Papers

  • Hierarchical Graph Topic Modeling with Topic Tree-based Transformer

    Textual documents are commonly connected in a hierarchical graph structure where a central document links to others with an exponentially growing connectivity. Though Hyperbolic Graph Neural Networks (HGNNs) excel at capturing such graph hierarchy, they cannot model the rich textual semantics within documents. Moreover, text contents in documents usually discuss …

  • Spectra and pseudospectra in the evaluation of material stability in phase field schemes

    We consider the dynamics of bodies with "active" microstructure described by vector-valued phase fields. For waves with time-varying amplitude, the associated evolution equation involves a matrix that can be non-normal, depending on the constitutive choices adopted for the microstructural actions associated with the considered phase field. The occurrence of non-normality …

  • Continuous Diffusion Model for Language Modeling

    Diffusion models have emerged as a promising alternative to autoregressive models in modeling discrete categorical data. Yet diffusion models that directly work on discrete data space do not fully exploit the power of iterative refinement, as the signals are lost during the transition between discrete states. Existing continuous diffusion models …

  • LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization

    We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates domain-specific knowledge extracted from natural language, enhanced through a retrieval-augmented generation (RAG) pipeline, to seamlessly integrate data-driven modeling with …

  • PropNet: a White-Box and Human-Like Network for Sentence Representation

    Transformer-based embedding methods have dominated the field of sentence representation in recent years. Although they have achieved remarkable performance on NLP missions, such as semantic textual similarity (STS) tasks, their black-box nature and large-data-driven training style have raised concerns, including issues related to bias, trust, and safety. Many efforts have …

  • MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation

    Memes present unique moderation challenges due to their subtle, multimodal interplay of images, text, and social context. Standard systems relying predominantly on explicit textual cues often overlook harmful content camouflaged by irony, symbolism, or cultural references. To address this gap, we introduce MemeSense, an adaptive in-context learning framework that fuses …

  • Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information

    Offline Reinforcement Learning (RL) focuses on learning policies solely from a batch of previously collected data. of- fering the potential to leverage such datasets effectively without the need for costly or risky active exploration. While recent advances in Offline Multi-Agent RL (MARL) have shown promise, most existing methods either rely …

  • Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models

    Despite the advanced capabilities of large language models (LLMs), their temporal reasoning ability remains underdeveloped. Prior works have highlighted this limitation, particularly in maintaining temporal consistency when understanding events. For example, models often confuse mutually exclusive temporal relations like ``before'' and ``after'' between events and make inconsistent predictions. In this …