6 papers
Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing
Miao Rang, Zhenni Bi, Hang Zhou +6
Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, t…
An Empirical Study of World Model Quantization
Zhongqian Fu, Tianyi Zhao, Kai Han +3
World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a compact latent space for tasks such as pl…
VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
Ying Nie, Kai Han, Hongguang Li +5
The rapid scaling of Large Language Models (LLMs) has achieved remarkable performance, but it also leads to prohibitive memory costs. Existing parameter-efficient approaches such a…
ROOT: Robust Orthogonalized Optimizer for Neural Network Training
Wei He, Kai Han, Hang Zhou +4
The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instabi…
Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
Miao Rang, Zhenni Bi, Hang Zhou +6
The rapid advancement of large language models (LLMs) has significantly advanced the capabilities of artificial intelligence across various domains. However, their massive scale an…
LLM Data Selection and Utilization via Dynamic Bi-level Optimization
Yang Yu, Kai Han, Hang Zhou +4
While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to…