C inference runtimes for language models on CPU-only systems.

Implementation of BDH-CQ: In-Context Learning with Recurrent Latent Reasoning, proposed by Pathway Research

Independent research fork of FoSp (AAAI 2024), adding Colab workflows, DSA regularization, and lightweight early-smoke segmentation experiments.

Transformer-based Algorithm-Implicit Learner

Benchmarking and Learning Generalist Embeddings for Tabular Understanding

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

A benchmark for evaluating audio encoders on various audio tasks.

This project provides a benchmark suite for evaluating the abilities of various models to perform tasks over tabular data, such as finding similar tables/columns/rows, perform entity matching, or c…

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。

An MCP server for interacting with Google Colab

Systematizing Unified Multimodal In-Context Learning through a Capability-Oriented Taxonomy

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Next-gen Foundation Model for Embodied AI

Benchmarking general decision-making with open & random worlds

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Experimenting Heuristic Learning with ImageNet

Browser-based real-time VJ engine that turns live audio and sound files into reactive visuals.

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

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

A new dataset that includes long audio, captions of local audio events, and temporal boundaries

Please also check https://github.com/line/castella

Official implementation of Vector-ICL: In-context Learning with Continuous Vector Representations (ICLR 2025)

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀