hpool vs AGC on Regularized Models
antoine_chaffin · x · 2026-07-07
However, the previous comparison targeted unregularized models. Which is better between hpool and AGC on regularized models? Across the 7 BEIR datasets evaluated, AGC had an average retention rate of 97.4%, slightly lower than hpool's 97.9%. Note that these results aren't directly comparable (due to different training data and scales), and the baseline results are also stronger (0.506 vs 0.462), so this is for reference only—the key takeaway is that simpler methods can achieve similar performance.
Related event: hpool Enables Flexible and Adaptive Compression for Retrieval Models(5 posts)→
More from Research
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27
- GPT-6 Pro reruns crime research: GTA V's 2013 launch tied to violence dips in four regions — emollick · 2026-10-27
- OpenAI's Aaron Lou on leaving a Stanford PhD for OpenAI, diffusion LMs vs autoregression — aaron_lou · 2026-10-27
- CLT-Forge: Open-source toolkit for cross-layer transcoder training and attribution graphs — ZhijingJin · 2026-10-27