20 results for “editability”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.
Aishwarya Agrawal, Roy Hirsch, Yasumasa Onoe, Sherry Ben +1 more
The paper introduces TECCI, a novel and challenging benchmark dataset of 7550 image-edit pairs, and demonstrates that current state-of-the-art text-guided image editing models struggle significantly w…
The authors introduce SMEBench, a large-scale benchmark for evaluating neural music editing systems.
Changhao Pan, Yifei Fan, Fan Zhuo, Yifu Chen +12 more
This paper provides a comprehensive review of audio editing in the era of foundation models, including a unified taxonomy of existing editing tasks and major foundation-model paradigms.
Wanying Ren, Xin Song, Futing Wang, Guoxiu He +1 more
The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…
The paper proposes Joint Neighborhood Optimization (JNO), a novel knowledge-editing framework that jointly addresses the coupled pressures of desirable knowledge propagation and unintended knowledge l…
Method introduces a dual-adapter editor for knowledge editing systems
Jun Wan, Zhongxin Liu, Dajun Chen, Wei Jiang +2 more
This paper proposes an adaptive code editing framework that dynamically selects optimal editing strategies based on task features.
Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang +3 more
AnyEdit++ introduces a structure-aware framework that uses Bayesian Surprise to adaptively segment long-form knowledge, significantly improving the coherence and accuracy of knowledge editing in LLMs.
Shiran Liu, Gaohui Xu, Sergio Burdisso, Thibault Bañeras-Roux +2 more
The paper proposes oracle-guided fine-tuning to improve post-editing of ASR transcripts by using curated pools of corrections, regularizers, and hard negatives.
Fei Deng, Yanwu Xu, Zhipeng Bao, Zhixing Zhang +3 more
BlazeEdit is a highly efficient, generalist image-to-image diffusion model designed for on-device deployment, consolidating multiple editing tasks into a compact 195M parameter model that runs quickly…