Related papers: The GRADIEND Python Package: An End-to-End System …

We introduce milearn, a Python package for multi-instance learning (MIL) that follows the familiar scikit-learn fit/predict interface while providing a unified framework for both classical and neural-network-based MIL algorithms for…

Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We present GraphChain, a framework that enables LLMs to analyze complex graphs…

Aggregate programming is a field-based coordination paradigm with over a decade of exploration and successful applications across domains including sensor networks, robotics, and IoT, with implementations in various programming languages,…

This project focuses on enhancing open-source large language models through instruction-tuning and providing comprehensive evaluations of their performance. We explore how various training data factors, such as quantity, quality, and…

The evaluation of cross-lingual semantic search models is often limited to existing datasets from tasks such as information retrieval and semantic textual similarity. We introduce Cross-Lingual Semantic Discrimination (CLSD), a lightweight…

In aligning large language models (LLMs), reward models have played an important role, but are standardly trained as discriminative models and rely only on labeled human preference data. In this paper, we explore methods that train reward…

Recent progress in Graph Neural Networks (GNNs) has greatly enhanced the ability to model complex molecular structures for predicting properties. Nevertheless, molecular data encompasses more than just graph structures, including textual…

Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs)…

The rapid proliferation of large language models (LLMs) has created an unprecedented demand for fine-tuning models for specialized domains, such as medical science. While federated learning (FL) offers a decentralized and privacy-preserving…

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…

Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research…

We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of…

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

A novel interpretable end-to-end learning scheme for language identification is proposed. It is in line with the classical GMM i-vector methods both theoretically and practically. In the end-to-end pipeline, a general encoding layer is…

In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically…

Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel,…

Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, existing alignment…

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards:…

Data discovery in data lakes with ever increasing datasets has long been recognized as a big challenge in the realm of data management, especially for semantic search of and hierarchical global catalog generation of tables. While large…