360 AI Research — Multimodal AI Research and Innovation

Multimodal Understanding

Multimodal Understanding

Fine-Grained Image–Text Retrieval

Fine-Grained

A next-generation vision-language model for fine-grained cross-modal retrieval. It addresses the bag-of-words effect and imprecise local alignment found in CLIP-derived models, surpasses SigLIP 2 and MetaCLIP 2, and supports both English and Chinese.

High-Precision Multimodal RAG

Multimodal RAG

A multimodal embedding model for high-precision retrieval across text, images, video, and mixed-modality inputs. It helps enterprise document understanding, retrieval, and question answering move beyond OCR plus plain text to represent multimodal information directly.

Multimodal VLA

Agent-Ready

Built for web and computer automation, this capability helps foundation models generalize to enterprise applications. It enables model-driven interaction with internal web systems without relying on brittle DOM identifiers and improves as operational experience accumulates.

Multimodal Generation

Multimodal Generation

High-Consistency Makeup Transfer

Controllable Image

High-fidelity makeup transfer for virtual try-on, ecommerce, and avatar workflows while preserving subject identity, with reusable template-based experiences.

Controllable Image Generation

Layer Editing

Precise layout control for complex, multi-subject scenes and layer-aware generation for professional creative workflows.

Controllable Image Editing

Video Creation

Decompose existing images into editable layers or extract a selected object as its own layer, giving professional creators precise control instead of unpredictable trial and error.

Controllable Video Generation and Editing

Controllable Image

Control the placement of multiple subjects within a shot and decompose existing video into editable element layers for professional post-production.

Tech Blog

Tech Blog

English translation pending — Article 06a6f4f8-9cde-4a44-a908-027c18680c7c

English translation pending — Article 06a6f4f8-9cde-4a44-a908-027c18680c7c

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-08-27

English translation pending — Article aca1d907-6968-4a0e-a8e6-f4196b15baf6

English translation pending — Article aca1d907-6968-4a0e-a8e6-f4196b15baf6

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-08-03

English translation pending — Article bf8ba3a0-da94-41b1-8240-fb36abb83f00

English translation pending — Article bf8ba3a0-da94-41b1-8240-fb36abb83f00

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-06-30

English translation pending — Article abeda5bd-6aae-4c34-b5f7-e284c4655eda

English translation pending — Article abeda5bd-6aae-4c34-b5f7-e284c4655eda

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-06-16

English translation pending — Article 2094b39f-ea7a-4673-abbd-ebe00cabc218

English translation pending — Article 2094b39f-ea7a-4673-abbd-ebe00cabc218

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-06-02

English translation pending — Article 3557a26c-4bf4-44d6-b07e-9ab3e03197b6

English translation pending — Article 3557a26c-4bf4-44d6-b07e-9ab3e03197b6

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-05-06

English translation pending — Article 26fd5d52-aad1-4ffa-9d0e-9ebdd9831560

English translation pending — Article 26fd5d52-aad1-4ffa-9d0e-9ebdd9831560

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-04-07

English translation pending — Article e2480d4f-5bf7-47e0-8cdb-31450474ce3d

English translation pending — Article e2480d4f-5bf7-47e0-8cdb-31450474ce3d

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2026-01-27

English translation pending — Article 6953ab7db3a45c5cc2a7c9d7

English translation pending — Article 6953ab7db3a45c5cc2a7c9d7

This published article is awaiting reviewed English localization.

360 AI Research Editorial Team · 2025-12-30

FG-CLIP 2 in a Smart Elder-Care Monitoring Course Project

FG-CLIP 2 in a Smart Elder-Care Monitoring Course Project

A student project shows how fine-grained vision–language understanding can support practical, multilingual monitoring scenarios.

360 AI Research · 2025-12-10

FG-CLIP 2: Fine-Grained Bilingual Vision–Language Understanding

FG-CLIP 2: Fine-Grained Bilingual Vision–Language Understanding

FG-CLIP 2 advances fine-grained image–text alignment with dynamic-resolution training, a redesigned objective, and stronger Chinese data.

Dawei Leng, Chunyu Xie, and Bin Wang · 2025-11-06

RzenEmbed: Multimodal Retrieval for Enterprise Documents

RzenEmbed: Multimodal Retrieval for Enterprise Documents

RzenEmbed creates unified semantic embeddings for text, images, video, and mixed-layout documents in enterprise retrieval and RAG.

Dawei Leng and Weijian Jian · 2025-09-24

Research Highlights

Selected Publications

FG-CLIP: Fine-Grained Visual and Textual Alignment

FG-CLIP: Fine-Grained Visual and Textual Alignment

A next-generation cross-modal VLM built for fine-grained understanding

RefVTON: Person-to-Person Try-on with Additional Unpaired Visual Reference

RefVTON: Person-to-Person Try-on with Additional Unpaired Visual Reference

End-to-end virtual try-on without complex human-detection preprocessing

LMM-Det: Make Large Multimodal Models Excel in Object Detection

LMM-Det: Make Large Multimodal Models Excel in Object Detection

Native object detection for LMMs without an external detector

PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models

PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models

A unified model that plans object layouts and generates images

IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities

IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities

A ControlNet-inspired adaptor architecture for multimodal LLMs

Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities

Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communities

Native Chinese text-to-image generation compatible with the Stable Diffusion ecosystem

Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task

Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task

An inference-efficient architecture for Text2Any tasks

HiCo: Hierarchical Controllable Diffusion Model for Layout-to-Image Generation

HiCo: Hierarchical Controllable Diffusion Model for Layout-to-Image Generation

Layout-controllable image generation for professional creative workflows