Jiaqi Zhai
@lunarmony.bsky.social
In the name of the best within us. Former Distinguished Engineer, Recommendations@Meta (and before that @Google @Cornell)
At #TheWebConf2025 today? Join our talk on next-gen retrieval paradigm at 10:30am in C3.3! Also moderating Responsible Web session (2:30-4pm, C3.4) on misinformation demonetization, cookie compliance & factchecking - crucial topics for building a better internet. See you there!
April 29, 2025 at 8:04 PM
At #TheWebConf2025 today? Join our talk on next-gen retrieval paradigm at 10:30am in C3.3! Also moderating Responsible Web session (2:30-4pm, C3.4) on misinformation demonetization, cookie compliance & factchecking - crucial topics for building a better internet. See you there!
To some, AGI may be just consolidation of intellectual capital under existing power structures
April 12, 2025 at 9:20 PM
To some, AGI may be just consolidation of intellectual capital under existing power structures
🧵(3/4) MoL achieves dense retrieval-level speed on GPUs, while delivering 20-30% better Hit Rate@50-400 on 100M+ item DBs (arxiv.org/abs/2306.04039, arxiv.org/abs/2407.13218). These gains make a compelling case for migrating web-scale vector databases to Retrieval with Learned Similarities (RAILS).
February 3, 2025 at 5:08 PM
🧵(3/4) MoL achieves dense retrieval-level speed on GPUs, while delivering 20-30% better Hit Rate@50-400 on 100M+ item DBs (arxiv.org/abs/2306.04039, arxiv.org/abs/2407.13218). These gains make a compelling case for migrating web-scale vector databases to Retrieval with Learned Similarities (RAILS).
🧵(2/4) Our paper introduces Mixture-of-Logits (MoL) - a universal approximator of similarity functions unifying sparse/dense retrieval, multi-embeddings, and generative approaches. Beyond theory, MoL achieves SotA from sequential retrieval on Transformers/HSTU to finetuning LMs for RAG/QA.
February 3, 2025 at 5:08 PM
🧵(2/4) Our paper introduces Mixture-of-Logits (MoL) - a universal approximator of similarity functions unifying sparse/dense retrieval, multi-embeddings, and generative approaches. Beyond theory, MoL achieves SotA from sequential retrieval on Transformers/HSTU to finetuning LMs for RAG/QA.
🧵(1/4) Interested in the next generation retrieval paradigm or making your recommendations, search, or RAG/LLMs applications 20-30% better? Check out Retrieval with Learned Similarities, a collaboration with Microsoft Research, accepted as an oral presentation (155 out of 2062 papers) at WWW 2025!
February 3, 2025 at 5:08 PM
🧵(1/4) Interested in the next generation retrieval paradigm or making your recommendations, search, or RAG/LLMs applications 20-30% better? Check out Retrieval with Learned Similarities, a collaboration with Microsoft Research, accepted as an oral presentation (155 out of 2062 papers) at WWW 2025!