Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning? An Extensive Investigation into the Capabilities and Limitations of LVLMs
Paper • 2406.00257 • Published
University of Alberta
university
Verified
AI & ML interests
None defined yet.
Recent Activity
Papers
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
tafseer-nayeem
authored 2
papers 11 days ago
yongchanghao
submitted a
paper to Daily Papers 12 days ago
LiyaoJiang
authored a
paper about 2 months ago
LiyaoJiang
submitted a
paper to Daily Papers about 2 months ago
montaserm
authored 3
papers about 2 months ago
iamniudi
authored 12
papers 3 months ago
Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
Paper • 2002.00748 • Published • 1
Neural Architecture Search For Keyword Spotting
Paper • 2009.00165 • Published
Instruction Fusion: Advancing Prompt Evolution through Hybridization
Paper • 2312.15692 • Published • 2
GOAt: Explaining Graph Neural Networks via Graph Output Attribution
Paper • 2401.14578 • Published • 1
FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting
Paper • 2408.11706 • Published • 7
PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation
Paper • 2412.14283 • Published • 3
Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
Paper • 2412.14628 • Published
Building Optimal Neural Architectures using Interpretable Knowledge
Paper • 2403.13293 • Published
AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
Paper • 2211.17228 • Published
GENNAPE: Towards Generalized Neural Architecture Performance Estimators
Paper • 2211.17226 • Published
Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search
Paper • 2109.12426 • Published
L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning
Paper • 2109.12425 • Published