Related papers: Preference Distillation via Value based Reinforcem…

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tuning, posing significant hurdles in data-scarce 3D domains.…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…

While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is…

Direct Preference Optimization (DPO) has become a standard recipe for aligning large language models, yet it is still unclear what kind of change it actually induces inside the network. This paper argues that DPO does not rewrite a models…

Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…

Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood difference between chosen and rejected responses. However,…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data.…

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternative is Direct Policy Optimization (DPO), which replaces an…

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the…

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. Traditionally, KD involves training the student to mimic the teacher's output…

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally…