Related papers: M$^3$Prune: Hierarchical Communication Graph Pruni…

Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often…

The vision of 6G communication demands autonomous and resilient networking in environments without fixed infrastructure. Yet most multi-agent reinforcement learning (MARL) approaches focus on isolated stages - exploration, relay formation,…

Effectively preserving both the structural and dynamical properties during the reduction of complex networks remains a significant research topic. Existing network reduction methods based on renormalization group or sampling often face…

The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solutions for pruning the large original graph into a small and…

Coordination graphs are a central abstraction in cooperative multi-agent reinforcement learning (MARL), yet existing sparse-graph learners lack a theoretically grounded mechanism to decide which edges should exist and how much information…

Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning…

The recent progress in multi-agent deep reinforcement learning(MADRL) makes it more practical in real-world tasks, but its relatively poor scalability and the partially observable constraints raise challenges to its performance and…

Pruning is a compression method which aims to improve the efficiency of neural networks by reducing their number of parameters while maintaining a good performance, thus enhancing the performance-to-cost ratio in nontrivial ways. Of…

Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they…

The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its performance is severely constrained by the trade-off between…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper…

The rapid evolution of Retrieval-Augmented Generation (RAG) toward multimodal, high-stakes enterprise applications has outpaced the development of domain specific evaluation benchmarks. Existing datasets often rely on general-domain corpora…

Graph-based Retrieval-Augmented Generation (Graph-RAG) enhances large language models (LLMs) by structuring retrieval over an external corpus. However, existing approaches typically assume a static corpus, requiring expensive full-graph…

Large Multimodal Models (LMMs) have achieved significant success across various tasks. These models usually encode visual inputs into dense token sequences, which are then concatenated with textual tokens and jointly processed by a language…

While deeply supervised networks are common in recent literature, they typically impose the same learning objective on all transitional layers despite their varying representation powers. In this paper, we propose Hierarchically Supervised…

We introduce CLARGA, a general-purpose multimodal fusion architecture for multimodal representation learning that works with any number and type of modalities without changing the underlying framework. Given a supervised dataset, CLARGA can…

While human cognition inherently retrieves information from diverse and specialized knowledge sources during decision-making processes, current Retrieval-Augmented Generation (RAG) systems typically operate through single-source knowledge…

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…