Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
3 results for “distribution shift”
Learning Implicit Causal World Models from Multi-Agent Demonstrations
Researchers propose a new method called Implicit Causal World Models to improve multi-agent reinforcement learning by disentangling causal mechanisms from statistical correlations in offline demonstrations, enabling more robust world modeling under distribution shift.
Jul 30, 2026
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
CoEvoT is a new prompting framework that dynamically updates graph token representations during Chain-of-Thought reasoning, enabling step-wise structural evidence refinement for Graph-LLMs under distribution shift.
Jul 17, 2026
NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts
NEST is a new machine learning framework introduced in an arXiv preprint that addresses dataset-level distribution shifts in multivariate time-series forecasting by modeling data as mixtures of distinct operational regimes using a two-phase mixture-of-experts architecture.
Jul 10, 2026