Related papers: Modular Linear Tokenization (MLT)

Symbolic and logic computation systems ranging from computer algebra systems to theorem provers are finding their way into science, technology, mathematics and engineering. But such systems rely on explicitly or implicitly represented…

Real-time detection of moving objects involves memorisation of features in the template image and their comparison with those in the test image. At high sampling rates, such techniques face the problems of high algorithmic complexity and…

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into discrete representations suitable for language-based processing. Discrete tokenization,…

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

We present Integer Linear Programming (ILP) Modulo Theories (IMT). An IMT instance is an Integer Linear Programming instance, where some symbols have interpretations in background theories. In previous work, the IMT approach has been…

Generalizable implicit neural representation (INR) enables a single continuous function, i.e., a coordinate-based neural network, to represent multiple data instances by modulating its weights or intermediate features using latent codes.…

Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…

A supervised machine learning (ML) based computational methodology for the design of particulate multifunctional composite materials with desired thermal conductivity (TC) is presented. The design variables are physical descriptors of the…

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Unsupervised visible-infrared person re-identification (USL-VI-ReID) endeavors to retrieve pedestrian images of the same identity from different modalities without annotations. While prior work focuses on establishing cross-modality…

Recent studies highlight various machine learning (ML)-based techniques for code clone detection, which can be integrated into developer tools such as static code analysis. With the advancements brought by ML in code understanding, ML-based…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

Single-image HDR reconstruction or inverse tone mapping (iTM) is a challenging task. In particular, recovering information in over-exposed regions is extremely difficult because details in such regions are almost completely lost. In this…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Using token representation from bidirectional language models (LMs) such as BERT is still a widely used approach for token-classification tasks. Even though there exist much larger unidirectional LMs such as Llama-2, they are rarely used to…

Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural…

When adapting Large Language Models for Recommendation (LLMRec), it is crucial to integrate collaborative information. Existing methods achieve this by learning collaborative embeddings in LLMs' latent space from scratch or by mapping from…