Related papers: CoTune: Co-evolutionary Configuration Tuning
Current image generation systems produce high-quality images but struggle with ambiguous user prompts, making interpretation of actual user intentions difficult. Many users must modify their prompts several times to ensure the generated…
We are exploring the problem of building an automated reasoning procedure that adaptively tunes the high-level solving strategy for a given problem. There are two main distinctive characteristics of our approach: tuning is performed solely…
Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…
A key challenge to make effective use of evolutionary algorithms is to choose appropriate settings for their parameters. However, the appropriate parameter setting generally depends on the structure of the optimisation problem, which is…
Low-Rank Adaptation (LoRA) is now the dominant method for parameter-efficient fine-tuning of large language models, but achieving a high-quality adapter often requires systematic hyperparameter tuning because LoRA performance is highly…
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…
Virtual screening applications are highly parameterized to optimize the balance between quality and execution performance. While output quality is critical, the entire screening process must be completed within a reasonable time. In fact, a…
Today's auto-tuners (e.g., AutoTVM, Ansor) generate efficient tensor programs by navigating a large search space to identify effective implementations, but they do so with opaque hardware details. Thus, their performance could fall behind…
Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions…
The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep learning software stacks and hardware accelerators is diverse…
Parameter-efficient tuning has become a trend in transferring large-scale foundation models to downstream applications. Existing methods typically embed some light-weight tuners into the backbone, where both the design and the learning of…
Mobile devices run deep learning models for various purposes, such as image classification and speech recognition. Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural…
Standard library implementations of functions like sin and exp optimize for accuracy, not speed, because they are intended for general-purpose use. But applications tolerate inaccuracy from cancellation, rounding error, and…
Application autotuning is a promising path investigated in literature to improve computation efficiency. In this context, the end-users define high-level requirements and an autonomic manager is able to identify and seize optimization…
Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…
Faced with the challenges of big data, modern cloud database management systems are designed to efficiently store, organize, and retrieve data, supporting optimal performance, scalability, and reliability for complex data processing and…
Advances in de novo synthesis of DNA and computational gene design methods make possible the customization of genes by direct manipulation of features such as codon bias and mRNA secondary structure. Codon context is another feature…
Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only…
Heterogeneous parallel systems are widely spread nowadays. Despite their availability, their usage and adoption are still limited, and even more rarely they are used to full power. Indeed, compelling new technologies are constantly…
Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in this field add…