Julian Killingback (@julian_a42f9a) 's Twitter Profile
Julian Killingback

@julian_a42f9a

PhD Student at UMass Amherst working on Information Retrieval and Natural Language Processing

ID: 1887971575099703298

calendar_today07-02-2025 21:08:22

24 Tweet

40 Followers

51 Following

Sumit (@_reachsumit) 's Twitter Profile Photo

Hypencoder: Hypernetworks for Information Retrieval Introduces a novel neural network architecture that produces small query-dependent networks for ranking, while being fast enough to search 8.8M documents in 60ms. 📝arxiv.org/abs/2502.05364 👨🏽‍💻github.com/jfkback/hypenc…

Sumit (@_reachsumit) 's Twitter Profile Photo

I published Vol. 91 of "Top Information Retrieval Papers of the Week" on Substack. 🔗 recsys.substack.com/p/adding-reaso…

I published Vol. 91 of "Top Information Retrieval Papers of the Week" on Substack.
🔗 recsys.substack.com/p/adding-reaso…
Sumit (@_reachsumit) 's Twitter Profile Photo

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs Hansi Zeng et al investigate how different retrieval paradigms scale with larger models, showing sparse retrieval consistently outperforms dense retrieval while demonstrating better generalization 📝arxiv.org/abs/2502.15526

Hansi Zeng (@hansizeng) 's Twitter Profile Photo

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs: arxiv.org/abs/2502.15526 Study scaling behaviors of retrieval models with different retrieval paradigms (sparse vs. dense) and fine-tuning objectives (contra. loss vs. KD) from 1B to 8B scale. Code: github.com/HansiZeng/scal…