5 citations · 6 across the 7 of their papers we have counts for
7 papers
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
Hao Wang, Hanchen Li, Qiuyang Mang +3
Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a s…
Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
Jongseok Park, Sunga Kim, Zhenyu Gu +2
Mixture of Experts (MoE) architecture has become the standard for state-of-the-art large language models, owing to its computational efficiency through sparse expert activation. Ho…
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics
Arash Ardakani, Altan Haan, Shangyin Tan +4
Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, t…
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
Linyuan Gong, Chenyan Xiong, Xiaodong Liu +5
This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5. We study various designs to pretrain…
An Evaluation of Memory Optimization Methods for Training Neural Networks
Xiaoxuan Liu, Siddharth Jha, Alvin Cheung
As models continue to grow in size, the development of memory optimization methods (MOMs) has emerged as a solution to address the memory bottleneck encountered when training large…
ADELT: Transpilation Between Deep Learning Frameworks
Linyuan Gong, Jiayi Wang, Alvin Cheung
We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skel…
GACT: Activation Compressed Training for Generic Network Architectures
Xiaoxuan Liu, Lianmin Zheng, Dequan Wang +9
Training large neural network (NN) models requires extensive memory resources, and Activation Compressed Training (ACT) is a promising approach to reduce training memory footprint.…