视觉语言模型

[ICML'25][TPAMI'26] Official implementation of paper "SparseVLM" and "SparseVLM+".

Open & Reproducible Research for Tracking VLAs

[ECCV 2026] Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Archived snapshot of Thinking-with-Visual-Primitives

[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving

[NeurIPS 2025] Official implementation of "RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics"

Foundation models based medical image analysis

[ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

[NeurIPS, 500+ Citations!] Alignment & Safety for multimodal foundation models

Scaling Vision Pre-Training to 4K Resolution

📚 A curated collection of papers and open-source code repositories dedicated to the application of Vision-Language Models (VLMs) for streaming video.

[ICML 2026] GRACE: deployable INT4 VLM via quantization-aware distillation.

Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx: Apple Silicon/MPS.

[ECCV 2024] Embodied Understanding of Driving Scenarios

Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.