Firoj112 commited on
Commit
3b4ba53
·
verified ·
1 Parent(s): 34aec53

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ Greetings from GEM Space, the heart of innovation behind our paper, "FRAGILE MAS
17
 
18
  ***Abstract***:
19
 
20
- The deployment of On-Device Language Models (ODLMs) on resource-constrained edge devices demands a delicate balance of efficiency, memory, power, and linguistic skill across diverse tasks. In "FRAGILE MASTERY", we explore the trade-offs between domain-specific optimization and cross-domain robustness, introducing the Generalized Edge Model (GEM). GEM integrates specialization and generalization using a Sparse Cross-Attention Router (SCAR), achieving a cross-domain F1 score of 0.89 with sub-100ms latency on platforms like Raspberry Pi 4 and Pixel 6. Across 47 benchmarks spanning eight domains—healthcare, legal, finance, STEM, and more—GEM boosts general-task performance by 7% over GPT-4 Lite while matching domain-specific results. With new metrics like the Domain Specialization Index (DSI) and a balanced distillation framework cutting catastrophic forgetting by 43%, this work offers a robust foundation for edge AI. [Paper link coming soon!]
21
 
22
  ***Architecture***:
23
  <div align="center">
 
17
 
18
  ***Abstract***:
19
 
20
+ The deployment of On-Device Language Models (ODLMs) on resource-constrained edge devices demands a delicate balance of efficiency, memory, power, and linguistic skill across diverse tasks. In "FRAGILE MASTERY", we explore the trade-offs between domain-specific optimization and cross-domain robustness, introducing the Generalized Edge Model (GEM). GEM integrates specialization and generalization using a Sparse Cross-Attention Router (SCAR), achieving a cross-domain F1 score of 0.89 with sub-100ms latency on platforms like Raspberry Pi 4 and Pixel 6. Across 47 benchmarks spanning eight domains—healthcare, legal, finance, STEM, and more—GEM boosts general-task performance by 7% over GPT-4 Lite while matching domain-specific results. With new metrics like the Domain Specialization Index (DSI) and a balanced distillation framework cutting catastrophic forgetting by 43%, this work offers a robust foundation for edge AI. [Paper Link](https://arxiv.org/abs/2503.22698)
21
 
22
  ***Architecture***:
23
  <div align="center">