ArXiv TLDR

Hui Li

7 papers ยท Latest:

Cryptography & Security

SecGoal: A Benchmark for Security Goal Extraction and Formalization from Protocol Documents

This paper introduces SecGoal, a benchmark and AI-assisted framework for extracting and formalizing security goals from protocol documents.

2604.27601
Statistical Machine Learning

Probabilistic data quality assessment for structural monitoring data via outlier-resistant conditional diffusion model

This paper introduces an outlier-resistant conditional diffusion model for probabilistic data quality assessment in structural health monitoring.

2604.26366

Adaptive Meta-Learning Stochastic Gradient Hamiltonian Monte Carlo Simulation for Bayesian Updating of Structural Dynamic Models

Introduces AM-SGHMC, an adaptive meta-learning SGHMC algorithm for efficient Bayesian updating of structural dynamic models without retraining.

2604.25710
Galaxies & Cosmology

Probing the Hot Gaseous Halos of Milky Way-like Galaxies in the TNG50 simulation

TNG50 simulation's Milky Way-like galaxy halos are too compact and lack hotter gas, suggesting issues with its feedback model.

2604.24494
Artificial Intelligence

SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context

SWE-AGILE is a software agent framework that uses dynamic context management to improve reasoning depth and efficiency in multi-turn SWE tasks.

2604.11716
Robotics

Learning Task-Invariant Properties via Dreamer: Enabling Efficient Policy Transfer for Quadruped Robots

DreamTIP integrates Task-Invariant Properties into Dreamer's world model for efficient sim-to-real transfer, enabling robust quadruped robot locomotion.

2604.02911
Natural Language Processing

Gemini: A Family of Highly Capable Multimodal Models

Gemini is a new family of multimodal AI models excelling in image, audio, video, and text understanding, achieving state-of-the-art results across numerous benchmarks including human-expert level on MMLU.

2312.11805

๐Ÿ“ฌ Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week โ€” summarized, scored, and delivered to your inbox every Monday.