Steven

yijunyang's activity

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

upvoted a paper 11 days ago

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Paper • 2504.07964 • Published 12 days ago • 61

authored a paper about 1 month ago

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Paper • 2503.08525 • Published Mar 11 • 16

upvoted a paper about 1 month ago

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Paper • 2503.08525 • Published Mar 11 • 16

commented a paper about 1 month ago

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Paper • 2503.08525 • Published Mar 11 • 16 •

2

upvoted a paper about 2 months ago

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts

Paper • 2502.20395 • Published Feb 27 • 47

liked a dataset 2 months ago

huanqia/MM-IQ

Viewer • Updated Feb 7 • 2.71k • 364 • 12

authored a paper 3 months ago

MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models

Paper • 2502.00698 • Published Feb 2 • 24

upvoted a paper 3 months ago

MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models

Paper • 2502.00698 • Published Feb 2 • 24

upvoted a paper 6 months ago

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Paper • 2410.23743 • Published Oct 31, 2024 • 64

authored 4 papers 6 months ago

Continual Task Allocation in Meta-Policy Network via Sparse Prompting

Paper • 2305.18444 • Published May 29, 2023 • 1

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

Paper • 2311.16714 • Published Nov 28, 2023 • 1

PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization

Paper • 2212.05652 • Published Dec 12, 2022 • 2

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Paper • 2410.07484 • Published Oct 9, 2024 • 50

upvoted a paper 6 months ago

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

Paper • 2410.07484 • Published Oct 9, 2024 • 50