Diversifying Joint Vision-Language Tokenization Learning
Paper
•
2306.03421
•
Published
•
2
Vardaan Pahuja
vardaan123
AI & ML interests
LLM Agents, Multimodal Foundation Models, Knowledge Graphs
Recent Activity
liked
a dataset
8 days ago
osunlp/Mind2Web-2
upvoted
a
paper
9 days ago
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
updated
a dataset
about 2 months ago
vardaan123/test_dataset
Organizations
authored
5
papers
5 months ago
A Systematic Investigation of KB-Text Embedding Alignment at Scale
Paper
•
2106.01586
•
Published
•
1
Bringing Back the Context: Camera Trap Species Identification as Link Prediction on Multimodal Knowledge Graphs
Paper
•
2401.00608
•
Published
•
2
A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
Paper
•
2212.09724
•
Published
•
1
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Paper
•
2502.11357
•
Published
•
10