Xuan Xiao

xiaoxuanzi's activity

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

upvoted a paper about 4 hours ago

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning

Paper • 2512.05591 • Published 3 days ago • 11

liked a dataset 4 days ago

a-m-team/AM-DeepSeek-R1-Distilled-1.4M

Preview • Updated Mar 30 • 1.69k • 170

upvoted a collection 25 days ago

SYNTHETIC-1

Collection

A collection of tasks & verifiers for reasoning datasets • 9 items • Updated Oct 7 • 66

upvoted a paper about 1 month ago

Open Multimodal Retrieval-Augmented Factual Image Generation

Paper • 2510.22521 • Published Oct 26 • 30

upvoted a paper about 2 months ago

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16 • 104

New activity in nvidia/Llama-3.3-Nemotron-70B-Reward-Multilingual 2 months ago

A simple hack that seriously affected my training

#1 opened 2 months ago by

xiaoxuanzi

upvoted a paper 2 months ago

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 19

liked a Space 3 months ago

Running

30

JudgeBench Leaderboard

🏆

30

Generate a leaderboard for evaluating language models

liked 2 models 3 months ago

Kwai-Klear/Klear-46B-A2.5B-Instruct

Text Generation • 46B • Updated Sep 7 • 56 • 81

Kwai-Klear/Klear-46B-A2.5B-Base

Text Generation • 46B • Updated Sep 7 • 52 • 28

upvoted a paper 4 months ago

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

Paper • 2508.07629 • Published Aug 11 • 42

updated a model over 1 year ago

xiaoxuanzi/CT-GAT

Updated Jun 26, 2024