works on
bidirectional generation 1hybrid attention 1language model fine-tuning 1masked diffusion language modeling 1pretrained autoregressive models 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models

Zhengtao Yao, Liuyang Song, Hongbo Zhang +4

Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR…