[2506.12104] DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Abstract page for arXiv paper 2506.12104: DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Abstract page for arXiv paper 2506.12104: DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Abstract page for arXiv paper 2505.24840: The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition
Abstract page for arXiv paper 2306.04810: Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neur...
Abstract page for arXiv paper 2502.05228: Physics-Informed Evolution: An Evolutionary Framework for Solving Quantum Control Problems Invo...
Abstract page for arXiv paper 2006.09534: Discriminative reconstruction via simultaneous dense and sparse coding
Abstract page for arXiv paper 2410.15281: LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments...
Abstract page for arXiv paper 2410.10700: LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
Abstract page for arXiv paper 2408.13366: CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers
Abstract page for arXiv paper 2406.07737: The Future of AI-Driven Software Engineering
Abstract page for arXiv paper 2404.05290: MindSet: Vision. A toolbox for testing DNNs on key psychological experiments
Abstract page for arXiv paper 2401.11605: Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
Abstract page for arXiv paper 2402.12760: A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
Abstract page for arXiv paper 2603.19091: Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
Abstract page for arXiv paper 2603.24402: AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
Abstract page for arXiv paper 2603.16951: Minimum-Action Learning: Energy-Constrained Symbolic Model Selection for Physical Law Identific...
Abstract page for arXiv paper 2603.23610: Environment Maps: Structured Environmental Representations for Long-Horizon Agents
Abstract page for arXiv paper 2602.00079: Embedding Compression via Spherical Coordinates
Abstract page for arXiv paper 2603.19042: Man and machine: artificial intelligence and judicial decision making