Xiangyu

xixy's activity

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

authored 6 papers about 9 hours ago

Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs

Paper • 2505.18573 • Published May 24, 2025

LongCat-Flash Technical Report

Paper • 2509.01322 • Published Sep 1, 2025 • 6

LongCat-Flash-Thinking Technical Report

Paper • 2509.18883 • Published Sep 23, 2025 • 4

Autoformalizer with Tool Feedback

Paper • 2510.06857 • Published Oct 8, 2025

Can Tool-Integrated Reinforcement Learning Generalize Across Diverse Domains?

Paper • 2510.11184 • Published Oct 13, 2025

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published 3 days ago • 134

upvoted a paper about 9 hours ago

LongCat-Flash-Thinking-2601 Technical Report

Paper • 2601.16725 • Published 3 days ago • 134

upvoted a paper 7 days ago

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published 11 days ago • 38

upvoted a paper about 1 month ago

Universal Reasoning Model

Paper • 2512.14693 • Published Dec 16, 2025 • 43

commented 2 papers about 1 month ago

Rethinking Expert Trajectory Utilization in LLM Post-training

Paper • 2512.11470 • Published Dec 12, 2025 • 8 •

4

State over Tokens: Characterizing the Role of Reasoning Tokens

Paper • 2512.12777 • Published Dec 14, 2025 • 5 •

6

commented 2 papers 3 months ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published Nov 9, 2025 • 133 •

12

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

Paper • 2511.06307 • Published Nov 9, 2025 • 52 •

5

upvoted a paper 3 months ago

DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation

Paper • 2511.06307 • Published Nov 9, 2025 • 52

upvoted an article 3 months ago

view article

Article

Budget Alignment: Making Models Reason in the User’s Language

• 

Nov 4, 2025

•

10

upvoted a paper 3 months ago

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions

Paper • 2510.26768 • Published Oct 30, 2025 • 34

commented 3 papers 3 months ago

Learning from the Best, Differently: A Diversity-Driven Rethinking on Data Selection

Paper • 2510.18909 • Published Oct 21, 2025 • 5 •

3

First Try Matters: Revisiting the Role of Reflection in Reasoning Models

Paper • 2510.08308 • Published Oct 9, 2025 • 24 •

4

First Try Matters: Revisiting the Role of Reflection in Reasoning Models

Paper • 2510.08308 • Published Oct 9, 2025 • 24 •

4

upvoted a paper 3 months ago

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Paper • 2509.26490 • Published Sep 30, 2025 • 20