← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonMIV-XJTU/JanusVLN

JanusVLN

[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"

50.9/100
★ 502Forks: 35
View on GitHub →Homepage →
Loading report...

Similar Projects

LLaVA-OneVision-1.5

52

Fully Open Framework for Democratized Multimodal Training

Python★ 757

vllm-mlx

60

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.

Python★ 531

langchain

94

The agent engineering platform

Python★ 128.7K

open-webui

94

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Python★ 126.3K
← Back to List