arXiv subjects

Songlin Wang

Publications and source records attributed to Songlin Wang.

At least 19 recordsLinked to original sources

arXiv2026

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly generating audio and video with fine-grained cross-modal correspondence remains challenging due to their fundamental structural differences. Most existing methods use audio and video VAEs trained separately. As a result, the two latent spaces lack cross-modal alignment, leaving the downstream generative model to learn cross-modal synchronization from scratch. We present OmniVAE, a jointly trained audio-video VAE that learns fine-grained semantic alignment between audio and video latent representations. Beyond reconstruction, OmniVAE uses a segment-level audio-video contrastive objective to capture temporal-semantic correspondence and align the two latent spaces. In parallel, it distills features from pretrained modality-specific semantic encoders into each modality, improving the downstream learnability of both latent spaces. Extensive experiments show that both objectives consistently improve the learnability of the latent spaces, translating into higher generation quality and more accurate cross-modal synchronization in downstream text-to-audio-video generation. These findings underscore the importance of learning unified representations as a foundation for omnimodal modeling.1

cs.SD↗

arXiv2026

MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: DeepStack cross-layer feature injection, which exposes the decoder to acoustic information from multiple encoder depths, and time markers, which provide explicit temporal cues by inserting timestamp markers into the audio-token stream. At the data level, we design an event-preserving audio annotation pipeline that segments raw audio at coherent event boundaries, applies branch-specific annotation to speech, music, and general audio, and merges the results into unified captions for pretraining. The intermediate branch-specific captions are further retained to support the construction of task-oriented SFT data. The model is pretrained on large-scale audio-language data, with time-aware objectives incorporated to support temporal grounding, and then undergoes multi-stage post-training to enhance instruction following and audio-grounded reasoning. We release 4B and 8B variants in both Instruct and Thinking configurations. MOSS-Audio achieves strong performance across general audio understanding, speech captioning, ASR, and timestamped ASR, positioning it as a promising understanding foundation for future voice agents.

cs.SD↗

arXiv2026

MOSS-TTS Technical Report

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

cs.SD↗

arXiv2026

RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce

Generative Retrieval (GR) is rapidly transforming e-commerce search by replacing traditional multi-stage pipelines with the autoregressive decoding of structured Semantic IDs (SIDs). Despite this architectural efficiency, aligning GR models with nuanced, real-world user preferences remains a critical challenge. While Direct Preference Optimization (DPO) offers an efficient alignment solution, its direct application to structured SIDs suffers from three limitations: (i) it penalizes shared hierarchical prefixes, causing gradient conflicts; (ii) it is vulnerable to noisy pseudo-negatives from implicit feedback; and (iii) in multi-label queries with multiple relevant items, it exacerbates a probability "squeezing effect" among valid candidates. To address these issues, we propose RAD-DPO, which introduces token-level gradient detachment to protect prefix structures, similarity-based dynamic reward weighting to mitigate label noise, and a multi-label global contrastive objective integrated with global SFT loss to explicitly expand positive coverage. Extensive offline evaluations and large-scale online A/B testing on JD.com's core search engine demonstrate that RAD-DPO achieves significant improvements in both retrieval precision and training efficiency, proving its robustness for massive industrial deployments.

cs.IR↗

arXiv2026

Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer

While semantic ID-based generative retrieval enables efficient end-to-end modeling in industrial applications, these methods face a persistent trade-off. On one hand, data-rich head items often suffer from ID collisions, which blur their distinct features and degrade downstream tasks. On the other hand, data-sparse tail items especially cold-start items are prone to semantic fragmentation during quantization; they are often mapped as isolated discrete points, which severely hinders their ability to generalize. To address this issue, we propose the Anchored Curriculum with Sequential Adaptive Quantization ($SA^2CRQ$) framework. The framework introduces Sequential Adaptive Residual Quantization (SARQ) to dynamically allocate code lengths based on item path entropy, assigning longer, discriminative IDs to head items and shorter, generalizable IDs to tail items. To mitigate data sparsity, the Anchored Curriculum Residual Quantization (ACRQ) component utilizes a frozen semantic manifold learned from head items to regularize and accelerate the representation learning of tail items. Experimental results from a large-scale industrial search system and multiple public datasets indicate that $SA^2CRQ$ yields consistent improvements over existing baselines, particularly in cold-start retrieval scenarios.

cs.IR↗

arXiv2026

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on cascaded pipelines, which increase cost, accumulate errors, and degrade overall quality. While systems such as Veo 3 and Sora 2 emphasize the value of simultaneous generation, joint multimodal modeling introduces unique challenges in architecture, data, and training. Moreover, the closed-source nature of existing systems limits progress in the field. In this work, we introduce MOVA (MOSS Video and Audio), an open-source model capable of generating high-quality, synchronized audio-visual content, including realistic lip-synced speech, environment-aware sound effects, and content-aligned music. MOVA employs a Mixture-of-Experts (MoE) architecture, with a total of 32B parameters, of which 18B are active during inference. It supports IT2VA (Image-Text to Video-Audio) generation task. By releasing the model weights and code, we aim to advance research and foster a vibrant community of creators. The released codebase features comprehensive support for efficient inference, LoRA fine-tuning, and prompt enhancement.

cs.CV↗

arXiv2026

MOSS Transcribe Diarize Technical Report

Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.

cs.SD↗

arXiv2025

A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval

Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy. Its core relies on a coarse-to-fine hierarchical architecture that enables rapid candidate selection and precise semantic matching, achieving millisecond-level response over billion-scale corpora. This capability makes it essential not only in traditional search and recommendation scenarios but also in the emerging paradigm of generative recommendation driven by large language models, where semantic IDs-themselves a form of coarse-to-fine representation-play a foundational role. However, the widely adopted dual-tower encoding architecture introduces inherent challenges, primarily representational space misalignment and retrieval index inconsistency, which degrade matching accuracy, retrieval stability, and performance on long-tail queries. These issues are further magnified in semantic ID generation, ultimately limiting the performance ceiling of downstream generative models. To address these challenges, this paper proposes a simple and effective framework named SCI comprising two synergistic modules: a symmetric representation alignment module that employs an innovative input-swapping mechanism to unify the dual-tower representation space without adding parameters, and an consistent indexing with dual-tower synergy module that redesigns retrieval paths using a dual-view indexing strategy to maintain consistency from training to inference. The framework is systematic, lightweight, and engineering-friendly, requiring minimal overhead while fully supporting billion-scale deployment. We provide theoretical guarantees for our approach, with its effectiveness validated by results across public datasets and real-world e-commerce datasets.

cs.IR↗

arXiv2025

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search

Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval performance. Though learning from cross-modality data has been studied extensively in tasks such as visual question answering or media summarization, multimodal retrieval remains a non-trivial and unsolved problem especially in the asymmetric scenario where the query is unimodal while the item is multimodal. In this paper, we propose a novel model named SMAR, which stands for Semantic-enhanced Modality-Asymmetric Retrieval, to tackle the problem of modality fusion and alignment in this kind of asymmetric scenario. Extensive experimental results on an industrial dataset show that the proposed model outperforms baseline models significantly in retrieval accuracy. We have open sourced our industrial dataset for the sake of reproducibility and future research works.

cs.IR↗

arXiv2024

Advancing Re-Ranking with Multimodal Fusion and Target-Oriented Auxiliary Tasks in E-Commerce Search

In the rapidly evolving field of e-commerce, the effectiveness of search re-ranking models is crucial for enhancing user experience and driving conversion rates. Despite significant advancements in feature representation and model architecture, the integration of multimodal information remains underexplored. This study addresses this gap by investigating the computation and fusion of textual and visual information in the context of re-ranking. We propose \textbf{A}dvancing \textbf{R}e-Ranking with \textbf{M}ulti\textbf{m}odal Fusion and \textbf{T}arget-Oriented Auxiliary Tasks (ARMMT), which integrates an attention-based multimodal fusion technique and an auxiliary ranking-aligned task to enhance item representation and improve targeting capabilities. This method not only enriches the understanding of product attributes but also enables more precise and personalized recommendations. Experimental evaluations on JD.com's search platform demonstrate that ARMMT achieves state-of-the-art performance in multimodal information integration, evidenced by a 0.22\% increase in the Conversion Rate (CVR), significantly contributing to Gross Merchandise Volume (GMV). This pioneering approach has the potential to revolutionize e-commerce re-ranking, leading to elevated user satisfaction and business growth.

cs.IR↗

arXiv2024

Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval

Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER employing Residual Quantization-based Semantic Identifiers (RQ-SID), have shown significant promise in e-commerce scenarios by effectively managing item IDs. However, a critical issue termed the "\textbf{Hourglass}" phenomenon, occurs in RQ-SID, where intermediate codebook tokens become overly concentrated, hindering the full utilization of generative retrieval methods. This paper analyses and addresses this problem by identifying data sparsity and long-tailed distribution as the primary causes. Through comprehensive experiments and detailed ablation studies, we analyze the impact of these factors on codebook utilization and data distribution. Our findings reveal that the "Hourglass" phenomenon substantially impacts the performance of RQ-SID in generative retrieval. We propose effective solutions to mitigate this issue, thereby significantly enhancing the effectiveness of generative retrieval in real-world E-commerce applications.

cs.IR↗

arXiv2024

MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search

Traffic allocation is a process of redistributing natural traffic to products by adjusting their positions in the post-search phase, aimed at effectively fostering merchant growth, precisely meeting customer demands, and ensuring the maximization of interests across various parties within e-commerce platforms. Existing methods based on learning to rank neglect the long-term value of traffic allocation, whereas approaches of reinforcement learning suffer from balancing multiple objectives and the difficulties of cold starts within realworld data environments. To address the aforementioned issues, this paper propose a multi-objective deep reinforcement learning framework consisting of multi-objective Q-learning (MOQ), a decision fusion algorithm (DFM) based on the cross-entropy method(CEM), and a progressive data augmentation system(PDA). Specifically. MOQ constructs ensemble RL models, each dedicated to an objective, such as click-through rate, conversion rate, etc. These models individually determine the position of items as actions, aiming to estimate the long-term value of multiple objectives from an individual perspective. Then we employ DFM to dynamically adjust weights among objectives to maximize long-term value, addressing temporal dynamics in objective preferences in e-commerce scenarios. Initially, PDA trained MOQ with simulated data from offline logs. As experiments progressed, it strategically integrated real user interaction data, ultimately replacing the simulated dataset to alleviate distributional shifts and the cold start problem. Experimental results on real-world online e-commerce systems demonstrate the significant improvements of MODRL-TA, and we have successfully deployed MODRL-TA on an e-commerce search platform.

cs.LG↗

arXiv2024

A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Search

Re-ranking is a process of rearranging ranking list to more effectively meet user demands by accounting for the interrelationships between items. Existing methods predominantly enhance the precision of search results, often at the expense of diversity, leading to outcomes that may not fulfill the varied needs of users. Conversely, methods designed to promote diversity might compromise the precision of the results, failing to satisfy the users' requirements for accuracy. To alleviate the above problems, this paper proposes a Preference-oriented Diversity Model Based on Mutual-information (PODM-MI), which consider both accuracy and diversity in the re-ranking process. Specifically, PODM-MI adopts Multidimensional Gaussian distributions based on variational inference to capture users' diversity preferences with uncertainty. Then we maximize the mutual information between the diversity preferences of the users and the candidate items using the maximum variational inference lower bound to enhance their correlations. Subsequently, we derive a utility matrix based on the correlations, enabling the adaptive ranking of items in line with user preferences and establishing a balance between the aforementioned objectives. Experimental results on real-world online e-commerce systems demonstrate the significant improvements of PODM-MI, and we have successfully deployed PODM-MI on an e-commerce search platform.

cs.IR↗

arXiv2024

Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model

In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations, meeting the system performance requirements presents a significant challenge. Contrasting with existing industry works, we propose a novel method: a Generalizable and RAnk-ConsistEnt Pre-Ranking Model (GRACE), which achieves: 1) Ranking consistency by introducing multiple binary classification tasks that predict whether a product is within the top-k results as estimated by the ranking model, which facilitates the addition of learning objectives on common point-wise ranking models; 2) Generalizability through contrastive learning of representation for all products by pre-training on a subset of ranking product embeddings; 3) Ease of implementation in feature construction and online deployment. Our extensive experiments demonstrate significant improvements in both offline metrics and online A/B test: a 0.75% increase in AUC and a 1.28% increase in CVR.

cs.IR↗

arXiv2023

A Multi-Granularity Matching Attention Network for Query Intent Classification in E-commerce Retrieval

Query intent classification, which aims at assisting customers to find desired products, has become an essential component of the e-commerce search. Existing query intent classification models either design more exquisite models to enhance the representation learning of queries or explore label-graph and multi-task to facilitate models to learn external information. However, these models cannot capture multi-granularity matching features from queries and categories, which makes them hard to mitigate the gap in the expression between informal queries and categories. This paper proposes a Multi-granularity Matching Attention Network (MMAN), which contains three modules: a self-matching module, a char-level matching module, and a semantic-level matching module to comprehensively extract features from the query and a query-category interaction matrix. In this way, the model can eliminate the difference in expression between queries and categories for query intent classification. We conduct extensive offline and online A/B experiments, and the results show that the MMAN significantly outperforms the strong baselines, which shows the superiority and effectiveness of MMAN. MMAN has been deployed in production and brings great commercial value for our company.

cs.IR↗

arXiv2023

Learning Multi-Stage Multi-Grained Semantic Embeddings for E-Commerce Search

Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework to learn embedding vectors for query and item separately and thus leverage efficient approximate nearest neighbor (ANN) search to retrieve relevant items. However, existing EBR methods usually ignore inconsistent user behaviors in industrial multi-stage search systems, resulting in insufficient retrieval efficiency with a low commercial return. To tackle this challenge, we propose to improve EBR methods by learning Multi-level Multi-Grained Semantic Embeddings(MMSE). We propose the multi-stage information mining to exploit the ordered, clicked, unclicked and random sampled items in practical user behavior data, and then capture query-item similarity via a post-fusion strategy. We then propose multi-grained learning objectives that integrate the retrieval loss with global comparison ability and the ranking loss with local comparison ability to generate semantic embeddings. Both experiments on a real-world billion-scale dataset and online A/B tests verify the effectiveness of MMSE in achieving significant performance improvements on metrics such as offline recall and online conversion rate (CVR).

cs.IR↗

arXiv2023

ZhichunRoad at Amazon KDD Cup 2022: MultiTask Pre-Training for E-Commerce Product Search

In this paper, we propose a robust multilingual model to improve the quality of search results. Our model not only leverage the processed class-balanced dataset, but also benefit from multitask pre-training that leads to more general representations. In pre-training stage, we adopt mlm task, classification task and contrastive learning task to achieve considerably performance. In fine-tuning stage, we use confident learning, exponential moving average method (EMA), adversarial training (FGM) and regularized dropout strategy (R-Drop) to improve the model's generalization and robustness. Moreover, we use a multi-granular semantic unit to discover the queries and products textual metadata for enhancing the representation of the model. Our approach obtained competitive results and ranked top-8 in three tasks. We release the source code and pre-trained models associated with this work.

cs.CL↗

arXiv2022

Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search

BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on. However, this technique may not always work, especially for two scenarios: a corpus that contains very different text from the general corpus Wikipedia, or a task that learns embedding spacial distribution for a specific purpose (e.g., approximate nearest neighbor search). In this paper, to tackle the above two scenarios that we have encountered in an industrial e-commerce search system, we propose customized and novel pre-training tasks for two critical modules: user intent detection and semantic embedding retrieval. The customized pre-trained models after fine-tuning, being less than 10% of BERT-base's size in order to be feasible for cost-efficient CPU serving, significantly improve the other baseline models: 1) no pre-training model and 2) fine-tuned model from the official pre-trained BERT using general corpus, on both offline datasets and online system. We have open sourced our datasets for the sake of reproducibility and future works.

cs.IR↗