Lists (13)
Stars
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
a multi node frp webui and for https://github.com/fatedier/frp server and client management, which makes this project a Cloudflare Tunnel/Tailscale Funnel/Ngork platform and agent open source alter…
Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"
Official code for "Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models"
Official Implementation of "PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations"
🔥 [ICLR 2026] Benchmark for robotic tabletop manipulation memory-intensive tasks
high-performance inference and serving library for interactive autoregressive video and world models
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Swift community driven package for OpenAI public API
[ICML 2026] Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
[RSS 2026] Mimic Intent, Not Just Trajectories (MINT) official implementation
Reshaping Action Error Distributions for Reliable Vision-Language-Action Models
XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios
A modern Android to-do app built with Kotlin and Jetpack Compose.
Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.
Mastering Diverse Domains through World Models
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
[RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Notion-style WYSIWYG editor with AI-powered autocompletion.
26m function call model that runs on incredibly small devices
A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI.