Related papers: Selective Lambda Lifting

Haskell, as implemented in the Glasgow Haskell Compiler (GHC), has been adding new type-level programming features for some time. Many of these features---chiefly: generalized algebraic datatypes (GADTs), type families, kind polymorphism,…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as…

This thesis concerns the implementation of Lambda Prolog, a higher-order logic programming language that supports the lambda-tree syntax approach to representing and manipulating formal syntactic objects. Lambda Prolog achieves its…

Pre-trained language models (PLMs) are increasingly being applied to code-related tasks. Although PLMs have achieved good results, they do not take into account potential high-order data correlations within the code. We propose three types…

Hardware accelerators, in particular accelerators for tensor processing, have many potential application domains. However, they currently lack the software infrastructure to support the majority of domains outside of deep learning.…

Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We…

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically…

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising acceleration method which can be divided into two categories:…

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…

Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness…

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…

High-level synthesis (HLS) is a powerful tool for developing efficient hardware accelerators that rely on specialized memory systems to achieve sufficient on-chip data reuse and off-chip bandwidth utilization. However, even with HLS,…

The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We…

To support the understanding of declarative probabilistic programming languages, we introduce a lambda-calculus with a fair binary probabilistic choice that chooses between its arguments with equal probability. The reduction strategy of the…

Probabilistic programming and the formal analysis of probabilistic algorithms are active areas of research, driven by the widespread use of randomness to improve performance. While functional correctness has seen substantial progress,…

The context of this work is the design of a software, called MEMSALab, dedicated to the automatic derivation of multiscale models of arrays of micro- and nanosystems. In this domain a model is a partial differential equation. Multiscale…

Ensuring the reproducibility of physics results is one of the crucial challenges in high-energy physics (HEP). In this study, we develop a proof-of-concept system that uses large language models (LLMs) to extract analysis procedures from…