NMSLIB author calls out ANN library paper for downplaying pioneering work
srchvrs · x · 2026-11-05
The author of NMSLIB publicly complained that a paper on general-purpose ANN libraries treats his earlier work unfairly: reducing it to an incidental mention and a questionable negative example, while devoting extensive attention to newer libraries that built on it. He noted NMSLIB was the first widely used ANN library supporting both dense and sparse representations, multiple similarity measures, and graph-based indexing for both, and that their 2016 CIKM paper showed graph-based methods are competitive on sparse data. He says he isn't questioning the new work, just that survey-style papers should credit and describe prior work accurately.
Related event: NMSLIB Author Protests New Vector Search Paper Downplaying His Work(4 posts)→
More from Research
- Researchers Undo SFT Behavior by Subtracting Weight Updates from Final Checkpoints — burny_tech · 2026-11-05
- USC-led $3.2M NIH project to analyze 94,000 brain scans across 8 mental illnesses — PTenigma · 2026-11-05
- USC's Zeta Law paper uses Riemann zeta function to predict when data is enough for discovery — PTenigma · 2026-11-05
- Stanford team forecasts GSM8K accuracy from zero-score models using hinted joint scaling laws — stanfordnlp · 2026-11-05
- Molecular Dataset Hub launches with 248 traced, quality-graded datasets — CatAstro_Piyush · 2026-11-05
- BenchFlow at Bench Summit: we're not ambitious enough with how we build evals — MeganRisdal · 2026-11-05