Search Results for author:
Found 26 papers, 20 papers with code
Semantic Scheduling for LLM Inference
Conventional operating system scheduling algorithms are largely content-ignorant, making decisions based on factors such as latency or fairness without considering the actual intents or semantics of processes.
LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
We present AIOS 1. 0, a novel platform designed to advance computer-use agent (CUA) capabilities through environmental contextualization.
Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
Autonomous LLM-based agents have emerged as a powerful paradigm for complex task execution, yet the field lacks standardized tools for development, deployment, distribution and discovery of agents.
OmniRouter: Budget and Performance Controllable Multi-LLM Routing
LLM routing is a crucial paradigm that dynamically selects the most suitable large language models from a pool of candidates to process diverse inputs, ensuring optimal resource utilization while maintaining response quality.
iAgent: LLM Agent as a Shield between User and Recommender Systems
Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
A-MEM: Agentic Memory for LLM Agents
To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way.
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
In this paper, we show that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K) while not having such patterns in values (V) in various modern transformer-based LLMs (Q, K, and V mean the representations output by the query, key, and value layers respectively).
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e. g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics.
From Commands to Prompts: LLM-based Semantic File System for AIOS
Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems (AIOS).
AutoFlow: Automated Workflow Generation for Large Language Model Agents
We believe that the automatic generation and interpretation of workflows in natural language represent a promising paradigm for solving complex tasks, particularly with the rapid development of LLMs.
AIOS Compiler: LLM as Interpreter for Natural Language Programming and Flow Programming of AI Agents
However, the inherent vagueness, ambiguity, and verbosity of natural language pose significant challenges in developing an interpreter that can accurately understand the programming logic and execute instructions written in natural language.
Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of ``Concept Depth'' to suggest that more complex concepts are typically acquired in deeper layers.
AIOS: LLM Agent Operating System
This AIOS kernel provides fundamental services (e. g., scheduling, context management, memory management, storage management, access control) and efficient management of resources (e. g., LLM and external tools) for runtime agents.
What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents
This study introduces "CosmoAgent," an innovative artificial intelligence system that utilizes Large Language Models (LLMs) to simulate complex interactions between human and extraterrestrial civilizations.
War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
Can we avoid wars at the crossroads of history?
LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation
LightLM tackles the issue by introducing a light-weight deep and narrow Transformer architecture, which is specifically tailored for direct generation of recommendation items.
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.
OpenAGI: When LLM Meets Domain Experts
This capability is vital for Artificial Intelligence (AI) and should be embedded in comprehensive AI Agents, enabling them to harness expert models for complex task-solving towards Artificial General Intelligence (AGI).
UNICORN: A Unified Backdoor Trigger Inversion Framework
Then, it proposes a unified framework to invert backdoor triggers based on the formalization of triggers and the identified inner behaviors of backdoor models from our analysis.
Rethinking the Reverse-engineering of Trojan Triggers
On average, the detection accuracy of our method is 93\%.
Theoretical Analysis of Deep Neural Networks in Physical Layer Communication
In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity.
A Low Complexity Learning-based Channel Estimation for OFDM Systems with Online Training
Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission.
Opening the Black Box of Deep Neural Networks in Physical Layer Communication
Deep Neural Network (DNN)-based physical layer techniques are attracting considerable interest due to their potential to enhance communication systems.
Fine Timing and Frequency Synchronization for MIMO-OFDM: An Extreme Learning Approach
Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency synchronization significantly impacts the overall system performance.
Performance Analysis on Machine Learning-Based Channel Estimation
In this situation, our analysis results can be applied to assess the performance and support the design of machine learning-based channel estimation.
Deep Neural Network Aided Scenario Identification in Wireless Multi-path Fading Channels
This letter illustrates our preliminary works in deep nerual network (DNN) for wireless communication scenario identification in wireless multi-path fading channels.
