UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

Code for RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Next Forcing: World Action Modeling with Multi-Chunk Prediction (MCP)

Visualize, query, and stream to train on multimodal robotics data.

from vibe coding to agentic engineering - practice makes claude perfect

[CVPR 2026] Official implementation of "GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation"

[RSS 2026] Ordered Action Tokenization

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

Academic Research Skills for Claude Code: research → write → review → revise → finalize

[CVPR 2026 Oral] VGGT Omega

Official implementation of AsymFlow, pi-Flow, GMFlow

My learning notes for ML SYS.

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

Official, Anthropic-managed directory of high quality Claude Code Plugins.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

NanoBanana PPT Skills 基于 AI 自动生成高质量 PPT 图片和视频的强大工具，支持智能转场和交互式播放

Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation context directly in the editor.