Related papers: Paragon: Parameter Generation for Controllable Mul…

Task-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods. How to trade off performance and model parameters is an important and difficult…

Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost…

This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…

Multi-objective optimization is key to solving many Engineering Design problems, where design parameters are optimized for several performance indicators. However, optimization results are highly dependent on how the designs are…

In this paper we introduce paraglide, a visualization system designed for interactive exploration of parameter spaces of multi-variate simulation models. To get the right parameter configuration, model developers frequently have to go back…

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative…

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

Complex networks theory has commonly been used for modelling and understanding the interactions taking place between the elements composing complex systems. More recently, the use of generative models has gained momentum, as they allow…

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Multimodal recommender systems improve the performance of canonical recommender systems with no item features by utilizing diverse content types such as text, images, and videos, while alleviating inherent sparsity of user-item interactions…

Model predictive control (MPC) is increasingly being considered for control of fast systems and embedded applications. However, the MPC has some significant challenges for such systems. Its high computational complexity results in high…

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However, the gaps between…

For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them. However, tuning these hyperparameters can come at a high computational cost, especially on larger datasets,…

This work addresses the problem of robot manipulation tasks under unknown dynamics, such as pick-and-place tasks under payload uncertainty, where active exploration and(/for) online parameter adaptation during task execution are essential…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

A variety of autonomous navigation algorithms exist that allow robots to move around in a safe and fast manner. However, many of these algorithms require parameter re-tuning when facing new environments. In this paper, we propose PTDRL, a…

Modern recommender systems lie at the heart of complex ecosystems that couple the behavior of users, content providers, advertisers, and other actors. Despite this, the focus of the majority of recommender research -- and most practical…

We explore a data-driven approach for learning to optimize neural networks. We construct a dataset of neural network checkpoints and train a generative model on the parameters. In particular, our model is a conditional diffusion transformer…

Future computing systems, from handhelds to supercomputers, will undoubtedly be more parallel and heterogeneous than todays systems to provide more performance and energy efficiency. Thus, GPUs are increasingly being used to accelerate…