Mingyang Song

hitsmy's activity

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

authored a paper 3 days ago

SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents

Paper • 2606.05761 • Published Jun 4 • 19

updated 2 models 4 days ago

PolicyShiftGuard/PolicyShiftGuard-7B-RP-SFT

Image-Text-to-Text • 8B • Updated 4 days ago • 17

PolicyShiftGuard/PolicyShiftGuard-3B-RP-SFT

Image-Text-to-Text • 4B • Updated 4 days ago • 16

published 2 models 4 days ago

PolicyShiftGuard/PolicyShiftGuard-7B-RP-SFT

Image-Text-to-Text • 8B • Updated 4 days ago • 17

PolicyShiftGuard/PolicyShiftGuard-3B-RP-SFT

Image-Text-to-Text • 4B • Updated 4 days ago • 16

updated a dataset 4 days ago

PolicyShiftGuard/PolicyShiftBench

Updated 4 days ago • 157

published a dataset 4 days ago

PolicyShiftGuard/PolicyShiftBench

Updated 4 days ago • 157

updated 2 models 4 days ago

PolicyShiftGuard/PolicyShiftGuard-7B

8B • Updated 4 days ago • 42

PolicyShiftGuard/PolicyShiftGuard-3B

4B • Updated 4 days ago • 66

published 2 models 4 days ago

PolicyShiftGuard/PolicyShiftGuard-7B

8B • Updated 4 days ago • 42

PolicyShiftGuard/PolicyShiftGuard-3B

4B • Updated 4 days ago • 66

upvoted a paper 9 days ago

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Paper • 2607.02440 • Published 11 days ago • 50

upvoted a paper 2 months ago

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Paper • 2605.05185 • Published May 6 • 106

published a dataset 3 months ago

PolicyShiftGuard/adaptive-policy-v2.8-withreason

Viewer • Updated Apr 20 • 20.2k • 162

updated a dataset 3 months ago

PolicyShiftGuard/adaptive-policy-v2.8-withreason

Viewer • Updated Apr 20 • 20.2k • 162

upvoted 2 papers 3 months ago

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

Paper • 2603.29620 • Published Mar 31 • 49

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Paper • 2603.28088 • Published Mar 30 • 87

upvoted an article 5 months ago

view article

Article

Your MoE Model Does Not Have to Select Fixed Number of Experts

• 

Spico

•

Feb 26

• 8

upvoted 2 papers 5 months ago

Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

Paper • 2602.07022 • Published Feb 2 • 19

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

Paper • 2602.09443 • Published Feb 10 • 59