Related papers: ALTA: Compiler-Based Analysis of Transformers

Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware. Current deep compilers typically predetermine layouts of tensors and then optimize loops of operators. However, such…

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…

Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high…

Speech-LLM models have demonstrated great performance in multi-modal and multi-task speech understanding. A typical speech-LLM paradigm is integrating speech modality with a large language model (LLM). While the Whisper encoder was…

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction…

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization abilities of…

Recent research in mechanistic interpretability has attempted to reverse-engineer Transformer models by carefully inspecting network weights and activations. However, these approaches require considerable manual effort and still fall short…

Multilingual automatic lyrics transcription (ALT) is a challenging task due to the limited availability of labelled data and the challenges introduced by singing, compared to multilingual automatic speech recognition. Although some…

What is the computational model behind a Transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, Transformers have no…

Search-optimization problems are plentiful in scientific and engineering domains. Artificial intelligence has long contributed to the development of search algorithms and declarative programming languages geared towards solving and modeling…

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend…

Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain language models, while the pronunciation aspect is seldom touched upon. This paper applies a novel computational analysis on the…

Recent work has shown that Transformers trained from scratch can successfully solve various arithmetic and algorithmic tasks, such as adding numbers and computing parity. While these Transformers generalize well on unseen inputs of the same…

Programming languages possess rich semantic information - such as data flow - that is represented by graphs and not available from the surface form of source code. Recent code language models have scaled to billions of parameters, but model…

This paper presents a language, Alda, that supports all of logic rules, sets, functions, updates, and objects as seamlessly integrated built-ins. The key idea is to support predicates in rules as set-valued variables that can be used and…

Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contrastive learning…

Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on…

We introduce ALT, an open-source Python package created for efficient and accurate time series classification (TSC). The package implements the adaptive law-based transformation (ALT) algorithm, which transforms raw time series data into a…

In the absence of sizable training data for most world languages and NLP tasks, translation-based strategies such as translate-test -- evaluating on noisy source language data translated from the target language -- and translate-train --…

One of the key factors in language productivity and human cognition is the ability of systematic compositionality, which refers to understanding composed unseen examples of seen primitives. However, recent evidence reveals that the…