Reference-sampled weighted SFT with prompt-normalized Boltzmann weights induces the same policy as fixed-reference KL-regularized RLVR, with BOLT as the estimator and a finite one-shot error decomposition separating coverage, variance, and other terms.
Efficient rlhf: Reducing the memory usage of ppo
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Gradient-informed placement of LoRA parameters recovers full performance under GRPO while random placement does not, due to differences in gradient rank and stability across training regimes.
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
HybridFlow combines single- and multi-controller paradigms with a 3D-HybridEngine to deliver 1.53x to 20.57x higher throughput for various RLHF algorithms compared to prior systems.
Reinforcement learning is advanced for communication-efficient federated optimization and for preference-aligned, contextually safe policies in large language models.
citing papers explorer
-
MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
MARLaaS enables concurrent RL fine-tuning across up to 32 tasks using LoRA adapters and a disaggregated asynchronous architecture, matching single-task performance while improving accelerator utilization by 4.3x and cutting end-to-end time by 85%.