Related papers: Critic-Driven Voronoi-Quantization for Distilling …
Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…
Diffusion policies have emerged as a powerful approach for robotic control, demonstrating superior expressiveness in modeling multimodal action distributions compared to conventional policy networks. However, their integration with online…
Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-teacher. Unlike GRPO,…
Recent advancements in reinforcement learning (RL) have led to remarkable achievements in robot locomotion capabilities. However, the complexity and ``black-box'' nature of neural network-based RL policies hinder their interpretability and…
Standard knowledge distillation for autoregressive models often suffers from distribution mismatch. While on-policy methods mitigate this by leveraging student-generated outputs, they rely on computationally expensive Reinforcement Learning…
Dataset distillation synthesizes a small dataset such that a model trained on this set approximates the performance of the original dataset. Recent studies on dataset distillation focused primarily on the design of the optimization process,…
Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under…
With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is…
Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive signals encoded in intermediate representations. In this paper,…
Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…
Large language models (LLMs) have demonstrated exceptional performance across various applications, but their conversational abilities decline sharply as model size decreases, presenting a barrier to their deployment in resource-constrained…
On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher, providing dense token-level rewards without external…
Recent years have witnessed the remarkable success of deep learning in remote sensing image interpretation, driven by the availability of large-scale benchmark datasets. However, this reliance on massive training data also brings two major…
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…
The multi-scale and non-linear nature of phase-field models of solidification requires fine spatial and temporal discretization, leading to long computation times. This could be overcome with artificial-intelligence approaches. Surrogate…
Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…
Interpreting the predictions of a black-box deep network can facilitate the reliability of its deployment. In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a…
Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…
The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…