Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations · HackerPapers discussions

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations — HN submission

Mon, 17 Aug 2026 04:09:34 GMT

Trillion-Parameter Sequential Transducers for Generative Recommendations (2024)

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations — mentioned by tullie

Sun, 23 Mar 2025 13:29:07 GMT

The other direction that isn’t explicitly mentioned in this post is the variants of SASRec and Bert4Rec that are still trained on ID-Tokens but showing scaling laws much like LLMs. E.g. Meta’s approach https://arxiv.org/abs/2402.17152 (paper write up here: https://www.shaped.ai/blog/is-this-the-chatgpt-moment-for-re...)

Paper and discussion history. A mention is not an endorsement.

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations — mentioned by murphym

Wed, 28 Aug 2024 15:53:24 GMT

funnily enough, that's the name of their recent recommendation algorithm paper https://arxiv.org/pdf/2402.17152

Paper and discussion history. A mention is not an endorsement.

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations — HN submission

Mon, 29 Jul 2024 12:30:10 GMT

Trillion-Parameter Sequential Transducers for Generative Recommendations

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations — HN submission

Sat, 20 Apr 2024 11:55:28 GMT

Trillion-Parameter Sequential Transducers for Generative Recommendations

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.