AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Follow builders, not influencers.

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

Use Claude Code, Codex and Pi for free from your terminal, app, IDE, or phone like OpenClaw (voice supported)

DySCO: Dynamic Attention-Scaling Decoding for Long-Context LMs

⏰ AI conference deadline countdowns

Tongyi Deep Research, the Leading Open-source Deep Research Agent

[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)

🚢 Data Toolkit for Sailor Language Models

[ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

A curated list of 120+ LLM libraries category wise.

Fully open reproduction of DeepSeek-R1

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Retrieval and Retrieval-augmented LLMs

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Ongoing research training transformer models at scale

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Inference code for Llama models

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).

Making large AI models cheaper, faster and more accessible

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Siamese and triplet networks with online pair/triplet mining in PyTorch

LightSeq: A High Performance Library for Sequence Processing and Generation

Soft-Masked Bert 复现论文:https://arxiv.org/pdf/2005.07421.pdf

Acceptance rates for the major AI conferences