Related papers: Countering Language Drift with Seeded Iterated Lea…

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods often focus on datasets collected from experts to produce a…

Recently, there has been an increasing need to develop agents capable of solving multiple tasks within the same environment, especially when these tasks are naturally associated with language. In this work, we propose a novel approach that…

Recent advancements in machine learning provide methods to train autonomous agents capable of handling the increasing complexity of sequential decision-making in robotics. Imitation Learning (IL) is a prominent approach, where agents learn…

Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive…

Multi-agent debate - multiple instances of large language models discussing problems in turn-based interaction - has shown promise for solving knowledge and reasoning tasks. However, these methods show limitations when solving complex…

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…

Spoken language understanding (SLU) acts as a critical component in goal-oriented dialog systems. It typically involves identifying the speakers intent and extracting semantic slots from user utterances, which are known as intent detection…

Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural…

Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities…

In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL), a hybrid end-to-end control policy that combines the sparse expert driving knowledge with reinforcement learning (RL) policy for autonomous driving (AD) task in CARLA…

Controlled text perturbation is useful for evaluating and improving model generalizability. However, current techniques rely on training a model for every target perturbation, which is expensive and hard to generalize. We present Tailor, a…

Simultaneous Machine Translation (SiMT) generates target translations while reading the source sentence. It relies on a policy to determine the optimal timing for reading sentences and generating translations. Existing SiMT methods…

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, recent investigations find that most-if…

In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic…

In this paper, we explore multi-task learning (MTL) as a second pretraining step to learn enhanced universal language representation for transformer language models. We use the MTL enhanced representation across several natural language…

Multi-agent inverse reinforcement learning (MIRL) can be used to learn reward functions from agents in social environments. To model realistic social dynamics, MIRL methods must account for suboptimal human reasoning and behavior.…