Related papers: DAIL: Beyond Task Ambiguity for Language-Condition…

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

Adversarial Imitation Learning (AIL) methods, while effective in settings with limited expert demonstrations, are often considered unstable. These approaches typically decompose into two components: Density Ratio (DR) estimation…

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

In-Context Learning (ICL) combined with pre-trained large language models has achieved promising results on various NLP tasks. However, ICL requires high-quality annotated demonstrations which might not be available in real-world scenarios.…

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy…

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single…

Various algorithms have been proposed to address the challenges posed by class-imbalanced learning from real-world data with long-tailed distributions. While these algorithms reduce prediction bias through rebalancing techniques, they often…

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

Although active learning (AL) in segmentation tasks enables experts to annotate selected regions of interest (ROIs) instead of entire images, it remains highly challenging, labor-intensive, and cognitively demanding due to the blurry and…

Generative adversarial imitation learning (GAIL) has attracted increasing attention in the field of robot learning. It enables robots to learn a policy to achieve a task demonstrated by an expert while simultaneously estimating the reward…

In recent years, much progress has been made in learning robotic manipulation policies that follow natural language instructions. Such methods typically learn from corpora of robot-language data that was either collected with specific tasks…

We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires…

Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction…

Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preference datasets is prohibitively expensive. \textit{This raises a…

Predicting the performance of highly configurable software systems is the foundation for performance testing and quality assurance. To that end, recent work has been relying on machine/deep learning to model software performance. However, a…

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…

Machine/deep learning models have been widely adopted for predicting the configuration performance of software systems. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…