Token pooling pairs well with embedding quantization and Matryoshka, says tomaarsen
tomaarsen · x · 2026-11-11
sentence-transformers maintainer tomaarsen shares that token pooling works remarkably well alongside (asymmetric) embedding quantization, and even with Matryoshka representation learning — though Matryoshka is lossier, it works well for models with native dimensionality well above 128.
More from Research
- Test-time self-distillation decoding beats beam search by 8.2 pts on MATH500 without training — hbouammar · 2026-11-12
- Anthropic's 'Worse Together': single coordinator agent beats per-user agent teams in all 4 tests — ombre-ai · 2026-11-12
- 1,440 Synthetic Control Specs Show Huge Leeway in California $20 Minimum Wage Studies — RexDouglass · 2026-11-12
- ICLR abstract word-frequency shift: 'novel' and 'comprehensive' plummet as LLM fingerprints fade — y_m_asano · 2026-11-12
- Evolving Infra: agent-adaptive LLM serving cuts latency up to 4.1x vs NVIDIA Dynamo — mit-han-lab · 2026-11-12
- Isomorphic Labs President on Using AI to Turn Drug Discovery into Precision Engineering — No Priors · 2026-11-12