Aishan Liu

Aegis, trained with CyberFactory, outperforms existing models by 22.8 points in cybersecurity tasks, showcasing the power of agentic learning in real-world applications.

SafeGen boosts VLMAD performance by over 24% in safety-critical scenario generation, bridging the sim-to-real gap that has long plagued autonomous driving systems.

Adversarial attacks on vision-language agents reveal critical vulnerabilities, with multi-view optimization strategies proving significantly more effective than isolated approaches.

Environmental illusions can degrade lane detection accuracy by over 7%, posing serious safety risks for autonomous vehicles.

Malicious instructions hidden in images can bypass existing skill scanners, exposing a critical vulnerability in LLM-based systems.

LLM agents can achieve near-impregnable defense against prompt injection with minimal utility loss by borrowing classic operating system virtualization techniques.

Text-to-image models can be tricked into generating images containing malicious text with over 90% success, even when standard jailbreak methods fail.

Industrial code generation gets a reasoning boost: InCoder-32B-Thinking leverages error-driven feedback and a code world model to achieve top-tier performance on complex hardware-aware tasks.

A new 32B code LLM trained specifically for industrial tasks crushes existing models on specialized domains like chip design and GPU kernel optimization, while remaining competitive on general coding benchmarks.