Related papers: Decompose, Structure, and Repair: A Neuro-Symbolic…
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…
Recent advances in large language models have accelerated open-vocabulary EEG-to-imagined-text decoding, where non-invasive neural activity recorded during visual perception is translated into coherent natural language descriptions of…
In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. To facilitate the learning of these symbolic sequences, we…
Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured…
The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…
Symbolic Regression (SR) plays a central role in scientific knowledge discovery by distilling mathematical equations from observational data. Most existing SR methods function within a bi-level optimization framework: an outer loop that…
This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…
Discourse Representation Theory (DRT) is a formal account for representing the meaning of natural language discourse. Meaning in DRT is modeled via a Discourse Representation Structure (DRS), a meaning representation with a model-theoretic…
Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via…
The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…
Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual…
Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations…
Recent developments in mechanical, aerospace, and structural engineering have driven a growing need for efficient ways to model and analyse structures at much larger and more complex scales than before. While established numerical methods…
In this paper we propose the Structured Deep Neural Network (structured DNN) as a structured and deep learning framework. This approach can learn to find the best structured object (such as a label sequence) given a structured input (such…
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and task generalization. However, their application to structured data analysis remains fragile due to inconsistencies in schema…
Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve the personalization of sequential recommendation under various user preferences. However, it faces the challenges of large parameter…
Communication system formulation is critical for advancing 6G and future wireless technologies, yet it remains a complex, expertise-intensive task. While Large Language Models (LLMs) offer potential, existing general-purpose models often…
Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasoning tasks: optical perception systems transcribe symbols…
With the rapid development of Large Language Models (LLMs), Natural Language Explanations (NLEs) have become increasingly important for understanding model predictions. However, these explanations often fail to faithfully represent the…
Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data -- particularly to…