OpenDFM / MobA
🎮Manipulates mobile phones just like how you would. Official code for "MobA: A Two-Level Agent System for Efficient Mobile Task Automation".
☆13Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for MobA
- Official implementation of the paper "MMInA: Benchmarking Multihop Multimodal Internet Agents"☆38Updated 7 months ago
- Simple Implementation of TinyGPTV in super simple Zeta lego blocks☆15Updated last week
- [NeurIPS 2024] TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration☆17Updated last month
- ☆15Updated 3 months ago
- Pytorch implementation of HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models☆28Updated 8 months ago
- Implementation of the model: "(MC-ViT)" from the paper: "Memory Consolidation Enables Long-Context Video Understanding"☆16Updated last week
- Official implementation of ECCV24 paper: POA☆24Updated 3 months ago
- Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆22Updated last month
- A Framework for Decoupling and Assessing the Capabilities of VLMs☆38Updated 4 months ago
- Code repo for "Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding"☆23Updated 3 months ago
- Lottery Ticket Adaptation☆36Updated last month
- ☆16Updated 3 months ago
- ☆12Updated 2 weeks ago
- ☆13Updated 6 months ago
- MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment☆31Updated 4 months ago
- ☆21Updated last month
- ☆59Updated last month
- ☆12Updated 2 months ago
- Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"☆47Updated last month
- Official Pytorch Implementation of Self-emerging Token Labeling☆30Updated 7 months ago
- ☆35Updated 3 months ago
- MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆17Updated 2 weeks ago
- My personal implementation of the model from "Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities", they haven't rel…☆11Updated 9 months ago
- [EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"☆14Updated last month
- A Data Source for Reasoning Embodied Agents☆19Updated last year
- A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.☆16Updated last month
- This is the implementation of CounterCurate, the data curation pipeline of both physical and semantic counterfactual image-caption pairs.☆17Updated 4 months ago
- SSL Video Representation Learning project☆10Updated 11 months ago
- ☆30Updated this week
- ☆21Updated this week