16 papers
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Wenxiao Fan, Jingling Fu, Lichen Ma +6
Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences with local objectives. This ove…
Is Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings
Wenxiao Fan, Jingling Fu, Luohang Liu +6
Reasoning-enhanced universal multimodal embeddings (UME) improve heterogeneous retrieval, but plausible rationales do not necessarily produce discriminative rankings. We study this…
PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster
Xiaoan Liu, Lichen Ma, Zipeng Guo +12
Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods either target end-to-end po…
TransAnyText: Translating Arbitrary Text in E-commerce Images via Structured Visual Generation
Xiaoan Liu, Lichen Ma, Zipeng Guo +13
Cross-border e-commerce image translation is essential for global retail, where product images, banners, and detail pages need to be produced in different languages. Existing metho…
Energy-Guided Flow Matching
Haoyang Tong, Yu He, Fang Li +6
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flo…
iFAN: Inference-Aware Learning for Plain Mask Transformers
Fang Li, Yu He, Haoyang Tong +7
Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly…
Match One, Learn with Graph: One-to-Graph Query Collaboration with Backward Sharing for Object Detection
Wenxiao Fan, Jingling Fu, Luohang Liu +8
One-to-one (O2O) matching enables Detection Transformers (DETRs) to perform end-to-end set prediction by assigning each object to a single positive query. However, the strongest cl…
Recompute or Reuse? Diagnosing and Mitigating Textual Shortcuts in VLM Self-Reflection
Wenxiao Fan, Jingling Fu, Fang Li +9
Vision-language models (VLMs) are expected to revise their reasoning when visual evidence changes. Failures to do so are often attributed to insufficient visual attention or contex…
GMO-EDIT: Grounded Multi-Operation Editing for E-Commerce Images
Zipeng Guo, Xiaoan Liu, Lichen Ma +9
Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature poses a dual challenge: mod…
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
Zipeng Guo, Lichen Ma, Yu He +4
End-to-end pixel-space diffusion models bypass the lossy compression of Latent Diffusion Models (LDMs) but struggle to jointly model low-frequency semantics and high-frequency sign…
HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
Yu He, Lichen Ma, Zipeng Guo +5
Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental "granularity dilemma": capturing global semantics favors…
LiWi: Layering in the Wild
Yu He, Fang Li, Haoyang Tong +7
Recent advances in generative models have empowered impressive layered image generation, yet their success is largely confined to graphic design domains. The layering of in-the-wil…
FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
Lichen Ma, Zipeng Guo, Yu He +5
To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged as a compelling end-to-end pa…
Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
Yu He, Ting Zhu, Yichun Liu +6
Recent research work on fashion outfit generation focuses on promoting visual consistency of garments by leveraging key information from reference image and text prompt. However, t…
RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning
Zipeng Guo, Lichen Ma, Xiaolong Fu +13
In web data, product images are central to boosting user engagement and advertising efficacy on e-commerce platforms, yet the intrusive elements such as watermarks and promotional…
Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
Xiaolong Fu, Lichen Ma, Zipeng Guo +9
The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these ga…