Changxin Tian

ChangxinTian's activity

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

authored 2 papers 2 months ago

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging

Paper • 2601.17858 • Published Jan 25 • 1

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics

Paper • 2510.09295 • Published Oct 10, 2025

authored a paper 5 months ago

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

Paper • 2510.22115 • Published Oct 25, 2025 • 85

authored 5 papers 6 months ago

Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness

Paper • 2508.18824 • Published Aug 26, 2025 • 1

Toward Stable and Consistent Evaluation Results: A New Methodology for Base Model Evaluation

Paper • 2503.00812 • Published Mar 2, 2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

Paper • 2503.05139 • Published Mar 7, 2025 • 6

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models

Paper • 2507.17702 • Published Jul 23, 2025 • 6

WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training

Paper • 2507.17634 • Published Jul 23, 2025 • 2