LI WENTONG

sunshine-lwt's activity

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

upvoted a paper 2 months ago

PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity

Paper • 2510.23603 • Published Oct 27, 2025 • 22

upvoted a paper 5 months ago

RynnEC: Bringing MLLMs into Embodied World

Paper • 2508.14160 • Published Aug 19, 2025 • 19

upvoted 3 papers 7 months ago

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?

Paper • 2506.05287 • Published Jun 5, 2025 • 14

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Paper • 2505.19147 • Published May 25, 2025 • 144

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

Paper • 2505.18675 • Published May 24, 2025 • 26

upvoted a paper about 1 year ago

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

Paper • 2501.00599 • Published Dec 31, 2024 • 46

upvoted a collection over 1 year ago

TokenPacker

Collection

Official model collection for the paper "TokenPacker: Efficient Visual Projector for Multimodal LLM" • 7 items • Updated Jul 25, 2024 • 4

upvoted a paper over 1 year ago

TokenPacker: Efficient Visual Projector for Multimodal LLM

Paper • 2407.02392 • Published Jul 2, 2024 • 23

upvoted a paper about 2 years ago

Osprey: Pixel Understanding with Visual Instruction Tuning

Paper • 2312.10032 • Published Dec 15, 2023 • 3