Xiangyu Zeng

Lanxingxuan's activity

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

upvoted a paper 1 day ago

RIVER: A Real-Time Interaction Benchmark for Video LLMs

Paper • 2603.03985 • Published 2 days ago • 4

upvoted 9 collections about 1 month ago

SteadyDancer

Collection

4 items • Updated Dec 4, 2025 • 3

SAM2-Plus

Collection

3 items • Updated Oct 29, 2025 • 1

KS-Gen

Collection

Learning Human Skill Generators at Key-Step Levels • 3 items • Updated Sep 17, 2025 • 1

PixNerd: Pixel Neural Field Diffusion

Collection

4 items • Updated Aug 1, 2025 • 2

DDT: Decoupled Diffusion Transformer

Collection

5 items • Updated Aug 1, 2025 • 1

CaRe

Collection

CaReBench data, CaRe models and all the contrastively trained MLLMs (including InternVL2, MiniCPM-V 2.6, LLaVA NeXT Video, Qwen2-VL and Tariser). • 6 items • Updated Mar 17, 2025 • 2

OVBench&VideoChatOnline

Collection

3 items • Updated May 31, 2025 • 1

StreamForest & ODVBench

Collection

6 items • Updated Sep 29, 2025 • 2

Video-o3

Collection

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning • 3 items • Updated 24 days ago • 1

upvoted a paper 3 months ago

VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Paper • 2504.06958 • Published Apr 9, 2025 • 13