2 citations · 2 across the 14 of their papers we have counts for
5 papers · 2 filters
Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
Dake Bu, Wei Huang, Andi Han +4
Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving reasoning performance, yet a pri…
Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories
Dake Bu, Wei Huang, Andi Han +5
Foundation models exhibit broad knowledge but limited task-specific reasoning, motivating post-training strategies such as RL with verifiable rewards (RLVR) and test-time scaling (…
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
Wei Huang, Andi Han, Yujin Song +4
The capacity of deep learning models is often large enough to both learn the underlying statistical signal and overfit to noise in the training set. This noise memorization can be…
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
Dake Bu, Wei Huang, Andi Han +4
In-context learning (ICL) has garnered significant attention for its ability to grasp functions/tasks from demonstrations. Recent studies suggest the presence of a latent task/func…
Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
Yilan Chen, Zhichao Wang, Wei Huang +3
Gradient-based optimization methods have shown remarkable empirical success, yet their theoretical generalization properties remain only partially understood. In this paper, we est…