Related papers: Reconsidering the Past: Optimizing Hidden States i…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Bilevel optimization (BO) has recently gained prominence in many machine learning applications due to its ability to capture the nested structure inherent in these problems. Recently, many hypergradient methods have been proposed as…

Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of…

We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that…

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Large pre-trained language models (PLMs) have garnered significant attention for their versatility and potential for solving a wide spectrum of natural language processing (NLP) tasks. However, the cost of running these PLMs may be…

In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word embeddings suffers…

Text summarization is a crucial task that requires the simultaneous optimization of multiple objectives, including consistency, coherence, relevance, and fluency, which presents considerable challenges. Although large language models (LLMs)…

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we…

The paper presents an overview of the Spoken Language Translator (SLT) system's hybrid language-processing architecture, focussing on the way in which rule-based and statistical methods are combined to achieve robust and efficient…

We consider the problem of learning observation models for robot state estimation with incremental non-differentiable optimizers in the loop. Convergence to the correct belief over the robot state is heavily dependent on a proper tuning of…

Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…

It is often advantageous to train models on a subset of the available train examples, because the examples are of variable quality or because one would like to train with fewer examples, without sacrificing performance. We present Gradient…

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…

Many NLP researchers rely on free computational services, such as Google Colab, to fine-tune their Transformer models, causing a limitation for hyperparameter optimization (HPO) in long-text classification due to the method having quadratic…