Sunzhu Li
YOU?
Author Swipe
View article: Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning Open
Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the encouraging results, a fundamental dilemma persists as RL impr…
View article: LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter Sharing
LightFormer: Light-weight Transformer Using SVD-based Weight Transfer and Parameter Sharing Open
Transformer has become an important technique for natural language processing tasks with great success. However, it usually requires huge storage space and computational cost, making it difficult to be deployed on resource-constrained edge…
View article: MorphTE: Injecting Morphology in Tensorized Embeddings
MorphTE: Injecting Morphology in Tensorized Embeddings Open
In the era of deep learning, word embeddings are essential when dealing with text tasks. However, storing and accessing these embeddings requires a large amount of space. This is not conducive to the deployment of these models on resource-…
View article: Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation
Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation Open
Transformer has been demonstrated effective in Neural Machine Translation (NMT). However, it is memory-consuming and time-consuming in edge devices, resulting in some difficulties for real-time feedback. To compress and accelerate Transfor…