Related papers: On-Policy Adversarial Flow Distillation for Autore…

We introduce Proximal Policy Distillation (PPD), a novel policy distillation method that integrates student-driven distillation and Proximal Policy Optimization (PPO) to increase sample efficiency and to leverage the additional rewards that…

Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown that robustness against adversarial attacks can also be…

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is…

Diffusion models have achieved remarkable success in video generation; however, the high computational cost of the denoising process remains a major bottleneck. Existing approaches have shown promise in reducing the number of diffusion…

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser…

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of response tokens…

Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Deep learning models are vulnerable to adversarial examples, posing critical security challenges in real-world applications. While Adversarial Training (AT ) is a widely adopted defense mechanism to enhance robustness, it often incurs a…

Adversarial Robustness Distillation (ARD) is a novel method to boost the robustness of small models. Unlike general adversarial training, its robust knowledge transfer can be less easily restricted by the model capacity. However, the…

Model distillation enables efficient emulation of frontier large language models (LLMs), creating a need for robust mechanisms to detect when a third-party student model has trained on a teacher model's outputs. However, existing…

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…

Policy Distillation (PD) has become an effective method to improve deep reinforcement learning tasks. The core idea of PD is to distill policy knowledge from a teacher agent to a student agent. However, the teacher-student framework…

On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for improving reasoning while avoiding the reward dependence of reinforcement learning and the…

Adversarial training has been widely explored for mitigating attacks against deep models. However, most existing works are still trapped in the dilemma between higher accuracy and stronger robustness since they tend to fit a model towards…