JJJYmmm/Multimodal-RoPEs
Official implement of paper "Revisiting Multimodal Positional Encoding in Vision–Language Models", ICLR 2026
Repositories
JJJYmmm/qwen-mm-plugins-hub
Docs Hub for Qwen MM Plugins
JJJYmmm/cua
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
JJJYmmm/robot.cpp
robot model inference in C/C++
JJJYmmm/llama.cpp
LLM inference in C/C++
JJJYmmm/mlx-vlm
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
JJJYmmm/Qwen-MM-Plugins
Make any agent harness multimodal-native.
JJJYmmm/JJJYmmm
About myself.
JJJYmmm/pi0.cpp
π₀ inference in C/C++, built on top of llama.cpp.
JJJYmmm/Pix2SeqV2-Pytorch
Simple Implementation of Pix2seqV2(multi-task)
JJJYmmm/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
JJJYmmm/Qwen-VL-Skills
dev
JJJYmmm/JJJYmmm.github.io
JJJYmmm/hands-on-modern-rl
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
JJJYmmm/mlx-lm
Run LLMs with MLX
JJJYmmm/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
JJJYmmm/Beingbeyond_D1
This repository provides the BeingBeyond D1 SDK, example Python scripts, and basic guidance for environment setup and common first-time troubleshooting.
JJJYmmm/mindcraft
Minecraft AI with LLMs+Mineflayer
JJJYmmm/Being-H
Being-H is BeingBeyond's family of human-centric embodied foundation models.
JJJYmmm/recipes
Common recipes to run vLLM
JJJYmmm/Qwen3.5
Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.
JJJYmmm/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
JJJYmmm/FireWall-with-Netfliter
基于Netfilter的Linux状态检测防火墙，支持NAT。华中科技大学2023学年网络安全课程设计项目，参考https://github.com/RicheyJang/RJFireWall
JJJYmmm/AssaultCubeHack-1.3.0.2
Self-aiming and perspective tools for Assault Cube ver1.3.0.2
JJJYmmm/Qwen2.5-VL
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
JJJYmmm/TextGenAdvTrack-2025Spring
JJJYmmm/Stealthy-and-Effective-Physical-Adversarial-Attacks-TIFS24
Supplementary Materials for paper: "Stealthy and Effective Physical Adversarial Attacks in Autonomous Driving"
JJJYmmm/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
JJJYmmm/OFA
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework