Related papers: SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer…

Financial regulations are increasingly complex, hindering automated compliance-especially the maintenance of logical consistency with minimal human oversight. We introduce a Neuro-Symbolic Compliance Framework that integrates Large Language…

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like…

As machine learning models increase in scale and complexity, obtaining sufficient training data has become a critical bottleneck due to acquisition costs, privacy constraints, and data scarcity in specialised domains. While synthetic data…

Tabular data synthesis is crucial in machine learning, yet existing general methods-primarily based on statistical or deep learning models-are highly data-dependent and often fall short in recommender systems. This limitation arises from…

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Large language models (LLMs) have demonstrated impressive capabilities in generating software code for high-level programming languages such as Python and C++. However, their application to hardware description languages, such as Verilog,…

Retrieval-Augmented Generation (RAG) is essential for integrating external knowledge into Large Language Model (LLM) outputs. While the literature on RAG is growing, it primarily focuses on systematic reviews and comparisons of new…

Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance, and material science. Existing Large (Multimodal) Language…

What mathematical functions do neural network components learn? Symbolic distillation addresses this question by expressing neural network components with interpretable, closed-form mathematical expressions that expose the functional…

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information. However, practical deployment is fundamentally constrained by the LLM's finite…

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, when applied to hardware description languages (HDL), these models exhibit significant limitations due to data…

Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still struggle with generating non-factual responses due to limitations…

The advancement of large language models (LLMs) is critically dependent on the availability of high-quality datasets for Supervised Fine-Tuning (SFT), alignment tasks like Direct Preference Optimization (DPO), etc. In this work, we present…

Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning. This paper introduces a novel neurosymbolic…

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing…

We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybrid CNN-LSTM…

It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints. One way to do this for classification tasks is via dataset synthesis, which can be…

With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturing global dependencies in video content and accommodating…

Large language models (LLMs) struggle with relation completion (RC), both with and without retrieval-augmented generation (RAG), particularly when the required information is rare or sparsely represented. To address this, we propose a novel…