While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyperparameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2L), a model capable of adapting large language models (LLMs) on the fly solely based on a natural language description of the target task. T2L is a hypernetwork trained to construct LoRAs in a single inexpensive forward pass. After training T2L on a suite of 9 pre-trained LoRA adapters (GSM8K, Arc, etc.), we show that the ad-hoc reconstructed LoRA instances match the performance of task-specific adapters across the corresponding test sets. Furthermore, T2L can compress hundreds of LoRA instances and zero-shot generalize to entirely unseen tasks. This approach provides a significant step towards democratizing the specialization of foundation models and enables language-based adaptation with minimal compute requirements. Our code is available at https://github.com/SakanaAI/text-to-lora

Test-driven development (TDD) is a widely-employed software development practice that mandates writing test cases based on a textual description before writing the actual code. While writing test cases is the centerpiece of TDD, it is time-consuming, expensive, and often shunned by developers. To address these issues associated with TDD, automated test case generation approaches have recently been investigated. Such approaches take source code as input, but not the textual description. Therefore, existing work does not fully support true TDD, as actual code is required to generate test cases. In addition, current deep learning-based test case generation approaches are trained with one learning objective, i.e., to generate test cases that are exactly matched with the ground-truth test cases. However, such approaches may limit the model’s ability to generate different yet correct test cases. In this paper, we introduce PyTester , a Text-to-Testcase generation approach that can automatically generate syntactically correct, executable, complete, and effective test cases while being aligned with a given textual description. We evaluate PyTester on the public APPS benchmark dataset, and the results show that our Deep RL approach enables PyTester , a small language model, to outperform much larger language models like GPT3.5, StarCoder, and InCoder. Our findings suggest that future research could consider improving small over large LMs for better resource efficiency by integrating the SE domain knowledge into the design of reinforcement learning architecture.

Human Activity Recognition (HAR) has rapidly gained interest over the years due to its wide range of applications in AI-based systems, particularly healthcare monitoring. HAR methods typically involve extracting relevant features from data provided by wearable sensors, smartphone sensors, cameras, or their combinations to classify different activities. Nevertheless, a major challenge lies in achieving high classification accuracy with limited data samples, particularly when distinguishing between activities with similar signal attributes. To address this challenge, we propose a novel HAR method called BinAry sequence-augmented spectrograM with Self-attention deep learning (BAMS). Our proposed method leverages only basic wearable sensor data. It utilizes short-time Fourier transform spectrograms to extract spatio-temporal sensor information. The spectrogram is integrated with a binary sequence that captures movement direction. We integrate a scaled dot-product self-attention mechanism into the model to prioritize data from wearable sensors, thereby enhancing the model's performance. The proposed method is evaluated on a public dataset using leave-one-subject-out cross-validation for efficacy and robustness. The method is found to achieve significant improvement over other state-of-the-art methods with the classification accuracy percentage and weighted F-1 scores of 88.06±5.11 and 87.36±5.96, respectively, for a twelve-activity classification.

Distributed Deep Reinforcement Learning (DRL) aims to leverage more computational resources to train autonomous agents with less training time. Despite recent progress in the field, reproducibility issues have not been sufficiently explored. This paper first shows that the typical actor-learner framework can have reproducibility issues even if hyperparameters are controlled. We then introduce Cleanba, a new open-source platform for distributed DRL that proposes a highly reproducible architecture. Cleanba implements highly optimized distributed variants of PPO and IMPALA. Our Atari experiments show that these variants can obtain equivalent or higher scores than strong IMPALA baselines in moolib and torchbeast and PPO baseline in CleanRL. However, Cleanba variants present 1) shorter training time and 2) more reproducible learning curves in different hardware settings.

Partner diversity is known to be crucial for training a robust generalist cooperative agent. In this paper, we show that partner specialization, in addition to diversity, is crucial for the robustness of a downstream generalist agent. We propose a principled method for quantifying both the diversity and specialization of a partner population based on the concept of mutual information. Then, we observe that the recently proposed cross-play minimization (XP-min) technique produces diverse and specialized partners. However, the generated partners are overfit, reducing their usefulness as training partners. To address this, we propose simple methods, based on reinforcement learning and supervised learning, for extracting the diverse and specialized behaviors of XP-min generated partners but not their overfitness. We demonstrate empirically that the proposed method effectively removes overfitness, and extracted populations produce more robust generalist agents compared to the source XP-min populations.