Skip to main content

Research Papers

Graph Retrieval-Augmented Generation: A Survey [https://arxiv.org/pdf/2408.08921] GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage.

VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool [https://arxiv.org/pdf/2408.08927] Verilog is a popular hardware description language for designing and modeling digital systems; thus, Verilog generation is one of the emerging areas of research to facilitate the design process. In this work, we propose VerilogCoder, a system of multiple Artificial Intelligence (AI) agents for Verilog code generation, to autonomously write Verilog code and fix syntax and functional errors using collaborative Verilog tools (i.e., syntax checker, simulator, and waveform tracer).

Temporal Reversed Training for Spiking Neural Networks with Generalized Spatio-Temporal Representation [https://arxiv.org/pdf/2408.09108] Brain-inspired spiking neural networks (SNNs) have received widespread attention. Unlike traditional artificial neural networks (ANNs), which transfer information using intensive floating-point values, SNNs transfer discrete 0-1 spikes between neurons, providing a more efficient neuromorphic computing paradigm.

Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversion [https://arxiv.org/pdf/2408.09403] Spiking neural networks (SNNs) are becoming a promising alternative to conventional artificial neural networks (ANNs) due to their rich neural dynamics and the implementation of energy-efficient neuromorphic chips.

Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [https://arxiv.org/pdf/2408.09176] Advancements in multi-agent LLM frameworks as well as emergent capabilities such as in-context learning have enabled LLMs to employ more sophisticated reasoning strategies, such as ‘chain-of-thought’ reasoning (CoT). We propose LLM-ACTR, which shows improved decision-making capabilities over LLMs by integrating intermediate representations extracted from a well-establish neuro-symbolic system: the ACT-R cognitive architecture.

Neuro-Symbolic AI for Military Applications [this is an exception that I present a paper on military defence mechanism, because it includes explanations about the civilian possibilities offered by Neuro-Symbolic AI. Otherwise I try to keep military context out of my content] [https://arxiv.org/pdf/2408.09224] Contributing to the growing body of research, this study represents a comprehensive exploration of the extensive possibilities offered by Neuro-Symbolic AI.

Siamese Multiple Attention Temporal Convolution Networks for Human Mobility Signature Identification [https://arxiv.org/pdf/2408.09230] We propose a Siamese Multiple Attention Temporal Convolutional Network (Siamese MA-TCN) to capitalize on the strengths of both TCN architecture and multi-head self-attention, enabling the proficient extraction of both local and long-term dependencies.

Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey [https://arxiv.org/pdf/2408.09675] Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain, multi-agent RL (MARL) not only need to learn the control policy but also requires consideration regarding interactions with all other agents in the environment, mutual influences among different system components, and the distribution of computational resources.

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting [https://arxiv.org/pdf/2408.09365] [Microsoft hides here its automatic prompt optimization technique for enhancing weaker models on complex task] Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. We propose Concept Distillation (CD), an automatic prompt optimization technique for enhancing weaker models on complex tasks.

ELASTIC: Efficient Linear Attention for Sequential Interest Compression [https://arxiv.org/pdf/2408.09380] New update on the transformer's attention mechanism. The quadratic computational and memory complexities of self attention have limited its scalability for modeling users' long range behaviour sequences. To address this problem, we propose ELASTIC, an Efficient Linear Attention for SequenTial Interest Compression, requiring only linear time complexity and decoupling model capacity from computational cost.

Attention is a smoothed cubic spline [https://arxiv.org/pdf/2408.09624] The attention module in a transformer is a smoothed cubic spline. Viewed in this manner, this mysterious but critical component of a transformer becomes a natural development of an old notion deeply entrenched in classical approximation theory.

Source: code_your_own_AI