LLM Digest

Story

arxiv_llm_reliability · Nov 4, 2026 · paper

Source brief

Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models

arxiv.orgNov 4, 2026
original source linked

In brief

Multimodal large reasoning models (MLRMs) integrate visual inputs with textual and parametric knowledge, allowing sensitive information to be accessed through cross-modal associations during reasoning. This raises privacy concerns when a visual input should no longer provide acce

Read the original at arxiv.org →Open in live feed Read that day’s brief

Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models

Earlier in this thread 4 items

Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection

SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models

Show HN: MoEShift - Faster large MoE inference with half the RAM