Xinyi Wan

ufotalent's activity

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

upvoted a paper 24 days ago

In-Context Reinforcement Learning for Tool Use in Large Language Models

Paper • 2603.08068 • Published 27 days ago • 42

upvoted a paper about 2 months ago

Rethinking the Trust Region in LLM Reinforcement Learning

Paper • 2602.04879 • Published Feb 4 • 37

upvoted a paper 2 months ago

Revisiting Parameter Server in LLM Post-Training

Paper • 2601.19362 • Published Jan 27 • 8

upvoted 2 papers 6 months ago

Language Models Can Learn from Verbal Feedback Without Scalar Rewards

Paper • 2509.22638 • Published Sep 26, 2025 • 70

Variational Reasoning for Language Models

Paper • 2509.22637 • Published Sep 26, 2025 • 69

upvoted a paper 7 months ago

Understanding Tool-Integrated Reasoning

Paper • 2508.19201 • Published Aug 26, 2025 • 32

upvoted a paper 11 months ago

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Paper • 2505.13438 • Published May 19, 2025 • 36

upvoted a paper about 1 year ago

PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization

Paper • 2503.01328 • Published Mar 3, 2025 • 16

upvoted an article about 1 year ago

view article

Article

DualPipe could be better without the Dual

• 

Feb 28, 2025

•

17

upvoted a collection over 1 year ago

🔱 Sailor2 Language Models

Collection

Sailing in South-East Asia with Inclusive Multilingual LLMs • 32 items • Updated Mar 2 • 30

upvoted a paper over 1 year ago

Balancing Pipeline Parallelism with Vocabulary Parallelism

Paper • 2411.05288 • Published Nov 8, 2024 • 20

upvoted a paper almost 2 years ago

Pipeline Parallelism with Controllable Memory

Paper • 2405.15362 • Published May 24, 2024 • 3

upvoted a paper about 2 years ago

Zero Bubble Pipeline Parallelism

Paper • 2401.10241 • Published Nov 30, 2023 • 25