KuaiRand
PulseAugur coverage of KuaiRand — every cluster mentioning KuaiRand across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New evaluator SurvEval improves recommender system re-ranking assessment
Researchers have developed SurvEval, a novel listwise evaluator designed to improve the assessment of re-ranking stages in recommender systems. Unlike existing methods that simplify user browsing assumptions and aggrega…
-
New Audit Method for Recommendation Logs Published on arXiv
A new research paper introduces a paired-support audit method for recommendation logs, utilizing the KuaiRand dataset. The study found that while user demeaning can significantly reduce absolute mean absolute error, it …
-
New RL methods enhance LLM reasoning with fine-grained credit assignment · 9 sources tracked
Researchers are developing new methods for credit assignment in reinforcement learning (RL) for large language models (LLMs) to improve their reasoning and decision-making capabilities. Several papers propose novel fram…
-
ChronicleRec framework compresses user behavior for improved recommendation systems
Researchers have developed ChronicleRec, a novel framework for pre-training and transferring user behavior models. This method compresses ultra-long historical action sequences into chronologically ordered "Chronicle To…
-
New framework improves ad pacing with calibrated uncertainty
A new research paper introduces a decision-calibrated conformal framework designed to improve pacing decisions in streaming advertising. This framework addresses uncertainties in future inventory, demand, and user exper…
-
New framework aids online experiment design under unknown interference
A new research paper introduces a framework for selecting online experiment designs when the mechanism of interference is unknown. The proposed method, called robust design selection, evaluates six different designs bas…