Yunheng Li

lyhisme's activity

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

submitted a paper to Daily Papers 1 day ago

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

Paper • 2602.13013 • Published 4 days ago • 7

authored 5 papers 5 months ago

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

Paper • 2509.18056 • Published Sep 22, 2025 • 27

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

Paper • 2406.00670 • Published Jun 2, 2024

Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction

Paper • 2412.06244 • Published Dec 9, 2024

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

Paper • 2508.01548 • Published Aug 3, 2025 • 14

Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignment

Paper • 2508.08811 • Published Aug 12, 2025 • 2