From the 5 of 24 papers with an AI index.
76 citations
- Stanford UniversityUS2 papers
- University of MichiganUS2 papers
- Amsterdam University of the ArtsNL1 paper
- Auburn UniversityUS1 paper
- Cambridge SchoolPT1 paper
- Carnegie Mellon UniversityUS1 paper
- Center for Integrated NanotechnologiesUS1 paper
- Chalmers University of TechnologySE1 paper
- Commonwealth Scientific and Industrial Research OrganisationAU1 paper
- Community Farm AllianceUS1 paper
- Department of Mathematical SciencesRU1 paper
- Depomed (United States)US1 paper
24 papers
Detecting Safety Training Modification in Language Models via Activation Analysis
Glen Messenger
We introduce AMS (Activation-based Model Scanner), a tool that detects modifications to safety training in language models by measuring the geometric structure of safety-relevant c…
Reproducing LightMem: Naive RAG Is Just as Good for Memory Management
Yongjie Zhou, Shuai Wang, Bevan Koopman +1
Long-term conversational agents require access to information from earlier interactions, such as a user's preferences, past requests, or previously mentioned facts. Repeatedly prov…
Differentiable Approximations for Distance Queries
Ahmed Abdelkader, David M. Mount
The widespread use of gradient-based optimization has motivated the adaptation of various classical algorithms into differentiable solvers compatible with learning pipelines. In th…
Heterogeneous Ranking in Industrial-Scale Recommender Systems: A Case Study
Di Bai, Jintao Liu, Zhenwei Tang +3
The paper describes an industrial case study of ranking heterogeneous content feeds in Google Discover using a heterogeneity-adaptive multi-gated mixture-of-experts model (HA-MoE)…
Planning Waste-to-Energy-Coupled AI Data Centers Through Grade-Matched Cooling and Corridor Screening
Qi He, Chunyu Qu, Wenjie Zuo
The paper proposes a screening framework that uses waste‑to‑energy plant heat to provide cooling for AI data centers, evaluating how far the thermal energy can be delivered along a…
Breaking the Loop: An Empirical Comparison of Strategies for Novelty and Freshness in YouTube Music
Srivaths Ranganathan, Zihuan Diao, Bernardo Cunha +7
Continuously trained ranking models in music recommenders fall into feedback loops where previously consumed items dominate recommendations. This suppresses two distinct content cl…