Yunpu Ma
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
arXiv 2026
ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
arXiv 2026
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
arXiv 2026
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
arXiv 2025
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding
arXiv 2025
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv 2025
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
arXiv 2025
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
arXiv 2024
GraphextQA: A Benchmark for Evaluating Graph-Enhanced Large Language Models
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers