NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
28 results for “keyword:"sample efficiency"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]FedORS: Sample-Efficient Personalized Federated Learning via Orthogonal Residual Sparse Components▼4.3k2.00
[PDF]PROSE: Enhancing Sample Efficiency in Code Generation via Plan-Aware Rollout Reorganization▼5.8k2.33
[PDF]Learning Cyber Defense with Limited Interaction: An Empirical Study of Reflective Prompt Optimization▼1.2k1.67
[PDF]Efficient Multi-Agent Reinforcement Learning under Sparse Binary Team Rewards with Few Suboptimal Prior Trajectories▲3.8k2.50
[PDF]Same Mastery, Opposite Directions: Signed Learning Progress for Prompt Revisiting in RLVR▼1.2k1.67
[PDF]Representational Manifold Hypothesis Enables Sample-efficient Online Contrastive Reinforcement Learning▲5.4k3.00
[PDF]WHEN ATTENTION FAILS ON FINITE FIELDS: GALOIS ALGEBRAIC REASONING NETWORKS WITH HARD COSET EXECUTION▲6.1k2.00
[PDF]Generate Multiple Actions, Execute One: Experience-Guided Action Selection for LLM Agent Reinforcement Learning▼4.5k2.67
[PDF]MATCHA: Bridging the Gap between Sample and Wall-Clock Efficiency in Model-Based Multi-Agent Reinforcement Learning▲4032.67
Withdrawn or desk rejected (9)
[PDF]Move, don't think: sample-efficient collision avoidance with lossy proximity sensorsWithdrawn1.67
[PDF]Seeing Globally, Detecting Locally: Injecting and Characterising Frozen Vision Transformer Priors in Object DetectionWithdrawn1.33