From the 1 of 10 linked papers with an AI index.
10 papers
Memory for Large Language Models
Sining Zhoubian, Dan Zhang, Evgeny Kharlamov +1
The paper surveys and categorizes the various memory mechanisms used in large language models, proposing a taxonomy based on representation, update dynamics, and persistence to uni…
RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism
Mengyang Sun, Maochuan Dou, Tao Feng +5
While Large Language Models (LLMs) are commonly fine-tuned to handle domain-specific tasks before being applied to vertical applications, adapting them to complex scenarios with di…
TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference
Dan Zhang, Min Cai, Jonathan Light +3
Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency,…
ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding
Sining Zhoubian, Dan Zhang, Jie Tang
With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verif…
ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Tao Feng, Wei Li, Didi Zhu +4
Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Optimizers such as SGD and Adam are commonly used for weight updates in continual learn…
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
Mengyang Sun, Yihao Wang, Tao Feng +3
In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domai…