相关论文: Rubric-based On-policy Distillation

We study off-policy learning (OPL) in contextual bandits, which plays a key role in a wide range of real-world applications such as recommendation systems and online advertising. Typical OPL in contextual bandits assumes an unconstrained…

As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-resource, budget-constrained settings? While large VLMs offer…

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Knowledge distillation (KD) aims to distill the knowledge from the teacher (larger) to the student (smaller) model via soft-label for the efficient neural network. In general, the performance of a model is determined by accuracy, which is…

Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…

Policy gradient methods are a vital ingredient behind the success of modern reinforcement learning. Modern policy gradient methods, although successful, introduce a residual error in gradient estimation. In this work, we argue that this…

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)…

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

Knowledge Distillation (KD) is a fundamental technique for compressing large language models (LLMs) into compact, efficient student models. However, existing white-box KD methods mainly focus on balancing ground truth and student-generated…

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

The shift toward interacting with frozen, "black-box" Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a critical optimization challenge. We propose a Reinforcement Learning (RL) framework for…

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher…

Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However,…

Formative assessment in STEM topics aims to promote student learning by identifying students' current understanding, thus targeting how to promote further learning. Previous studies suggest that the assessment performance of current…

Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment…

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…

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…

The off-policy paradigm casts recommendation as a counterfactual decision-making task, allowing practitioners to unbiasedly estimate online metrics using offline data. This leads to effective evaluation metrics, as well as learning…