arXiv AI
Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Sep 15
Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
On-policy distillation (OPD) has emerged as an effective approach for large language model post-training, yet existing objectives face a trade-off between objective fidelity and optimization stability...
arXiv AI
Aug 26
On-policy Distillation with Verifiable Reward
arXiv:2608.24696v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training lar...
arXiv AI
Sep 1
Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
arXiv:2605.06387v4 Announce Type: replace-cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy dist...
Hugging Face Trending Papers
Sep 23
Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following
Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tuned models still routinely violate some of them. E...
arXiv Machine Learning
Jul 22
H$^2$SD: Hybrid Hindsight Self-Distillation
arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.
arXiv Machine Learning
Jun 19
A Survey of On-Policy Distillation for Large Language Models
arXiv:2604. 00626v4 Announce Type: replace Abstract: As Large Language Models continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become an important engineering problem, and knowledge distillation remains a common technique for this transfer.