3 papers
cs.LG2025
Constructing Efficient Fact-Storing MLPs for Transformers
Owen Dugan, Roberto Garcia, Ronny Junkins +5
The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Rec…
cs.LG2025
Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
Roberto Garcia, Jerry Liu, Daniel Sorvisto +1
Large Language Models (LLMs) are computationally intensive, particularly during inference. Neuron-adaptive techniques, which selectively activate neurons in Multi-Layer Perceptron…
cs.AI2024
FullStack Bench: Evaluating LLMs as Full Stack Coders
Bytedance-Seed-Foundation-Code-Team, :, Yao Cheng +53
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most exist…