Xiuyu Li

xiuyul's activity

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

upvoted 2 papers 28 days ago

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

Paper • 2512.05033 • Published Dec 4, 2025 • 15

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models

Paper • 2512.07843 • Published Nov 24, 2025 • 21

updated a model about 2 months ago

xiuyul/deepcoder-sandbox-Qwen3-4B-Instruct-2507-32rank-4e-05lr-step100-merged

Text Generation • 4B • Updated Nov 10, 2025 • 3

published a model about 2 months ago

xiuyul/deepcoder-sandbox-Qwen3-4B-Instruct-2507-32rank-4e-05lr-step100-merged

Text Generation • 4B • Updated Nov 10, 2025 • 3

updated a model about 2 months ago

xiuyul/deepcoder-sandbox-Qwen3-4B-Instruct-2507-32rank-4e-05lr-step80-merged

Text Generation • 4B • Updated Nov 9, 2025 • 4

published a model about 2 months ago

xiuyul/deepcoder-sandbox-Qwen3-4B-Instruct-2507-32rank-4e-05lr-step80-merged

Text Generation • 4B • Updated Nov 9, 2025 • 4

published a model 2 months ago

xiuyul/deepcoder-Qwen-Qwen3-4B-Instruct-2507-32rank-4e-05lr-8group-128batch-1_0temp-seed0-merged

Text Generation • 4B • Updated Nov 3, 2025 • 3

updated a model 2 months ago

xiuyul/deepcoder-Qwen-Qwen3-4B-Instruct-2507-32rank-4e-05lr-8group-128batch-1_0temp-seed0-merged

Text Generation • 4B • Updated Nov 3, 2025 • 3

upvoted a paper 5 months ago

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Paper • 2508.10395 • Published Aug 14, 2025 • 42

updated a dataset 5 months ago

Parallel-Reasoning/apr_sft_data

Preview • Updated Aug 15, 2025 • 12 • 1

published a dataset 5 months ago

Parallel-Reasoning/apr_sft_data

Preview • Updated Aug 15, 2025 • 12 • 1

updated a dataset 5 months ago

Parallel-Reasoning/sosp_sft_data

Viewer • Updated Aug 15, 2025 • 500k • 15

published a dataset 5 months ago

Parallel-Reasoning/sosp_sft_data

Viewer • Updated Aug 15, 2025 • 500k • 15

updated a dataset 5 months ago

Parallel-Reasoning/countdown_problems

Viewer • Updated Aug 15, 2025 • 501k • 37

published a dataset 5 months ago

Parallel-Reasoning/countdown_problems

Viewer • Updated Aug 15, 2025 • 501k • 37