Mingxuan Xia

MingxuanXia's activity

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

upvoted 2 papers 1 day ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 10 days ago • 88

Enhancing Rubric-based RL via Self-Distillation

Paper • 2607.18082 • Published 15 days ago • 21

submitted a paper to Daily Papers 1 day ago

Enhancing Rubric-based RL via Self-Distillation

Paper • 2607.18082 • Published 15 days ago • 21

liked a dataset 5 days ago

m-a-p/COIG-CQIA

Viewer • Updated Apr 18, 2024 • 44.7k • 7.25k • 759

upvoted a paper 6 days ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 8 days ago • 82

upvoted a paper 19 days ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published 20 days ago • 103

upvoted 2 papers 2 months ago

OPRD: On-Policy Representation Distillation

Paper • 2606.06021 • Published Jun 4 • 8

Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs

Paper • 2606.05846 • Published Jun 4 • 4

upvoted 2 papers 3 months ago

Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning

Paper • 2605.11458 • Published May 12 • 7

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 114

upvoted a paper 4 months ago

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Paper • 2604.03993 • Published Apr 5 • 43

upvoted a collection 6 months ago

LLaDA2.1

Collection

3 items • Updated Jun 15 • 29

upvoted 2 papers 6 months ago

Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

Paper • 2601.17058 • Published Jan 22 • 191

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published Jan 21 • 75

upvoted a paper 7 months ago

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published Jan 16 • 27

liked 2 datasets 10 months ago

nnilayy/medqa-usmle

Viewer • Updated Sep 11, 2024 • 12.7k • 179 • 1

dreamerdeo/finqa

Viewer • Updated Mar 6, 2023 • 8.28k • 8.16k • 28

upvoted a paper about 1 year ago

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Paper • 2506.16054 • Published Jun 19, 2025 • 60

commented a paper about 1 year ago

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation

Paper • 2506.03857 • Published Jun 4, 2025 • 2 •

2

authored a paper about 1 year ago

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation

Paper • 2506.03857 • Published Jun 4, 2025 • 2