xiaokun sun

yscsb's activity

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

upvoted a paper 3 months ago

Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration

Paper • 2309.01131 • Published Sep 3, 2023 • 2

upvoted 6 papers 4 months ago

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

Paper • 2505.03739 • Published May 6, 2025 • 10

DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model

Paper • 2512.12633 • Published Dec 14, 2025 • 2

RISE-Video: Can Video Generators Decode Implicit World Rules?

Paper • 2602.05986 • Published Feb 5 • 28

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published Mar 6 • 50

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published Apr 6 • 236

When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition

Paper • 2603.16256 • Published Mar 17 • 2