yanlin lai

lyn22333's activity

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

upvoted a paper about 14 hours ago

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published 2 days ago • 22

upvoted a paper 10 days ago

Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction

Paper • 2602.18996 • Published 12 days ago • 15

upvoted a paper 22 days ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 23 days ago • 187

upvoted a collection 24 days ago

PRIME

Collection

PRIME data & models • 4 items • Updated 26 days ago • 3

updated a model 28 days ago

lyn22333/Policy-Qwen3-8B-R-Align-8B

8B • Updated 28 days ago • 13

updated 2 datasets 29 days ago

lyn22333/R-Align-RL-Data

Viewer • Updated 29 days ago • 109k • 17

lyn22333/R-Align-BMK

Viewer • Updated 29 days ago • 17.4k • 32

updated a model 29 days ago

lyn22333/Policy-Qwen3-8B-R-Align-14B

8B • Updated 29 days ago • 7

upvoted a paper 30 days ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

Paper • 2602.01851 • Published Feb 2 • 16

updated a collection 30 days ago

R-Align

Collection

R-Align model & data. • 6 items • Updated 30 days ago

published 2 models 30 days ago

lyn22333/Policy-Qwen3-8B-R-Align-8B

8B • Updated 28 days ago • 13

lyn22333/Policy-Qwen3-8B-R-Align-14B

8B • Updated 29 days ago • 7

updated 2 models 30 days ago

lyn22333/GenRM-R-Align-8B

8B • Updated 30 days ago • 15

lyn22333/GenRM-R-Align-14B

15B • Updated 30 days ago • 22

authored a paper about 1 month ago

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

Paper • 2508.05592 • Published Aug 7, 2025 • 6

liked a model about 1 month ago

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated 21 days ago • 327k • • 684

upvoted a paper about 1 month ago

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

Paper • 2508.05592 • Published Aug 7, 2025 • 6

updated a collection about 1 month ago

R-Align

Collection

R-Align model & data. • 6 items • Updated 30 days ago

published a model about 1 month ago

lyn22333/GenRM-R-Align-14B

15B • Updated 30 days ago • 22