1 citations · 1 across the 2 of their papers we have counts for
3 papers
cs.LG2026
Language Models Share a Readout Bottleneck in Working Memory
Dongyu Gong
Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and errors concentrate on lures, items…
cs.CL2024
Self-Attention Limits Working Memory Capacity of Transformer-Based Models
Dongyu Gong, Hantao Zhang
Recent work on Transformer-based large language models (LLMs) has revealed striking limits in their working memory capacity, similar to what has been found in human behavioral stud…
cs.AI2023★ 1 cited
Working Memory Capacity of ChatGPT: An Empirical Study
Dongyu Gong, Xingchen Wan, Dingmin Wang
Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In thi…