activity
20242026
collaborators

19 papers

cs.AI2026

Mitigating Over-Personalization in LLMs via Structured Memory

Hakeem Hannoon, Andrew Zhao, Mihir Narayan +2

Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user information is reintroduced into the…

cs.CL2026

Shieldstral

Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +274

We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…

cs.AI2026

Fara-1.5: Scalable Learning Environments for Computer Use Agents

Ahmed Awadallah, Sahil Gupta, Yash Lara +12

Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires two key ingredients: environment…

cs.CR2026

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

Yiran Wu, Mauricio Velazco, Andrew Zhao +9

We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Rea…

cs.AI2026

Voxtral TTS

Mistral-AI, :, Alexander H. Liu +186

We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…

cs.CR2026

The Art of Building Verifiers for Computer Use Agents

Corby Rosset, Pratyusha Sharma, Andrew Zhao +2

Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In thi…