Related papers: NRGPT: An Energy-based Alternative for GPT

Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algorithms, leading to a…

Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-trivial, as it often requires a large number of iterations…

As large language models (LLMs) scale in size and adoption, their computational and environmental costs continue to rise. Prior benchmarking efforts have primarily focused on latency reduction in idealized settings, often overlooking the…

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…

Foundational models based on the transformer architecture are currently the state-of-the-art in general language modeling, as well as in scientific areas such as material science and climate. However, training and deploying these models is…

In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. Our experiments show that EBM training can help the model…

This paper introduces ClimateGPT, a model family of domain-specific large language models that synthesize interdisciplinary research on climate change. We trained two 7B models from scratch on a science-oriented dataset of 300B tokens. For…

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks,…

Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the…

Graph neural networks are a popular variant of neural networks that work with graph-structured data. In this work, we consider combining graph neural networks with the energy-based view of Grathwohl et al. (2019) with the aim of obtaining a…

This study presents a thorough examination of various Generative Pretrained Transformer (GPT) methodologies in sentiment analysis, specifically in the context of Task 4 on the SemEval 2017 dataset. Three primary strategies are employed: 1)…

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different implementations for better performance, e.g., Post-LayerNorm…

Political scientists often grapple with data scarcity in text classification. Recently, fine-tuned BERT models and their variants have gained traction as effective solutions to address this issue. In this study, we investigate the potential…

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its novel combination of…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

In this paper, we present a study of the recent advancements which have helped bring Transfer Learning to NLP through the use of semi-supervised training. We discuss cutting-edge methods and architectures such as BERT, GPT, ELMo, ULMFit…

adaptNMT is an open-source application that offers a streamlined approach to the development and deployment of Recurrent Neural Networks and Transformer models. This application is built upon the widely-adopted OpenNMT ecosystem, and is…

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features…

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…