arXiv subjects

Jinsong Lan

Publications and source records attributed to Jinsong Lan.

33 records · Page 2Linked to original sources

arXiv2025

Enhancing Sequential Recommendation with World Knowledge from Large Language Models

Sequential Recommendation System~(SRS) has become pivotal in modern society, which predicts subsequent actions based on the user's historical behavior. However, traditional collaborative filtering-based sequential recommendation models often lead to suboptimal performance due to the limited information of their collaborative signals. With the rapid development of LLMs, an increasing number of works have incorporated LLMs' world knowledge into sequential recommendation. Although they achieve considerable gains, these approaches typically assume the correctness of LLM-generated results and remain susceptible to noise induced by LLM hallucinations. To overcome these limitations, we propose GRASP (Generation Augmented Retrieval with Holistic Attention for Sequential Prediction), a flexible framework that integrates generation augmented retrieval for descriptive synthesis and similarity retrieval, and holistic attention enhancement which employs multi-level attention to effectively employ LLM's world knowledge even with hallucinations and better capture users' dynamic interests. The retrieved similar users/items serve as auxiliary contextual information for the later holistic attention enhancement module, effectively mitigating the noisy guidance of supervision-based methods. Comprehensive evaluations on two public benchmarks and one industrial dataset reveal that GRASP consistently achieves state-of-the-art performance when integrated with diverse backbones. The code is available at: https://anonymous.4open.science/r/GRASP-SRS.

cs.IR↗

arXiv2025

Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization

Embedding models are a cornerstone of modern AI. Driven by Multimodal Large Language Models (MLLMs), they have made great progress in architecture and data curation, while the holistic paradigm is still limited to SSC, i.e., single input, singular embedding, contrastive supervision, which collapses rich, multifaceted inputs into monolithic embeddings and fails to fully exploit MLLM capabilities. In this paper, we tailor one Parallel Decoupling Framework (PDF) for multimodal embedding learning, by utilizing the proprietary steerability of MLLMs, i.e., their ability to flexibly generate quite differentiated response under explicit instructions. Concretely, PDF conditions a shared MLLM backbone on distinct, learnable prefixes to roll out multiple parallel paths for one input, then relies on these paths to obtain parallel embeddings. To promote full parallel diversity, we employ Mutual Information Minimization (MIM) as an explicit constraint, coupled with per-path contrastive supervision to maintain semantic alignment. Such dual-objectives force PDF to yield robust semantic coverage and a generalizable embedding space. Ultimately, the remarkable embedding space are accessible at inference via one single forward pass, incurring negligible computational overhead. We instantiate PDF on multiple MLLM backbones and prove its effectiveness on MMEB benchmark. Significant gains are consistently achieved across various resolutions and model sizes, e.g., boosting the VLM2Vec-LLaVA-1.6-LR model by a remarkable +8.9% (7B), while the VLM2Vec-Qwen2VL models by +4.2% (2B) and +3.1% (7B). In terms of efficiency, our 2B model surpasses its baseline by +2.6% using only half the computational budget.

cs.LG↗

arXiv2025

Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation

The unification of understanding and generation within a single multi-modal large model (MLLM) remains one significant challenge, largely due to the dichotomy between continuous and discrete visual tokenizations. Continuous tokenizer (CT) achieves strong performance by bridging multiple independently-trained understanding modules and generation modules, but suffers from complex multi-stage pipelines and substantial engineering overhead. Conversely, discrete tokenizers (DT) offer a conceptually elegant idea by quantizing each image into a primitive, but inevitably leading to information loss and performance degradation. To resolve this tension, we question the binary choice between CT and DT, inspired by the wave-particle duality of light, and propose the Continuous-Discrete Dualistic Visual Tokenizer (CDD-VT). We treat visual data as a flexible composition of image primitives derived from quantized codebooks, with the crucial insight that the primitive number assigned to each visual sample is adaptively determined according to its complexity: simple instances use a few primitives, emulating discrete tokenization, while complex instances use many, approximating continuous tokenization. Two core components are designed: Diverse Quantitative Primitives, which encourage primitives orthogonality to better populate information space, and Dynamic Primitive Allocator, which assesses sample complexity to determine the optimal set of primitives. Extensive experiments on reconstruction, retrieval and classification show that CDD-VT achieves superior performance over to specialized CT and DT, effectively getting strong result within a concise and scalable MLLM.

cs.CV↗

arXiv2025

Leveraging Scene Context with Dual Networks for Sequential User Behavior Modeling

Modeling sequential user behaviors for future behavior prediction is crucial in improving user's information retrieval experience. Recent studies highlight the importance of incorporating contextual information to enhance prediction performance. One crucial but usually neglected contextual information is the scene feature which we define as sub-interfaces within an app, created by developers to provide specific functionalities, such as ``text2product search" and ``live" modules in e-commence apps. Different scenes exhibit distinct functionalities and usage habits, leading to significant distribution gap in user engagement across them. Popular sequential behavior models either ignore the scene feature or merely use it as attribute embeddings, which cannot effectively capture the dynamic interests and interplay between scenes and items when modeling user sequences. In this work, we propose a novel Dual Sequence Prediction networks (DSPnet) to effectively capture the dynamic interests and interplay between scenes and items for future behavior prediction. DSPnet consists of two parallel networks dedicated to learn users' dynamic interests over items and scenes, and a sequence feature enhancement module to capture the interplay for enhanced future behavior prediction. Further, we introduce a Conditional Contrastive Regularization (CCR) loss to capture the invariance of similar historical sequences. Theoretical analysis suggests that DSPnet is a principled way to learn the joint relationships between scene and item sequences. Extensive experiments are conducted on one public benchmark and two collected industrial datasets. The method has been deployed online in our system, bringing a 0.04 point increase in CTR, 0.78\% growth in deals, and 0.64\% rise in GMV. The codes are available at this anonymous github: \textcolor{blue}{https://anonymous.4open.science/r/DSPNet-ForPublish-2506/}.

cs.IR↗

arXiv2025

Learning Multi-Branch Cooperation for Enhanced Click-Through Rate Prediction at Taobao

Existing click-through rate (CTR) prediction works have studied the role of feature interaction through a variety of techniques. Each interaction technique exhibits its own strength, and solely using one type usually constrains the model's capability to capture the complex feature relationships, especially for industrial data with enormous input feature fields. Recent research shows that effective CTR models often combine an MLP network with a dedicated feature interaction network in a two-parallel structure. However, the interplay and cooperative dynamics between different streams or branches remain under-researched. In this work, we introduce a novel Multi-Branch Cooperation Network (MBCnet) which enables multiple branch networks to collaborate with each other for better complex feature interaction modeling. Specifically, MBCnet consists of three branches: the Extensible Feature Grouping and Crossing (EFGC) branch that promotes the model's memorization ability of specific feature fields, the low rank Cross Net branch and Deep branch to enhance explicit and implicit feature crossing for improved generalization. Among these branches, a novel cooperation scheme is proposed based on two principles: Branch co-teaching and moderate differentiation. Branch co-teaching encourages well-learned branches to support poorly-learned ones on specific training samples. Moderate differentiation advocates branches to maintain a reasonable level of difference in their feature representations on the same inputs. This cooperation strategy improves learning through mutual knowledge sharing and boosts the discovery of diverse feature interactions across branches. Experiments on large-scale industrial datasets and online A/B test at Taobao app demonstrate MBCnet's superior performance, delivering a 0.09 point increase in CTR, 1.49% growth in deals, and 1.62% rise in GMV. Core codes are available online.

cs.IR↗

arXiv2025

MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework

Recent advancements in large language models (LLMs) and multi-modal LLMs have been remarkable. However, these models still rely solely on their parametric knowledge, which limits their ability to generate up-to-date information and increases the risk of producing erroneous content. Retrieval-Augmented Generation (RAG) partially mitigates these challenges by incorporating external data sources, yet the reliance on databases and retrieval systems can introduce irrelevant or inaccurate documents, ultimately undermining both performance and reasoning quality. In this paper, we propose Multi-Modal Knowledge-Based Retrieval-Augmented Generation (MMKB-RAG), a novel multi-modal RAG framework that leverages the inherent knowledge boundaries of models to dynamically generate semantic tags for the retrieval process. This strategy enables the joint filtering of retrieved documents, retaining only the most relevant and accurate references. Extensive experiments on knowledge-based visual question-answering tasks demonstrate the efficacy of our approach: on the E-VQA dataset, our method improves performance by +4.2% on the Single-Hop subset and +0.4% on the full dataset, while on the InfoSeek dataset, it achieves gains of +7.8% on the Unseen-Q subset, +8.2% on the Unseen-E subset, and +8.1% on the full dataset. These results highlight significant enhancements in both accuracy and robustness over the current state-of-the-art MLLM and RAG frameworks.

cs.AI↗

arXiv2025

Beyond Static Scenes: Camera-controllable Background Generation for Human Motion

In this paper, we investigate the generation of new video backgrounds given a human foreground video, a camera pose, and a reference scene image. This task presents three key challenges. First, the generated background should precisely follow the camera movements corresponding to the human foreground. Second, as the camera shifts in different directions, newly revealed content should appear seamless and natural. Third, objects within the video frame should maintain consistent textures as the camera moves to ensure visual coherence. To address these challenges, we propose DynaScene, a new framework that uses camera poses extracted from the original video as an explicit control to drive background motion. Specifically, we design a multi-task learning paradigm that incorporates auxiliary tasks, namely background outpainting and scene variation, to enhance the realism of the generated backgrounds. Given the scarcity of suitable data, we constructed a large-scale, high-quality dataset tailored for this task, comprising video foregrounds, reference scene images, and corresponding camera poses. This dataset contains 200K video clips, ten times larger than existing real-world human video datasets, providing a significantly richer and more diverse training resource. Project page: https://yaomingshuai.github.io/Beyond-Static-Scenes.github.io/

cs.GR↗

arXiv2025

Squeeze Out Tokens from Sample for Finer-Grained Data Governance

Widely observed data scaling laws, in which error falls off as a power of the training size, demonstrate the diminishing returns of unselective data expansion. Hence, data governance is proposed to downsize datasets through pruning non-informative samples. Yet, isolating the impact of a specific sample on overall model performance is challenging, due to the vast computation required for tryout all sample combinations. Current data governors circumvent this complexity by estimating sample contributions through heuristic-derived scalar scores, thereby discarding low-value ones. Despite thorough sample sieving, retained samples contain substantial undesired tokens intrinsically, underscoring the potential for further compression and purification. In this work, we upgrade data governance from a 'sieving' approach to a 'juicing' one. Instead of scanning for least-flawed samples, our dual-branch DataJuicer applies finer-grained intra-sample governance. It squeezes out informative tokens and boosts image-text alignments. Specifically, the vision branch retains salient image patches and extracts relevant object classes, while the text branch incorporates these classes to enhance captions. Consequently, DataJuicer yields more refined datasets through finer-grained governance. Extensive experiments across datasets demonstrate that DataJuicer significantly outperforms existing DataSieve in image-text retrieval, classification, and dense visual reasoning.

cs.LG↗

arXiv2024

Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text) contrastive paradigm to learn alignment from large-scale messy web data, CLIP faces a serious myopic dilemma, resulting in biases towards monotonous short texts and shallow visual expressivity. To overcome these issues, this paper advances CLIP into one novel holistic paradigm, by updating both diverse data and alignment optimization. To obtain colorful data with low cost, we use image-to-text captioning to generate multi-texts for each image, from multiple perspectives, granularities, and hierarchies. Two gadgets are proposed to encourage textual diversity. To match such (image, multi-texts) pairs, we modify the CLIP image encoder into multi-branch, and propose multi-to-multi contrastive optimization for image-text part-to-part matching. As a result, diverse visual embeddings are learned for each image, bringing good interpretability and generalization. Extensive experiments and ablations across over ten benchmarks indicate that our holistic CLIP significantly outperforms existing myopic CLIP, including image-text retrieval, open-vocabulary classification, and dense visual tasks.

cs.CV↗

arXiv2024

Counterfactual Learning-Driven Representation Disentanglement for Search-Enhanced Recommendation

For recommender systems in internet platforms, search activities provide additional insights into user interest through query-click interactions with items, and are thus widely used for enhancing personalized recommendation. However, these interacted items not only have transferable features matching users' interest helpful for the recommendation domain, but also have features related to users' unique intents in the search domain. Such domain gap of item features is neglected by most current search-enhanced recommendation methods. They directly incorporate these search behaviors into recommendation, and thus introduce partial negative transfer. To address this, we propose a Counterfactual learning-driven representation disentanglement framework for search-enhanced recommendation, based on the common belief that a user would click an item under a query not solely because of the item-query match but also due to the item's query-independent general features (e.g., color or style) that interest the user. These general features exclude the reflection of search-specific intents contained in queries, ensuring a pure match to users' underlying interest to complement recommendation. According to counterfactual thinking, how would user preferences and query match change for items if we removed their query-related features in search, we leverage search queries to construct counterfactual signals to disentangle item representations, isolating only query-independent general features. These representations subsequently enable feature augmentation and data augmentation for the recommendation scenario. Comprehensive experiments on real datasets demonstrate ClardRec is effective in both collaborative filtering and sequential recommendation scenarios.

cs.IR↗

arXiv2024

Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models

Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the model perspective: pruning, distillation, quantization, but completely overlook the data-perspective redundancy. To fill the overlook, this paper pioneers the severity of data redundancy, and designs one plug-and-play Turbo module guided by information degree to prune inefficient tokens from visual or textual data. In pursuit of efficiency-performance trade-offs, information degree takes two crucial factors into consideration: mutual redundancy and semantic value. Concretely, the former evaluates data duplication between sequential tokens; while the latter evaluates each token by its contribution to the overall semantics. As a result, tokens with high information degree carry less redundancy and stronger semantics. For VLMs' calculation, Turbo works as a user-friendly plug-in that sorts data referring to information degree, utilizing only top-level ones to save costs. Its advantages are multifaceted, e.g., being generally compatible to various VLMs across understanding and generation, simple use without re-training and trivial engineering efforts. On multiple VLMs benchmarks, we fully experiment to demonstrate the good acceleration of Turbo, under negligible performance drop.

cs.CV↗

arXiv2024

Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos

Video try-on is a challenging task and has not been well tackled in previous works. The main obstacle lies in preserving the details of the clothing and modeling the coherent motions simultaneously. Faced with those difficulties, we address video try-on by proposing a diffusion-based framework named "Tunnel Try-on." The core idea is excavating a "focus tunnel" in the input video that gives close-up shots around the clothing regions. We zoom in on the region in the tunnel to better preserve the fine details of the clothing. To generate coherent motions, we first leverage the Kalman filter to construct smooth crops in the focus tunnel and inject the position embedding of the tunnel into attention layers to improve the continuity of the generated videos. In addition, we develop an environment encoder to extract the context information outside the tunnels as supplementary cues. Equipped with these techniques, Tunnel Try-on keeps the fine details of the clothing and synthesizes stable and smooth videos. Demonstrating significant advancements, Tunnel Try-on could be regarded as the first attempt toward the commercial-level application of virtual try-on in videos.

cs.CV↗

arXiv2024

Cell Variational Information Bottleneck Network

In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method. Our Cell Variational Information Bottleneck Network is constructed by stacking VIB cells, which generate feature maps with uncertainty. As layers going deeper, the regularization effect will gradually increase, instead of directly adding excessive regular constraints to the output layer of the model as in Deep VIB. Under each VIB cell, the feedforward process learns an independent mean term and an standard deviation term, and predicts the Gaussian distribution based on them. The feedback process is based on reparameterization trick for effective training. This work performs an extensive analysis on MNIST dataset to verify the effectiveness of each VIB cells, and provides an insightful analysis on how the VIB cells affect mutual information. Experiments conducted on CIFAR-10 also prove that our cellVIB is robust against noisy labels during training and against corrupted images during testing. Then, we validate our method on PACS dataset, whose results show that the VIB cells can significantly improve the generalization performance of the basic model. Finally, in a more complex representation learning task, face recognition, our network structure has also achieved very competitive results.

cs.CV↗

arXiv2024

Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment

This paper introduces a novel framework for virtual try-on, termed Wear-Any-Way. Different from previous methods, Wear-Any-Way is a customizable solution. Besides generating high-fidelity results, our method supports users to precisely manipulate the wearing style. To achieve this goal, we first construct a strong pipeline for standard virtual try-on, supporting single/multiple garment try-on and model-to-model settings in complicated scenarios. To make it manipulable, we propose sparse correspondence alignment which involves point-based control to guide the generation for specific locations. With this design, Wear-Any-Way gets state-of-the-art performance for the standard setting and provides a novel interaction form for customizing the wearing style. For instance, it supports users to drag the sleeve to make it rolled up, drag the coat to make it open, and utilize clicks to control the style of tuck, etc. Wear-Any-Way enables more liberated and flexible expressions of the attires, holding profound implications in the fashion industry.

cs.CV↗

arXiv2024

Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentation

Cross-domain CTR (CDCTR) prediction is an important research topic that studies how to leverage meaningful data from a related domain to help CTR prediction in target domain. Most existing CDCTR works design implicit ways to transfer knowledge across domains such as parameter-sharing that regularizes the model training in target domain. More effectively, recent researchers propose explicit techniques to extract user interest knowledge and transfer this knowledge to target domain. However, the proposed method mainly faces two issues: 1) it usually requires a super domain, i.e. an extremely large source domain, to cover most users or items of target domain, and 2) the extracted user interest knowledge is static no matter what the context is in target domain. These limitations motivate us to develop a more flexible and efficient technique to explicitly transfer knowledge. In this work, we propose a cross-domain augmentation network (CDAnet) being able to perform explicit knowledge transfer between two domains. Specifically, CDAnet contains a designed translation network and an augmentation network which are trained sequentially. The translation network computes latent features from two domains and learns meaningful cross-domain knowledge of each input in target domain by using a designed cross-supervised feature translator. Later the augmentation network employs the explicit cross-domain knowledge as augmented information to boost the target domain CTR prediction. Through extensive experiments on two public benchmarks and one industrial production dataset, we show CDAnet can learn meaningful translated features and largely improve the performance of CTR prediction. CDAnet has been conducted online A/B test in image2product retrieval at Taobao app, bringing an absolute 0.11 point CTR improvement, a relative 0.64% deal growth and a relative 1.26% GMV increase.

cs.IR↗