OneTrans-GSR unifies reranking and mix-ranking in recommender systems
OneTrans-GSR generates slates end-to-end with reinforcement learning and improves GMV/u by 2.63% while cutting latency by 13%.
Stories per day · 30 days
3 RSS
Relatedadaptive-computation2generative-recommendation2looprec2sequential-recommendation2collaborative-filtering1cosine-similarity1embeddings1facebook1feed1jevrec1knowledge-distillation1language-models1llm1meta1phantom-correlation1privacy1product-launch1ranking1
16 stories, newest first · one card per story
Stories tagged #recommender-systems
JevRec uses variable-length item codes for generative recommendation
On three public datasets it beat compared baselines and used less train and inference time than TIGER.
Recommender similarity can be phantom correlation from user activity
Independent consumption with unequal volume still yields strong item associations under a Rasch model.
Distillation aligns item and code spaces for generative recommenders
Item Distribution Matching lifts average Recall@10 by 15.39%, and Code Marginal Matching lifts NDCG@10 by 8.28%.
LoopRec varies recursion depth per item in sequential recommenders
A shared block and per-item exit gate beat matched fixed-depth models on public benchmarks across four backbone families.
LoopRec assigns per-item recursion depth in sequential recommenders
A shared block and per-item exit gate beat matched fixed-depth models; rarer and more recent items get deeper compute.
Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
A cosine-similarity attack recovers recommender item identities from language embeddings and can aid user re-identification.
Your Algorithm, Your Words: New Ways to Shape What You See on Facebook
Meta lets Facebook users steer Feed and Reels recommendations with their own words.
Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders
ReMaRk rewards LLM recommenders against all valid replies jointly, matching Rank-GRPO in fewer steps.
Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning
Explanatory World Models reassign delayed RL credit and beat PPO and LaRe on long-horizon tasks.
Personal-Agent Mediated Recommendation with Cross-Platform User History
PAMO trains personal LLM agents to re-rank platform recommendations using cross-platform history with fewer harmful overrides.
Yandex Introduces Sona: A Single Generative Recommender That Replaces Entire Recommendation Cascade
Yandex's Sona transformer replaced Music's recommendation cascade and lifted likes 11.42% in testing.
Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
PerTIDE transfers user-history updates from news to movies, beating a random core by 15.23 MRR.
Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation
A latent preference model lifts YouTube Shorts viewer enjoyment 2.67% by correcting watch-time confounders.
FlashVector: Agent for Hierarchical Model Serving Stack Optimization
FlashVector agent optimizes all layers of Unity's ad-serving stack, delivering up to 2x model-server throughput and 1.98x latency speedup in production.
Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD
A 302-participant study finds engagement-optimized short-form video recommenders cause disproportionate time blindness and distress for users with ADHD.