Jiawei Zhao

Deep Think with Confidence

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?

Why RL Updates Look Sparse: An Implicit Compass Drives Optimization Bias

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts

From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications

Tensor-GaLore: Memory-Efficient Training via Gradient Tensor Decomposition

Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients

From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients