Related papers: Tangent: Automatic differentiation using source-co…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

We propose to apply several gradient estimation techniques to enable the differentiation of programs with discrete randomness in High Energy Physics. Such programs are common in High Energy Physics due to the presence of branching processes…

Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a…

Recently, there has been a growing interest in automatic software vulnerability detection. Pre-trained model-based approaches have demonstrated superior performance than other Deep Learning (DL)-based approaches in detecting…

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video…

Automatic code generation has recently attracted large attention and is becoming more significant to the software development process. Solutions based on Machine Learning and Artificial Intelligence are being used to increase human and…

Programs involving discontinuities introduced by control flow constructs such as conditional branches pose challenges to mathematical optimization methods that assume a degree of smoothness in the objective function's response surface.…

The construction of high-quality parallel corpora for translation research has increasingly evolved from simple sentence alignment to complex, multi-layered annotation tasks. This methodological shift presents significant challenges for…

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle…

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage. In this work, we propose a novel decoding…

Python data science libraries such as Pandas and NumPy have recently gained immense popularity. Although these libraries are feature-rich and easy to use, their scalability limitations require more robust computational resources. In this…

The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used…

The recent advancements in large language models (LLMs) have been extraordinary, yet the escalating inference costs associated with them present challenges in real-world applications. To address these challenges, we propose a novel approach…

The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical "hard" prompts are made from interpretable words and tokens, and must be hand-crafted by humans. There are also "soft"…

We explore the possibility of exact algorithmic learning with gradient-based methods and introduce a differentiable framework capable of strong length generalization on arithmetic tasks. Our approach centers on Differentiable Finite-State…

Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of…

The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal attention in a…

Computing the differences between two versions of the same program is an essential task for software development and software evolution research. AST differencing is the most advanced way of doing so, and an active research area. Yet, AST…