Lists (2)
Sort Name ascending (A-Z)
Stars
EAT: Evolving Agent Teams (NeurIPS'26). A supervisor agent evolves teams of coding agents for long-running optimization tasks.
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
PFCCLab / supersonic-moe
Forked from Dao-AILab/sonic-moeAn extended sonic-moe implementation, with FP8 support fully developed by agents
Runnable RL recipes (miles, slime, NeMo-RL) and the cwtrain library for training against CoreWeave Dedicated Inference with RL Rollouts.
A Reinforcement Learning (RL) simulation environment built for training and evaluating defensive and offensive autonomous models on simulated and emulated networks, with a focus on modularity and c…
Official code for LoRA-RLPO and LoRA-RLMO: geometry-preserving orthonormal LoRA initialization for stable RLVR (DAPO/GRPO).
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
Official implementation of iSDFT: information-proximal on-policy self-distillation for continual learning in LLMs. Training code, checkpoints, and evaluation results.
📄Score Centering Stabilizes Off-policy Reinforcement Learning
Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub
From Task-based to Instruction-based Automated Log Analysis
Must-read papers and blogs about parametric knowledge mechanism in LLMs.
A curated list of papers and selected technical blogs on Loop Models.
This is the code repository of paper "SFT Conflicts, RL Coexists"
Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.
AlphaGo Moment for Model Architecture Discovery.
A pi extension with a single tool: execute, running TypeScript in a persistent Bun evaluator. Files, shell, and subagents are expressed as code rather than as more tools.
[NeurIPS 2026] Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.
LeanDojo-v2 is an end-to-end framework for training, evaluating, and deploying AI-assisted theorem provers for Lean 4.
🧘 BLISS – a Benchmark for Language Induction from Small Sets