"VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking"

QeRL enables RL for 32B LLMs on a single H100 GPU.

Agent Git: Agent Version Control, Open-Branching, and Reinforcement Learning MDP for Agentic AI. A Standalone Agentic AI Infrastructure Layer for LangGraph Ecosystems

Automatic Video Generation from Scientific Papers

Pantheon-CLI, our first release of PantheonOS, the AgentOS that re-imagines Science

A Scientific Multimodal Foundation Model

Nano-consistent-150k

Offical implementation of "SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection"

This is the implement of the paper "RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models"

Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Being-VL-0.5: Unified Multimodal Understanding via Byte-Pair Visual Encoding

Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs"

H-Net: Hierarchical Network with Dynamic Chunking

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

The official implementation of "ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning"

Official code repo for our work "Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models"

RS-Agent: An LLM-driven Remote Sensing Intelligent Agent

ThinkGeo is a Comprehensive Benchmark to evaluate Tool-Augmented Agents for Remote Sensing Tasks

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Open-source unified multimodal model

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

[ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models'.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration

中文nlp解决方案(大模型、数据、模型、训练、推理)