argumentation Framework for User-Centered Explainable AI in Public Health and Biomedical Sciences

Ensuring transparency and trust in AI-driven public health and biomedical sciences systems requires more than accurate predictions-it demands explanations that are clear, contextual, and socially accountable. While explainable AI (XAI) has advanced in areas like feature attribution and model interpretability, most methods still lack the structure and adaptability needed for diverse health stakeholders, including clinicians, policymakers, and the general public. We introduce PHAX-a Public Health Argumentation and eXplainability framework-that leverages structured argumentation to generate human-centered explanations for AI outputs. PHAX is a multi-layer architecture combining defeasible reasoning, adaptive natural language techniques, and user modeling to produce context-aware, audience-specific justifications. More specifically, we show how argumentation enhances explainability by supporting AI-driven decision-making, justifying recommendations, and enabling interactive dialogues across user types. We demonstrate the applicability of PHAX through use cases such as medical term simplification, patient-clinician communication, and policy justification. In particular, we show how simplification decisions can be modeled as argument chains and personalized based on user expertise-enhancing both interpretability and trust. By aligning formal reasoning methods with communicative demands, PHAX contributes to a broader vision of transparent, human-centered AI in public health.

Generative Recommendation with Semantic IDs: A Practitioner's Handbook

Generative recommendation (GR) has gained increasing attention for its promising performance compared to traditional models. A key factor contributing to the success of GR is the semantic ID (SID), which converts continuous semantic representations (e.g., from large language models) into discrete ID sequences. This enables GR models with SIDs to both incorporate semantic information and learn collaborative filtering signals, while retaining the benefits of discrete decoding. However, varied modeling techniques, hyper-parameters, and experimental setups in existing literature make direct comparisons between GR proposals challenging. Furthermore, the absence of an open-source, unified framework hinders systematic benchmarking and extension, slowing model iteration. To address this challenge, our work introduces and open-sources a framework for Generative Recommendation with semantic ID, namely GRID, specifically designed for modularity to facilitate easy component swapping and accelerate idea iteration. Using GRID, we systematically experiment with and ablate different components of GR models with SIDs on public benchmarks. Our comprehensive experiments with GRID reveal that many overlooked architectural components in GR models with SIDs substantially impact performance. This offers both novel insights and validates the utility of an open-source platform for robust benchmarking and GR research advancement. GRID is open-sourced at https://github.com/snap-research/GRID.

Exploration on Demand: From Algorithmic Control to User Empowerment

Recommender systems often struggle with over-specialization, which severely limits users' exposure to diverse content and creates filter bubbles that reduce serendipitous discovery. To address this fundamental limitation, this paper introduces an adaptive clustering framework with user-controlled exploration that effectively balances personalization and diversity in movie recommendations. Our approach leverages sentence-transformer embeddings to group items into semantically coherent clusters through an online algorithm with dynamic thresholding, thereby creating a structured representation of the content space. Building upon this clustering foundation, we propose a novel exploration mechanism that empowers users to control recommendation diversity by strategically sampling from less-engaged clusters, thus expanding their content horizons while preserving relevance. Experiments on the MovieLens dataset demonstrate the system's effectiveness, showing that exploration significantly reduces intra-list similarity from 0.34 to 0.26 while simultaneously increasing unexpectedness to 0.73. Furthermore, our Large Language Model-based A/B testing methodology, conducted with 300 simulated users, reveals that 72.7% of long-term users prefer exploratory recommendations over purely exploitative ones, providing strong evidence for the system's ability to promote meaningful content discovery without sacrificing user satisfaction.

ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

Real-world user-generated short videos, especially those distributed on platforms such as WeChat Channel and TikTok, dominate the mobile internet. However, current large multimodal models lack essential temporally-structured, detailed, and in-depth video comprehension capabilities, which are the cornerstone of effective video search and recommendation, as well as emerging video applications. Understanding real-world shorts is actually challenging due to their complex visual elements, high information density in both visuals and audio, and fast pacing that focuses on emotional expression and viewpoint delivery. This requires advanced reasoning to effectively integrate multimodal information, including visual, audio, and text. In this work, we introduce ARC-Hunyuan-Video, a multimodal model that processes visual, audio, and textual signals from raw video inputs end-to-end for structured comprehension. The model is capable of multi-granularity timestamped video captioning and summarization, open-ended video question answering, temporal video grounding, and video reasoning. Leveraging high-quality data from an automated annotation pipeline, our compact 7B-parameter model is trained through a comprehensive regimen: pre-training, instruction fine-tuning, cold start, reinforcement learning (RL) post-training, and final instruction fine-tuning. Quantitative evaluations on our introduced benchmark ShortVid-Bench and qualitative comparisons demonstrate its strong performance in real-world video comprehension, and it supports zero-shot or fine-tuning with a few samples for diverse downstream applications. The real-world production deployment of our model has yielded tangible and measurable improvements in user engagement and satisfaction, a success supported by its remarkable efficiency, with stress tests indicating an inference time of just 10 seconds for a one-minute video on H20 GPU.