pranonrahman / ChartSumm
ChartSum is a large scale benchmark for automatic chart to text summarization
☆11Updated last year
Alternatives and similar repositories for ChartSumm:
Users that are interested in ChartSumm are comparing it to the libraries listed below
- ☆109Updated 7 months ago
- ☆67Updated 6 months ago
- [NAACL 2024] MMC: Advancing Multimodal Chart Understanding with LLM Instruction Tuning☆95Updated last month
- ☆11Updated last year
- Dataset introduced in PlotQA: Reasoning over Scientific Plots☆73Updated last year
- MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning☆135Updated last year
- The proposed simulated dataset consisting of 9,536 charts and associated data annotations in CSV format.☆22Updated last year
- ☆21Updated 7 months ago
- [ACL 2024] ChartAssistant is a chart-based vision-language model for universal chart comprehension and reasoning.☆113Updated 5 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆66Updated 3 months ago
- M-HalDetect Dataset Release☆22Updated last year
- ☆39Updated last year
- [EMNLP 2022] TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data☆17Updated last year
- ☆17Updated 3 months ago
- A Self-Training Framework for Vision-Language Reasoning☆66Updated last month
- ☆60Updated last year
- Code for Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models☆78Updated 8 months ago
- ☆62Updated 8 months ago
- [AAAI 2025]Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning☆30Updated 5 months ago
- Paper collections of multi-modal LLM for Math/STEM/Code.☆77Updated last week
- ☆179Updated 7 months ago
- M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆55Updated 2 months ago
- The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''☆199Updated 11 months ago
- ☆13Updated 2 months ago
- EMNLP2023 - InfoSeek: A New VQA Benchmark focus on Visual Info-Seeking Questions☆18Updated 9 months ago
- ☆14Updated last year
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆33Updated 10 months ago
- ☆10Updated 8 months ago
- SciCap Dataset☆53Updated 3 years ago