LightOn Achieves 2x Lossless Compression for ColBERT
antoine_chaffin · x · 2026-07-07
LightOn announced that by introducing hierarchical pooling, they achieved 2x lossless compression on the ColBERT retrieval model's state, calling it an even bigger "free lunch." The technology aims to reduce the storage and deployment costs of retrieval models.
More from Research
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22