Yuanxin Liu

lyx97's activity

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

upvoted a paper about 17 hours ago

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

Paper • 2510.27492 • Published 4 days ago • 56

upvoted 2 papers 1 day ago

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Paper • 2504.17343 • Published Apr 24 • 13

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

Paper • 2505.22613 • Published May 28 • 9

upvoted a paper 7 days ago

FARMER: Flow AutoRegressive Transformer over Pixels

Paper • 2510.23588 • Published 7 days ago • 56

authored a paper 8 days ago

Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence

Paper • 2510.20470 • Published 12 days ago • 11

liked a dataset 10 days ago

marinero4972/Open-o3-Video

Preview • Updated 12 days ago • 88 • 3

upvoted 2 papers 11 days ago

Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence

Paper • 2510.20470 • Published 12 days ago • 11

Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence

Paper • 2510.20579 • Published 11 days ago • 52

liked 2 models 12 days ago

Qwen/Qwen3-VL-8B-Thinking

Image-Text-to-Text • 9B • Updated 19 days ago • 82.4k • 134

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated 19 days ago • 1.22M • • 382

liked a model 15 days ago

RUBBISHLIKE/Conan-7B

849k • Updated 15 days ago • 194 • 4

liked a dataset 16 days ago

lyx97/UVE-Bench

Viewer • Updated 25 days ago • 1.88k • 65 • 1

authored 4 papers 19 days ago

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Paper • 2504.17343 • Published Apr 24 • 13

TEMPLE:Temporal Preference Learning of Video LLMs via Difficulty Scheduling and Pre-SFT Alignment

Paper • 2503.16929 • Published Mar 21

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

Paper • 2505.22613 • Published May 28 • 9

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?

Paper • 2505.23359 • Published May 29 • 39

upvoted a paper 19 days ago

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Paper • 2504.13180 • Published Apr 17 • 19

updated a dataset 25 days ago

lyx97/UVE-Bench

Viewer • Updated 25 days ago • 1.88k • 65 • 1

liked a dataset about 2 months ago

TempoFunk/webvid-10M

Viewer • Updated Aug 19, 2023 • 10.7M • 8.16k • 85

updated a Space 2 months ago

Running

12

12

TempCompass

🥇

Submit and view model evaluations