VLM
Open Source
LLaVA-OneVision 2.0
A full-frame-rate vision-language model that unifies image and video understanding.
- Multimodal Large Models
Glint-VL-Video-8B
A vision-language model for long-video understanding
Glint-VL-Video-8B is the first large video-understanding model to use codec streams as its visual unit. Built on our independently developed and open-source LLaVA-OneVision stack, it identifies key events, locates time ranges, and extracts evidence from long videos for review, retrieval, and process analysis.
Open-source foundation：LLaVA-OneVision 2.0
Open research and proprietary models form one foundation
Research spans VLMs, visual foundations, multimodal embeddings, multimodal RAG, face recognition, and 3D vision. Choose a direction to view its code, papers, and project pages.
VLM
Open Source
LLaVA-OneVision-1.5
A vision-language model training framework with fully open training and evaluation datasets, training code, and model weights.
- Multimodal Large Models
VLM
AAAI 2026
ViCToR
A visual-token reconstruction approach that improves multimodal model performance on fine-grained visual understanding, chart interpretation, and document parsing.
- Multimodal LLMs
VLM
CVPR 2026
StreamingRVOS
An LLM-based streaming referring video segmentation method for real-time, continuous segmentation of referred objects in long videos, suitable for video analytics and robotic perception.
- Streaming Video Segmentation
- Referring Segmentation
Visual Foundations
Open Source
MVT v2.0 (OneVision-Encoder)
The first codec-stream-based vision encoder to unify image and video understanding tasks.
- Vision Encoder
- Image Understanding
- Video Understanding
Visual Foundations
ICCV 2025Open Source
MVT v1.5 (RICE)
A region-level supervised visual representation learning method that delivers clear gains in segmentation, dense detection, and visual perception for multimodal large language models.
- Vision Foundation Model
Visual Foundations
ECCV 2024Open Source
MVT v1.1 (MLCD)
A general-purpose visual foundation model trained with a multi-label signal margin loss for visual representation learning.
- Vision Foundation Model
Visual Foundations
ICLR 2023
MVT v1.0 (Unicom)
A universal and compact representation learning framework for image retrieval and the first work to introduce margin-based learning to ViTs.
- Image Retrieval
- Representation Learning
- Weakly Supervised Learning
Visual Foundations
NeurIPS 2025
UniViT
A vision encoder that unifies image and video understanding tasks, advancing toward a unified ViT foundation model.
- Vision Encoder
- Image Understanding
- Video Understanding
Multimodal Embeddings
AAAI 2026Open Source
UniME-V2
A universal multimodal embedding model that uses an MLLM-as-a-Judge mechanism to mine hard negatives with soft matching scores and achieve finer-grained cross-modal semantic alignment.
- Multimodal Embedding
Multimodal Embeddings
ACM MM 2025Open Source
UniME V1
A universal embedding learning framework for multimodal large language models that combines two-stage text discriminative knowledge distillation and contrastive learning while mitigating false negatives.
- Multimodal Embedding
Multimodal Embeddings
ACM MM 2025Open Source
RealSyn
A multimodal interleaved document transformation paradigm that combines real and synthetic text to build large-scale interleaved image-text training datasets.
- Multimodal Pretraining
- Interleaved Image-Text Dataset
Multimodal Embeddings
ACM MM 2025Open Source
DeGLA
An alignment framework that improves compositional understanding in vision-language pretraining through self-distillation and a grounded image-text contrastive loss that mitigates catastrophic forgetting.
- Vision-Language Pretraining
- Compositional Understanding
- Global-Local Alignment
Multimodal Embeddings
ICCV 2023Open Source
ALIP
A vision-language pretraining method that adaptively combines original and generated captions to improve the robustness and generalization of CLIP-like models on noisy data and zero-shot retrieval tasks.
- Vision-Language Pretraining
Multimodal Embeddings
EMNLP 2024Open Source
RWKV-CLIP
A vision-language representation model built on the post-Transformer RWKV architecture, combining the parallel training efficiency of Transformers with the efficient inference of RNNs.
- Vision-Language Pretraining
- RWKV
- Efficient Inference
Multimodal Embeddings
AAAI 2025
CLIP-CID
An efficient CLIP distillation method that applies image-semantic balancing to reduce transfer bias and transfer knowledge from large vision-language models to smaller models.
- Vision-Language Pretraining
- Knowledge Distillation
Multimodal Embeddings
EMNLP 2025Open Source
GA-DMS
A cross-modal alignment framework for text-based person retrieval, applicable to security monitoring and cross-camera person search.
- Text-Based Person Retrieval
Multimodal RAG
COLM 2026Open Source
ComDoc
A comprehensive benchmark for document retrieval-augmented generation (RAG) systems, with realistic test sets and evaluation protocols for assessing document-level retrieval and generation quality.
- Multimodal Document RAG
- Benchmark Evaluation
Face Recognition
CVPR 2022
PartialFC
An efficient training method for large-scale face recognition that can be applied directly to face recognition model training with hundreds of millions of identities.
- Face Recognition
- Large-Scale Training
Face Recognition
ICML 2026
FR-IQ
A validation-free metric for estimating the intrinsic potential of face recognition datasets. It predicts whether a dataset can produce a high-performance model without full training, reducing the cost of large-scale face data cleaning and selection.
- Face Recognition
- Intrinsic Data Quality Estimation
3D Vision
SIGGRAPH Asia 2024Open Source
GVHMR
A world-grounded human motion recovery method based on gravity-view coordinates. It robustly recovers 3D human motion with absolute ground position from monocular video for motion capture, AR/VR, and related applications.
- Monocular 3D Human Reconstruction
3D Vision
ICCV 2025Open Source
MotionStreamer
A streaming motion generation framework based on a diffusion autoregressive model for real-time motion generation in games, animation, and digital humans.
- Human Motion Generation
- Streaming Generation
- Diffusion Model
3D Vision
ICCV 2025Open Source
UniVerse
A unified framework that uses scene priors from video diffusion models for radiance field reconstruction, improving robust 3D reconstruction from sparse views for AR/VR content creation and digital twins.
- 3D Reconstruction
- Video Diffusion
- Neural Rendering
3D Vision
ICCV 2025Open Source
Motion-2-to-3
A method that uses 2D motion data to improve 3D motion generation, producing diverse 3D motions from 2D-only annotations while reducing the cost of collecting 3D motion data.
- 3D Motion Generation
- Multi-View Synthesis
3D Vision
CVPR 2026
Mocap-2-to-3
A framework that uses 2D data pretraining for monocular multi-view 3D motion recovery, reducing reliance on expensive motion-capture equipment.
- Monocular 3D Motion Recovery
- Motion Capture
Full-stack model fine-tuning services, tailored to your business
The LLaVA CommunityThe LLaVA community is a major force for innovation in open-source multimodal AI, advancing the deep integration of visual understanding and large language models. Its key contribution is the development of Visual Instruction Tuning, enabling models not only to recognize image content but also to conduct multi-turn question answering, logical analysis, and task execution across images, documents, and video. By opening model code, training methods, data-construction practices, and evaluation systems, LLaVA has substantially lowered the barrier to multimodal research and application development while establishing an important foundation for continued progress in image understanding, OCR, chart analysis, long-video understanding, and spatial reasoning. Through an open, reproducible, and extensible technical ecosystem, the LLaVA community is accelerating multimodal AI innovation in customer service, content creation, education, industrial inspection, robotics, and other real-world settings. provides a full model-optimization stack spanning foundational training, parameter-efficient fine-tuning, and knowledge distillation, closed by objective evaluation and production deployment. Data stays on site while capability accumulates in the customer model.
Model Training
Build datasets, training recipes, and version baselines around domain data and target tasks, with support for 4B and 8B VLM training.
- Data governance and multimodal annotation
- Training monitoring and checkpoint recovery
- Model versions and experiment records
Model Fine-Tuning
Use SFT, LoRA, and QLoRA to adapt general models to customer tasks, domain knowledge, and output requirements.
- Cost-efficient parameter adaptation
- Private blind tests and A/B comparison
- Controlled quality, cost, and delivery cycle
Model Distillation
Transfer knowledge and business reasoning from larger models into smaller ones while balancing quality, latency, and private deployment cost.
- Distillation for LLMs below 32B
- Quantization, compilation, and inference tuning
- Cloud, private, and edge deployment
Model optimization delivery flow
01 Data PreparationData governance and multimodal annotation. Data stays on site.
02 Model OptimizationTrain / Tune / Distill
03 Evaluate and AlignObjective evaluation, private blind tests, and A/B comparison.
04 Deploy and DeliverProduction deployment to cloud, private, or edge environments. Capability accumulates in the customer model.
Deliver model capability into operations
City governance orchestrates video, image, and multimodal capabilities through algorithms. Finance reshapes operational control with an integrated cloud-edge-device architecture while processing documents locally.
Glint-VL-Video-8B / Glint-VL-SE-8B
Visual Intelligence for City Management
Combines CV and multimodal models around a perception—understanding—analysis—alert—governance workflow, turning distributed visual resources into searchable, analyzable, and actionable business information.
- Video-8B understands long-video events, locates time ranges, and extracts evidence
- SE-8B strengthens critical-event, person, vehicle, and fine-grained attribute recognition
- Cloud-edge collaboration closes the loop from spatiotemporal analysis to proactive risk discovery
Glint-VL-BK-8B
Intelligent Finance
Combines CV and multimodal models with edge computing nodes in a cloud-edge-device architecture, providing unified capabilities for operations, security, internal control, and retail banking while improving efficiency and accelerating digital transformation.
- BK-8B continuously understands branches, vaults, and office buildings
- Connects human behavior, critical events, locations, and supporting evidence
- Completes delivery with a local 32B LLM, OCR, and an AI gateway
Contact us now to build your enterprise model
Tell us about your business scenario, data conditions, and deployment requirements. Our original model team will plan your model fine-tuning, evaluation, and private deployment path.