Alternatives and similar repositories for RL-with-Cold-Start

Users that are interested in RL-with-Cold-Start are comparing it to the libraries listed below

• Liuziyu77 / MIA-DPO
  Official implement of MIA-DPO
  ☆59Updated 5 months ago
• OpenGVLab / V2PE
  [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
  ☆51Updated 7 months ago
• beichenzbc / BoostStep
  official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"
  ☆36Updated 5 months ago
• kxfan2002 / SophiaVL-R1
  SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
  ☆57Updated 3 weeks ago
• MikeWangWZHL / dymu
  ☆16Updated 2 months ago
• GAIR-NLP / thinking-with-generated-images
  Doodling our way to AGI ✏️ 🖼️ 🧠
  ☆72Updated last month
• njucckevin / MM-Self-Improve
  A Self-Training Framework for Vision-Language Reasoning
  ☆80Updated 5 months ago
• MME-Benchmarks / MME-Unify
  MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models
  ☆41Updated 3 months ago
• xjtupanda / Sparrow
  Repo for paper "T2Vid: Translating Long Text into Multi-Image is the Catalyst for Video-LLMs"
  ☆49Updated 4 months ago
• Mr-Loevan / FAST
  Fast-Slow Thinking for Large Vision-Language Model Reasoning
  ☆16Updated 2 months ago
• ggg0919 / cantor
  ☆86Updated last year
• waltonfuture / MM-UPT
  Unsupervised GRPO
  ☆39Updated last month
• Hon-Wong / ByteVideoLLM
  [ICCV 2025] Dynamic-VLM
  ☆23Updated 7 months ago
• NUS-TRAIL / NoisyRollout
  NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
  ☆78Updated last month
• ModalMinds / MM-PRM
  MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
  ☆24Updated last month
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆105Updated last month
• MikeWangWZHL / PAPO
  Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"
  ☆60Updated this week
• ding523 / Curr_REFT
  ☆64Updated last month
• RifleZhang / LLaVA-Reasoner-DPO
  ☆84Updated 6 months ago
• foundation-multimodal-models / CAL
  [NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
  ☆58Updated 9 months ago
• ekonwang / VisuoThink
  [Arxiv Paper 2504.09130]: VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
  ☆20Updated 2 months ago
• OpenGVLab / MMIU
  [ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
  ☆83Updated 10 months ago
• kokolerk / TON
  Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
  ☆40Updated this week
• Liuziyu77 / MMDU
  Official repository of MMDU dataset
  ☆92Updated 9 months ago
• gyhdog99 / RACRO2
  Official PyTorch implementation of RACRO (https://www.arxiv.org/abs/2506.04559)
  ☆15Updated 2 weeks ago
• LanceZPF / OpenING
  Official Implementation of OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
  ☆26Updated 2 weeks ago
• chenllliang / G1
  G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
  ☆72Updated 2 months ago
• EvolvingLMMs-Lab / VideoMMMU
  ☆50Updated 3 weeks ago
• bigai-nlco / VideoLLaMB
  [ICCV 2025] Official Repository of VideoLLaMB: Long Video Understanding with Recurrent Memory Bridges
  ☆71Updated 4 months ago
• arctanxarc / MC-LLaVA
  Official implementation of MC-LLaVA.
  ☆32Updated last month