Alternatives and similar repositories for AHN

Users that are interested in AHN are comparing it to the libraries listed below

• Zacks917 / AutoDeco
  ☆62Updated last month
• yannqi / R-4B
  The official repository of "R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Integration"
  ☆127Updated 3 months ago
• MiniMax-AI / One-RL-to-See-Them-All
  The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning
  ☆328Updated 6 months ago
• snu-mllab / KVzip
  [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
  ☆155Updated 2 weeks ago
• SimonAytes / SoT
  Official code repository for Sketch-of-Thought (SoT)
  ☆128Updated 7 months ago
• MiniMax-AI / SynLogic
  [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  ☆187Updated 5 months ago
• MetaStone-AI / MetaStone-S1
  The open-source code of MetaStone-S1.
  ☆107Updated 4 months ago
• Tencent / llm.hunyuan.T1
  ☆85Updated 8 months ago
• bigai-nlco / TokenSwift
  [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  ☆118Updated 6 months ago
• Tencent / digitalhuman
  ☆185Updated this week
• FreedomIntelligence / LongLLaVA
  LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
  ☆211Updated 11 months ago
• efficientscaling / Z1
  [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆67Updated 8 months ago
• MiroMindAI / MiroTrain
  MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.
  ☆99Updated 3 months ago
• bin123apple / InfantAgent
  [NeurIPS 2025] A multimodal agent that can interact with its own PC in a multimodal manner.
  ☆34Updated last month
• baichuan-inc / Baichuan-Omni-1.5
  ☆182Updated 10 months ago
• opendatalab / REST
  ☆32Updated 4 months ago
• inclusionAI / dFactory
  Easy and Efficient dLLM Fine-Tuning
  ☆139Updated last week
• inclusionAI / Ring-V2
  Ring-V2 is a reasoning MoE LLM provided and open-sourced by InclusionAI.
  ☆81Updated last month
• MiroMindAI / MiroMind-M1
  MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.
  ☆245Updated 4 months ago
• SalesforceAIResearch / LATTE
  ☆68Updated 2 months ago
• TergelMunkhbat / concise-reasoning
  Code for paper called Self-Training Elicits Concise Reasoning in Large Language Models
  ☆42Updated 7 months ago
• VainF / Thinkless
  [NeurIPS 2025] Thinkless: LLM Learns When to Think
  ☆245Updated 2 months ago
• OpenGVLab / SDLM
  Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation lengt…
  ☆76Updated last week
• xlang-ai / OSWorld-G
  [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis
  ☆134Updated last month
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆100Updated 3 months ago
• We-Math / We-Math
  The code and data of We-Math, accepted by ACL 2025 main conference.
  ☆133Updated last month
• zhijie-group / SIFT
  SIFT: Grounding LLM Reasoning in Contexts via Stickers
  ☆57Updated 9 months ago
• si0wang / ThinkLite-VL
  ☆105Updated 6 months ago
• thu-coai / Glyph
  Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
  ☆522Updated last month
• OpenIXCLab / CODA
  CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
  ☆32Updated 3 months ago