Erik Nielsen
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
The paper proposes SubFit, a novel compression technique that achieves superior LLM compression by replacing non-contiguous, submodule-level components (Attention and FeedForward) with lightweight residual bypasses, significantly improving the perplexity-accuracy trade-off.
Highlighted terms show continued research focus across papers