LLM Digest

Story

arxiv_cs_ai · Oct 7, 2026 · paper

Source brief

Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning

arxiv.orgOct 7, 2026
original source linked

In brief

As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing. Machine unlearning offers one approach to addressing these conc...

Feed lens

evaluation

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

Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning

Earlier in this thread 4 items

The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints

Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem