Related papers: Towards Flexible Inference in Sequential Decision …

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

We propose an algorithm for next query recommendation in interactive data exploration settings, like knowledge discovery for information gathering. The state-of-the-art query recommendation algorithms are based on sequence-to-sequence…

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error…

The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new…

We study the problem of smooth imitation learning for online sequence prediction, where the goal is to train a policy that can smoothly imitate demonstrated behavior in a dynamic and continuous environment in response to online, sequential…

Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…

Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…

Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the…

Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in…

Multimodalities provide promising performance than unimodality in most tasks. However, learning the semantic of the representations from multimodalities efficiently is extremely challenging. To tackle this, we propose the Transformer based…

In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them.…

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in…

Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, aiming to select the best-performing LLMs tailored to the domains of user queries, while managing computational resources. However,…

We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of…

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.…

The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models show state-of-the-art performance on a wide range of tasks including reading comprehension,…

We apply a Transformer architecture, specifically BERT, to learn flexible and high quality molecular representations for drug discovery problems. We study the impact of using different combinations of self-supervised tasks for pre-training,…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally due to catastrophic forgetting. Existing approaches rely on experience replay, optimization…