Related papers: SequenceMatch: Imitation Learning for Autoregressi…

End-to-end autonomous driving is typically built upon imitation learning (IL), yet its performance is constrained by the quality of human demonstrations. To overcome this limitation, recent methods incorporate reinforcement learning (RL)…

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present…

While pre-trained large-scale deep models have garnered attention as an important topic for many downstream natural language processing (NLP) tasks, such models often make unreliable predictions on out-of-distribution (OOD) inputs. As such,…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

In this work, we propose MixMOOD - a systematic approach to mitigate effect of class distribution mismatch in semi-supervised deep learning (SSDL) with MixMatch. This work is divided into two components: (i) an extensive out of distribution…

We present a novel view that unifies two frameworks that aim to solve sequential prediction problems: learning to search (L2S) and recurrent neural networks (RNN). We point out equivalences between elements of the two frameworks. By…

We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered…

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that…

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…

We consider the problem of Imitation Learning (IL) by actively querying noisy expert for feedback. While imitation learning has been empirically successful, much of prior work assumes access to noiseless expert feedback which is not…

Deep learning models have proven to be effective on medical datasets for accurate diagnostic predictions from images. However, medical datasets often contain noisy, mislabeled, or poorly generalizable images, particularly for edge cases and…

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…

Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…

Non-autoregressive translation models (NAT) have achieved impressive inference speedup. A potential issue of the existing NAT algorithms, however, is that the decoding is conducted in parallel, without directly considering previous context.…

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation patterns while avoiding the forgetting of previous…

Imitation learning (IL) is a frequently used approach for data-efficient policy learning. Many IL methods, such as Dataset Aggregation (DAgger), combat challenges like distributional shift by interacting with oracular experts.…

In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without needing further training. This has led to claims about these model's ability to solve (learn) unseen tasks with only a few…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…