Dynamic Latent Routing
We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the "search, select, update" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT. Mechanistic analyses and targeted code ablations show that DLR learns structured routing behaviors with distinct causal roles.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compress them into a unified end-to-end mappin…
Multivariate Time Series ForecastingLAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning
Imitation learning enables robots to acquire manipulation skills from demonstrations, yet deploying a policy across tasks with heterogeneous dynamics remains challenging, as models tend to average over distinct behaviora…
ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis…
TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization
Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive reasoning by operating over continuous representations. However, the in…
Reinforcement LearningStatistic-Augmented, Decoupled MoE Routing and Aggregating in Autonomous Driving
Autonomous driving (AD) scenarios are inherently complex and diverse, posing significant challenges for a single deep learning model to effectively cover all possible conditions, such as varying weather, traffic densitie…
Semantic SegmentationAutonomous Driving