Yunheng Li

lyhisme's activity

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

updated a Space 1 day ago

Running

ASID-Caption

🦉

updated a dataset 1 day ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 1 day ago • 241k • 84 • 4

updated 2 models 1 day ago

AudioVisual-Caption/ASID-Captioner-3B

Image-Text-to-Text • 5B • Updated 1 day ago • 53 • 1

AudioVisual-Caption/ASID-Captioner-7B

Image-Text-to-Text • 9B • Updated 1 day ago • 30 • 3

upvoted a paper 9 days ago

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

Paper • 2602.13013 • Published 12 days ago • 8

submitted a paper to Daily Papers 10 days ago

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

Paper • 2602.13013 • Published 12 days ago • 8

published 2 models 12 days ago

AudioVisual-Caption/ASID-Captioner-3B

Image-Text-to-Text • 5B • Updated 1 day ago • 53 • 1

AudioVisual-Caption/ASID-Captioner-7B

Image-Text-to-Text • 9B • Updated 1 day ago • 30 • 3

published a Space 14 days ago

Running

ASID-Caption

🦉

liked a dataset 14 days ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 1 day ago • 241k • 84 • 4

published a dataset 15 days ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 1 day ago • 241k • 84 • 4

upvoted a paper 5 months ago

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Paper • 2510.08540 • Published Oct 9, 2025 • 109

authored a paper 5 months ago

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

Paper • 2509.18056 • Published Sep 22, 2025 • 27

upvoted a paper 5 months ago

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

Paper • 2509.18056 • Published Sep 22, 2025 • 27

commented a paper 5 months ago

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

Paper • 2509.18056 • Published Sep 22, 2025 • 27 •

3

authored 4 papers 5 months ago

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

upvoted a paper 5 months ago

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

Paper • 2508.01548 • Published Aug 3, 2025 • 14