Alternatives and similar repositories for FlexAttention

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

• yuecao0119 / MMInstruct
  [SCIS 2024] The official implementation of the paper "MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Di…
  ☆61Updated last year
• Hon-Wong / ByteVideoLLM
  [ICCV 2025] Dynamic-VLM
  ☆28Updated last year
• hasanar1f / HiRED
  [AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Visio…
  ☆44Updated 8 months ago
• yuecao0119 / MMFuser
  The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". …
  ☆62Updated last year
• alibaba / conv-llava
  ☆124Updated last year
• locuslab / llava-token-compression
  ☆46Updated last year
• Yangyi-Chen / SOLO
  [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"
  ☆147Updated last year
• Haochen-Wang409 / TreeVGR
  Official implementation of "Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology"
  ☆72Updated 2 months ago
• JieShibo / MemVP
  [ICML 2024] Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
  ☆50Updated last year
• iancovert / locality-alignment
  ☆54Updated 11 months ago
• palchenli / VL-Instruction-Tuning
  ☆92Updated 2 years ago
• techmonsterwang / iLLaMA
  Adapting LLaMA Decoder to Vision Transformer
  ☆30Updated last year
• XMUDeepLIT / AVG-LLaVA
  Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"
  ☆33Updated last year
• MME-Benchmarks / MME-RealWorld
  ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?
  ☆150Updated 2 months ago
• OpenGVLab / TPO
  Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
  ☆64Updated 5 months ago
• SliMM-X / CoMP-MM
  Official repository of "CoMP: Continual Multimodal Pre-training for Vision Foundation Models"
  ☆40Updated 9 months ago
• core-mm / core-mm
  ☆17Updated last year
• TempleX98 / MoVA
  [NeurIPS 2024] MoVA: Adapting Mixture of Vision Experts to Multimodal Context
  ☆168Updated last year
• EvolvingLMMs-Lab / OpenMMReasoner
  Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
  ☆132Updated 3 weeks ago
• Shengcao-Cao / groundLMM
  Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision
  ☆44Updated 2 months ago
• FreedomIntelligence / TRIM
  We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their…
  ☆20Updated this week
• waltonfuture / MM-UPT
  [NeurIPS 2025] Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO
  ☆73Updated 2 months ago
• RifleZhang / LLaVA-Reasoner-DPO
  ☆109Updated last year
• HJYao00 / DenseConnector
  【NeurIPS 2024】Dense Connector for MLLMs
  ☆180Updated last year
• InternScience / MME-Reasoning
  Official Repository: A Comprehensive Benchmark for Logical Reasoning in MLLMs
  ☆45Updated 6 months ago
• LaVi-Lab / Visual-Table
  [EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"
  ☆20Updated last year
• OpenGVLab / MMIU
  [ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
  ☆92Updated last year
• maifoundations / Visionary-R1
  Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
  ☆43Updated 6 months ago
• YuxiXie / V-DPO
  Preference Learning for LLaVA
  ☆58Updated last year
• RUCAIBox / Virgo
  Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*
  ☆109Updated 7 months ago