8 papers
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 (…
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…
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…
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Dake Bu, Wei Huang, Andi Han +4
Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection b…
On the Feature Learning in Diffusion Models
Andi Han, Wei Huang, Yuan Cao +1
The predominant success of diffusion models in generative modeling has spurred significant interest in understanding their theoretical foundations. In this work, we propose a featu…
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
Yujin Han, Andi Han, Wei Huang +2
Despite the remarkable success of diffusion models (DMs) in data generation, they exhibit specific failure cases with unsatisfactory outputs. We focus on one such limitation: the a…