← back to paper

Review history

arxiv: 2506.13514 · 2 revisions

TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
   197806 ms 17312 in 21065 out 2026-08-15T20:00:31.752988+00:00
2. 2026-08-07 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   132838 ms 17492 in 13492 out 2026-08-07T00:31:46.620501+00:00