Image de couverture de livre

Lever: Inference-Time Policy Reuse under Support Constraints

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vitenko, Ihor, Ibrahim, Noha, Amer-Yahia, Sihem
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Optimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition
par: Silva, Ricardo Pedro Querido Andrade, et autres
Publié: (2026)

Producer-Fairness in Sequential Bundle Recommendation
par: Rio, Alexandre, et autres
Publié: (2025)

A Sampling-based Framework for Hypothesis Testing on Large Attributed Graphs
par: Wang, Yun, et autres
Publié: (2024)

Personalized Top-k Set Queries Over Predicted Scores
par: Nia, Sohrab Namazi, et autres
Publié: (2025)

Lever: Speculative LLM Inference on Smartphones
par: Wang, Tuowei, et autres
Publié: (2026)

Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
par: Queeney, James, et autres
Publié: (2022)

On the Reuse Bias in Off-Policy Reinforcement Learning
par: Ying, Chengyang, et autres
Publié: (2022)

Policy Constraint by Only Support Constraint for Offline Reinforcement Learning
par: Gao, Yunkai, et autres
Publié: (2025)

Knockoffs Inference under Privacy Constraints
par: Cai, Zhanrui, et autres
Publié: (2025)

Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control
par: Kendiukhov, Ihor
Publié: (2026)

Efficient Biological Data Acquisition through Inference Set Design
par: Neporozhnii, Ihor, et autres
Publié: (2024)

Tight Sample Complexity Bounds for Entropic Best Policy Identification
par: Essakine, Amer, et autres
Publié: (2026)

Reusing Trajectories in Policy Gradients Enables Fast Convergence
par: Montenegro, Alessandro, et autres
Publié: (2025)

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics
par: Kendiukhov, Ihor
Publié: (2026)

KoopAGRU: A Koopman-based Anomaly Detection in Time-Series using Gated Recurrent Units
par: Yahia, Issam Ait, et autres
Publié: (2025)

Selection of the Best Policy under Fairness Constraints for Subpopulations
par: Zhu, Tingyu, et autres
Publié: (2026)

Optimal Policy Learning under Budget and Coverage Constraints
par: Cerulli, Giovanni
Publié: (2026)

Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
par: Yang, Xu, et autres
Publié: (2023)

Quantifying Ranking Instability Across Evaluation Protocol Axes in Gene Regulatory Network Benchmarking
par: Kendiukhov, Ihor
Publié: (2026)

A Review of Developmental Interpretability in Large Language Models
par: Kendiukhov, Ihor
Publié: (2025)

ContextPilot: Fast Long-Context Inference via Context Reuse
par: Jiang, Yinsicheng, et autres
Publié: (2025)

Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence
par: Kendiukhov, Ihor
Publié: (2026)

Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
par: Kendiukhov, Ihor
Publié: (2026)

What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
par: Kendiukhov, Ihor
Publié: (2026)

Multi-Dimensional Spectral Geometry of Biological Knowledge in Single-Cell Transformer Representations
par: Kendiukhov, Ihor
Publié: (2026)

Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
par: Kendiukhov, Ihor
Publié: (2026)

Data as a Lever: A Neighbouring Datasets Perspective on Predictive Multiplicity
par: Ganesh, Prakhar, et autres
Publié: (2025)

DARE: Diffusion Language Model Activation Reuse for Efficient Inference
par: Frumkin, Natalia, et autres
Publié: (2026)

Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach
par: Panda, Subhodip, et autres
Publié: (2025)

ICaRus: Identical Cache Reuse for Efficient Multi Model Inference
par: Woo, Sunghyeon, et autres
Publié: (2026)

Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
par: Gao, Shiqing, et autres
Publié: (2024)

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
par: Pravetz, Thomas
Publié: (2026)

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
par: Gu, Zhuohan, et autres
Publié: (2024)

Inference Time Policy Optimization for Offline RL with Differentiable World Models
par: Deb, Rohan, et autres
Publié: (2026)

Estimation of Optimal Dynamic Treatment Assignment Rules under Policy Constraints
par: Sakaguchi, Shosei
Publié: (2021)

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs
par: Gangavarapu, Tushaar, et autres
Publié: (2026)

Fortytwo: Swarm Inference with Peer-Ranked Consensus
par: Larin, Vladyslav, et autres
Publié: (2025)

Semiparametric Off-Policy Inference for Optimal Policy Values under Possible Non-Uniqueness
par: Wei, Haoyu
Publié: (2025)

Towards Principled Design of Mixture-of-Experts Language Models under Memory and Inference Constraints
par: Liew, Seng Pei, et autres
Publié: (2026)

MDP Planning as Policy Inference
par: Tolpin, David
Publié: (2026)