Related papers: Reinforcement Guided Multi-Task Learning Framework…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

Obtaining labeled data to train a model for a task of interest is often expensive. Prior work shows training models on multitask data augmented with task descriptions (prompts) effectively transfers knowledge to new tasks. Towards…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

With the rise of generative language models, machine-generated text detection has become a critical challenge. A wide variety of models is available, but inconsistent datasets, evaluation metrics, and assessment strategies obscure…

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires…

Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on…

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly,…

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

Many multiagent systems in the real world include multiple types of agents with different abilities and functionality. Such heterogeneous multiagent systems have significant practical advantages. However, they also come with challenges…

Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across various visual tasks. However, most existing judge models are optimized for single-task scenarios…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Multilingual studies of social bias in open-ended LLM generation remain limited: most existing benchmarks are English-centric, template-based, or restricted to recognizing pre-specified stereotypes. We introduce StereoTales, a multilingual…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…