相关论文: How to Leverage Demonstration Data in Alignment fo…

Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the principle of hindsight learning: by observing states visited…

We address the problem of imitation learning with multi-modal demonstrations. Instead of attempting to learn all modes, we argue that in many tasks it is sufficient to imitate any one of them. We show that the state-of-the-art methods such…

Despite rapid progress in large language models (LLMs), the statistical structure of their weights, activations, and gradients-and its implications for initialization, training dynamics, and efficiency-remains largely unexplored. We…

Assembly state recognition facilitates the execution of assembly procedures, offering feedback to enhance efficiency and minimize errors. However, recognizing assembly states poses challenges in scalability, since parts are frequently…

Tabular data is foundational to predictive modeling in various crucial industries, including healthcare, finance, retail, sustainability, etc. Despite the progress made in specialized models, there is an increasing demand for universal…

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that…

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the…

Rank-based statistical metrics, such as the invariant statistical loss (ISL), have recently emerged as robust and practically effective tools for training implicit generative models. In this work, we introduce dual-ISL, a novel…

We present ImplicitSLIM, a novel unsupervised learning approach for sparse high-dimensional data, with applications to collaborative filtering. Sparse linear methods (SLIM) and their variations show outstanding performance, but they are…

This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning…

Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the…

Generalized zero-shot learning(GZSL) aims to classify samples from seen and unseen labels, assuming unseen labels are not accessible during training. Recent advancements in GZSL have been expedited by incorporating…

Imitation learning (IL) aims to learn a policy from expert demonstrations and has been applied to various applications. By learning from the expert policy, IL methods do not require environmental interactions or reward signals. However,…

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by using potentially erroneous pseudo-labels is still not well understood. To deepen the understanding…

Large Language Models (LLMs) have recently gained the In-Context Learning (ICL) ability with the models scaling up, allowing them to quickly adapt to downstream tasks with only a few demonstration examples prepended in the input sequence.…

RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representations to improve generalization for robotic manipulation. Visual foundation models enable…