arXiv subjects

Xianfeng Tan

Publications and source records attributed to Xianfeng Tan.

6 recordsLinked to original sources

arXiv2026

RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation

Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural hallucinations via retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns (e.g., fabric weaves, intricate logos) to become nearly un-sampleable. Naively applying Reinforcement Learning (RL) post-training further triggers Artifact Hacking, where models exploit semantic biases in generic reward models by generating deceptive checkerboard noise. Our key insight is that RL can fundamentally reshape the sampling distribution of flow models---elevating the probability of high-fidelity trajectories under accurate reward guidance---while adversarial regularization prevents exploitation of reward blind spots. Realizing this principle requires three prerequisites: (i)inherent capacity, established through a 27,725-pair high-complexity garment dataset (STGarment-Plus) and a Dual-Image-Stream FLUX architecture upgrade; (ii)perceptive reward, provided by a novel attribute-aware reward model (Garment-RM) trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy; and (iii)hacking prevention, enforced by our Adversarial-Regularized GRPO (AR-GRPO) strategy that integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.

cs.CV↗

arXiv2025

SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation

Generating talking avatar driven by audio remains a significant challenge. Existing methods typically require high computational costs and often lack sufficient facial detail and realism, making them unsuitable for applications that demand high real-time performance and visual quality. Additionally, while some methods can synchronize lip movement, they still face issues with consistency between facial expressions and upper body movement, particularly during silent periods. In this paper, we introduce SyncAnimation, the first NeRF-based method that achieves audio-driven, stable, and real-time generation of speaking avatar by combining generalized audio-to-pose matching and audio-to-expression synchronization. By integrating AudioPose Syncer and AudioEmotion Syncer, SyncAnimation achieves high-precision poses and expression generation, progressively producing audio-synchronized upper body, head, and lip shapes. Furthermore, the High-Synchronization Human Renderer ensures seamless integration of the head and upper body, and achieves audio-sync lip. The project page can be found at https://syncanimation.github.io

cs.CV↗

arXiv2024

RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation

Standard clothing asset generation involves restoring forward-facing flat-lay garment images displayed on a clear background by extracting clothing information from diverse real-world contexts, which presents significant challenges due to highly standardized structure sampling distributions and clothing semantic absence in complex scenarios. Existing models have limited spatial perception, often exhibiting structural hallucinations and texture distortion in this high-specification generative task. To address this issue, we propose a novel Retrieval-Augmented Generation (RAG) framework, termed RAGDiffusion, to enhance structure determinacy and mitigate hallucinations by assimilating knowledge from language models and external databases. RAGDiffusion consists of two processes: (1) Retrieval-based structure aggregation, which employs contrastive learning and a Structure Locally Linear Embedding (SLLE) to derive global structure and spatial landmarks, providing both soft and hard guidance to counteract structural ambiguities; and (2) Omni-level faithful garment generation, which introduces a coarse-to-fine texture alignment that ensures fidelity in pattern and detail components within the diffusing. Extensive experiments on challenging real-world datasets demonstrate that RAGDiffusion synthesizes structurally and texture-faithful clothing assets with significant performance improvements, representing a pioneering effort in high-specification faithful generation with RAG to confront intrinsic hallucinations and enhance fidelity.

cs.CV↗

arXiv2023

Cold & Warm Net: Addressing Cold-Start Users in Recommender Systems

Cold-start recommendation is one of the major challenges faced by recommender systems (RS). Herein, we focus on the user cold-start problem. Recently, methods utilizing side information or meta-learning have been used to model cold-start users. However, it is difficult to deploy these methods to industrial RS. There has not been much research that pays attention to the user cold-start problem in the matching stage. In this paper, we propose Cold & Warm Net based on expert models who are responsible for modeling cold-start and warm-up users respectively. A gate network is applied to incorporate the results from two experts. Furthermore, dynamic knowledge distillation acting as a teacher selector is introduced to assist experts in better learning user representation. With comprehensive mutual information, features highly relevant to user behavior are selected for the bias net which explicitly models user behavior bias. Finally, we evaluate our Cold & Warm Net on public datasets in comparison to models commonly applied in the matching stage and it outperforms other models on all user types. The proposed model has also been deployed on an industrial short video platform and achieves a significant increase in app dwell time and user retention rate.

cs.IR↗

arXiv2022

Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems

Recommender System (RS) is an important online application that affects billions of users every day. The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL) that predicts various user feedback, i.e., clicks, likes, sharings, and a Multi-Task Fusion model (MTF) that combines the multi-task outputs into one final ranking score with respect to user satisfaction. There has not been much research on the fusion model while it has great impact on the final recommendation as the last crucial process of the ranking. To optimize long-term user satisfaction rather than obtain instant returns greedily, we formulate MTF task as Markov Decision Process (MDP) within a recommendation session and propose a Batch Reinforcement Learning (RL) based Multi-Task Fusion framework (BatchRL-MTF) that includes a Batch RL framework and an online exploration. The former exploits Batch RL to learn an optimal recommendation policy from the fixed batch data offline for long-term user satisfaction, while the latter explores potential high-value actions online to break through the local optimal dilemma. With a comprehensive investigation on user behaviors, we model the user satisfaction reward with subtle heuristics from two aspects of user stickiness and user activeness. Finally, we conduct extensive experiments on a billion-sample level real-world dataset to show the effectiveness of our model. We propose a conservative offline policy estimator (Conservative-OPEstimator) to test our model offline. Furthermore, we take online experiments in a real recommendation environment to compare performance of different models. As one of few Batch RL researches applied in MTF task successfully, our model has also been deployed on a large-scale industrial short video platform, serving hundreds of millions of users.

cs.IR↗

arXiv2019

Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionary multi-tasking, or multi-factorial optimization, is an emerging subfield of multi-task optimization, which integrates evolutionary computation and multi-task learning. This paper proposes a novel and easy-to-implement multi-tasking genetic algorithm (MTGA), which copes well with significantly different optimization tasks by estimating and using the bias among them. Comparative studies with eight state-of-the-art single- and multi-task approaches in the literature on nine benchmarks demonstrated that on average the MTGA outperformed all of them, and had lower computational cost than six of them. Based on the MTGA, a simultaneous optimization strategy for fuzzy system design is also proposed. Experiments on simultaneous optimization of type-1 and interval type-2 fuzzy logic controllers for couple-tank water level control demonstrated that the MTGA can find better fuzzy logic controllers than other approaches.

cs.NE↗