Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
4 results for “model-agnostic”
SPOTting the Future: Lookahead Explanations for Deep Reinforcement Learning
Researchers introduced SPOT, a model-agnostic, sampling-based framework for generating lookahead explanations of deep reinforcement learning policies by constructing finite-horizon decision trees via environment simulation.
Aug 12, 2026
Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes
Researchers propose a model-agnostic, post-hoc sentence-level attribution method for proprietary LLMs using an Energy-Based Model surrogate to quantify prompt influence without repeated API calls.
Aug 5, 2026
Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning
A new model-agnostic framework for learning downstream rewards to optimize long-term user engagement in recommender systems has been proposed and deployed across multiple Pinterest surfaces, addressing sparse and delayed retention signals.
Jul 18, 2026
Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates
A new training technique called 'exogenous dropout' improves robustness of time series forecasting models to corrupted or missing exogenous covariates without sacrificing clean-data accuracy, and is released as an open benchmark and baseline recommendation.
Jul 9, 2026