Fangyuan Yu PRO

Ksgk-fy's activity

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

updated a collection 2 days ago

Embodied AI

Collection

Embodiment enables interaction of model with environment. Key is to anticipate what change could've come with its current action. • 36 items • Updated 2 days ago • 1

updated 2 collections 6 days ago

Embodied AI

Collection

Embodiment enables interaction of model with environment. Key is to anticipate what change could've come with its current action. • 36 items • Updated 2 days ago • 1

Memory

Collection

Prompt is text-based memory. System II prompting is updating memory. Parametric memory is long-term, while prompt-based are short-tem. • 23 items • Updated 6 days ago • 2

updated a collection 18 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

upvoted a paper 18 days ago

Memory Retrieval and Consolidation in Large Language Models through Function Tokens

Paper • 2510.08203 • Published 18 days ago • 7

updated a collection 18 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

upvoted a paper 18 days ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published 18 days ago • 243

updated a collection 18 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

upvoted a paper 24 days ago

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26 • 176

updated a collection 25 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

upvoted a paper 25 days ago

The Three Regimes of Offline-to-Online Reinforcement Learning

Paper • 2510.01460 • Published 26 days ago • 1

updated a collection 25 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

commented a paper 25 days ago

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models

Paper • 2510.00046 • Published about 1 month ago •

1

updated a collection 25 days ago

Fine Dataset

Collection

2 items • Updated 25 days ago

commented a paper 25 days ago

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Paper • 2510.02263 • Published 25 days ago • 8 •

2

updated a collection 25 days ago

Representation & Optimization

Collection

Understanding about representation sheds light on optimization • 95 items • Updated 18 days ago • 4

upvoted 2 papers 25 days ago

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

Paper • 2510.02263 • Published 25 days ago • 8

RLP: Reinforcement as a Pretraining Objective

Paper • 2510.01265 • Published Sep 26 • 39

commented a paper 25 days ago

Generalized Parallel Scaling with Interdependent Generations

Paper • 2510.01143 • Published 26 days ago • 4 •

2