Wei-Yao Wang

SwyWang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 5 days ago

VIRTUE

Collection

Visual-Interactive Text-Image Universal Embedder (ICLR-26) • 5 items • Updated 5 days ago • 3

upvoted a paper 4 months ago

Not Just What, But When: Integrating Irregular Intervals to LLM for Sequential Recommendation

Paper • 2507.23209 • Published Jul 31, 2025 • 3

upvoted a paper 5 months ago

VIRTUE: Visual-Interactive Text-Image Universal Embedder

Paper • 2510.00523 • Published Oct 1, 2025 • 7

upvoted 2 papers 12 months ago

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

Paper • 2503.02597 • Published Mar 4, 2025 • 1

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems

Paper • 2502.11098 • Published Feb 16, 2025 • 13