5 citations · 5 across the 5 of their papers we have counts for
4 papers · 1 filter
CoTranslator: Reverse to Forward Chain-of-Thought Translator for Reasoning Distillation
Zinan Tang, Zhuoshi Pan, Kairui Chen +5
Reasoning distillation requires chain-of-thought (CoT) data with correct answers, but obtaining such data efficiently remains challenging. Forward CoT generation (FCG) followed by…
Hierarchical Alignment: Block-Level LoRA-DPO for Preference Tuning in Large Language Models
Yukun Zhang, Yishen Chen, Qi Dong
Preference tuning typically distributes adapter updates across every Transformer layer. We study how the placement of a fixed LoRA budget affects Direct Preference Optimization (DP…
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
Yukun Zhang, Qi Dong, Mengkang Li
Understanding how latent representations evolve during generation is a central open problem in large language model interpretability. We introduce \textbf{Dynamical Manifold Evolut…
Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework
Yukun Zhang, Qi Dong
We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cr…