ArXiv TLDR

Bo Li

4 papers · Latest:

Natural Language Processing

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models

ML-Bench&Guard provides a policy-grounded multilingual safety benchmark and dLLM guardrail for culturally and legally aligned LLM safety.

2605.00689
Computer Vision

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

This paper proposes a new five-level taxonomy for visual generation, shifting from appearance synthesis to intelligent, agentic world modeling.

2604.28185
Cryptography & Security

MARD: A Multi-Agent Framework for Robust Android Malware Detection

MARD is a multi-agent LLM framework for robust Android malware detection, achieving high accuracy, interpretability, and cost-efficiency against concept drift.

2604.25264
Natural Language Processing

Green Shielding: A User-Centric Approach Towards Trustworthy AI

Green Shielding proposes a user-centric approach to build trustworthy AI by characterizing how benign input variations affect LLM behavior.

2604.24700

📬 Weekly AI Paper Digest

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