BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Paper
•
2412.04626
•
Published
•
14
Xiangru (Edward) Jian
HideOnBush
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 12 hours ago
The Underappreciated Power of Vision Models for Graph Structural
Understanding
liked
a model
3 days ago
meta-llama/Llama-3.2-3B
upvoted
a
paper
3 days ago
Scaling Latent Reasoning via Looped Language Models
Organizations
authored
2
papers
11 days ago
authored
6
papers
12 days ago
Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
Paper
•
2405.19600
•
Published
Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization
Paper
•
2208.08681
•
Published
Roughness Index for Loss Landscapes of Neural Network Models of Partial Differential Equations
Paper
•
2103.11069
•
Published
DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models
Paper
•
2404.05083
•
Published
LazyVLM: Neuro-Symbolic Approach to Video Analytics
Paper
•
2505.21459
•
Published
Scope: Selective Cross-modal Orchestration of Visual Perception Experts
Paper
•
2510.12974
•
Published
authored
5
papers
5 months ago
Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks
Paper
•
2310.11612
•
Published
InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution
Paper
•
2310.13276
•
Published
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Paper
•
2503.15661
•
Published
•
2
GraphOmni: A Comprehensive and Extendable Benchmark Framework for Large Language Models on Graph-theoretic Tasks
Paper
•
2504.12764
•
Published
•
41
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Paper
•
2505.21497
•
Published
•
108