Zhanpeng Zhou

On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning

Achieving low-bit Muon through subspace preservation and grid quantization

IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring

Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws

Unintended Harmful Knowledge Elicitation Issue in Large Reasoning Models and a RL Solution

How Does Local Landscape Geometry Evolve in Language Model Pre-Training?

Efficient Hyperparameter Tuning via Trajectory Invariance Principle

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training

On the Role of Label Noise in the Feature Learning Process

The Role of Label Noise in the Feature Learning Process