collaborators

7 papers

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.LG2026

The Appeal and Reality of Recycling LoRAs with Adaptive Merging

Haokun Liu, Gyung Hyun Je, Marco Ciccone +3

The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These m…

cs.CR2026

From Storage to Steering: Memory Control Flow Attacks on LLM Agents

Zhenlin Xu, Xiaogang Zhu, Yu Yao +2

Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and executio…

cs.CV2026

PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models

Jiahui Guang, Zexun Zhan, Zhenlin Xu +5

Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmarks rely on synthetic knowledge…

cs.AI2026

Voxtral Realtime

Mistral-AI, :, Alexander H. Liu +166

We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…

cs.CV2025

Spherical Leech Quantization for Visual Tokenization and Generation

Yue Zhao, Hanwen Jiang, Zhenlin Xu +3

Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of…