English
Related papers

Related papers: Aging with GRACE: Lifelong Model Editing with Disc…

200 papers

While large pre-trained models have enabled impressive results on a variety of downstream tasks, the largest existing models still make errors, and even accurate predictions may become outdated over time. Because detecting all such failures…

Machine Learning · Computer Science 2022-06-15 Eric Mitchell , Charles Lin , Antoine Bosselut , Chelsea Finn , Christopher D. Manning

Scene Text Editing (STE) involves replacing text in a scene image with new target text while preserving both the original text style and background texture. Existing methods suffer from two major challenges: inconsistency and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Fuxiang Yang , Tonghua Su , Donglin Di , Yin Chen , Xiangqian Wu , Zhongjie Wang , Lei Fan

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number of parameters and complex transformer-based architectures result in significant resource…

Databases · Computer Science 2026-04-15 Tianhao Tang , Haoyang Li , Lei Chen

Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks can make prediction errors after deployment as the world…

Machine Learning · Computer Science 2024-10-29 Zhimeng Jiang , Zirui Liu , Xiaotian Han , Qizhang Feng , Hongye Jin , Qiaoyu Tan , Kaixiong Zhou , Na Zou , Xia Hu

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Computation and Language · Computer Science 2026-02-11 Yisu Wang , Ming Wang , Haoyuan Song , Wenjie Huang , Chaozheng Wang , Yi Xie , Xuming Ran

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting…

Computation and Language · Computer Science 2025-01-15 Jiaang Li , Quan Wang , Zhongnan Wang , Yongdong Zhang , Zhendong Mao

Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality…

Graphics · Computer Science 2025-10-20 Kenan Tang , Yanhong Li , Yao Qin

Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can result in model degradation. Recent techniques avoid making…

Computation and Language · Computer Science 2025-10-10 Hammad Rizwan , Domenic Rosati , Ga Wu , Hassan Sajjad

Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of…

Computation and Language · Computer Science 2025-03-17 Qizhou Chen , Taolin Zhang , Xiaofeng He , Dongyang Li , Chengyu Wang , Longtao Huang , Hui Xue

Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and selecting reasoning data well requires assessing them…

Artificial Intelligence · Computer Science 2026-05-14 Junjie Li , Ziao Wang , NingXuan Ma , Jianghong Ma , Xiaofeng Zhang

In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements. To counter packet losses without retransmission, two primary strategies are employed -- encoder-based…

While most neural generative models generate outputs in a single pass, the human creative process is usually one of iterative building and refinement. Recent work has proposed models of editing processes, but these mostly focus on editing…

Machine Learning · Computer Science 2021-03-08 Ziyu Yao , Frank F. Xu , Pengcheng Yin , Huan Sun , Graham Neubig

Across many real-time video applications, we see a growing need (especially in long delays and dynamic bandwidth) to allow clients to decode each frame once any (non-empty) subset of its packets is received and improve quality with each new…

Multimedia · Computer Science 2022-11-01 Yihua Cheng , Anton Arapin , Ziyi Zhang , Qizheng Zhang , Hanchen Li , Nick Feamster , Junchen Jiang

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Computation and Language · Computer Science 2024-06-18 Belinda Z. Li , Emmy Liu , Alexis Ross , Abbas Zeitoun , Graham Neubig , Jacob Andreas

Compiler pass selection and phase ordering present a significant challenge in achieving optimal program performance, particularly for objectives like code size reduction. Standard compiler heuristics offer general applicability but often…

Software Engineering · Computer Science 2025-10-16 Haolin Pan , Chao Zha , Jinyuan Dong , Mingjie Xing , Yanjun Wu

We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities. Among many efforts on task-free CL, a notable family of approaches are…

Machine Learning · Statistics 2021-12-09 Xisen Jin , Arka Sadhu , Junyi Du , Xiang Ren

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and…

Computation and Language · Computer Science 2025-09-09 Zherui Li , Houcheng Jiang , Hao Chen , Baolong Bi , Zhenhong Zhou , Fei Sun , Junfeng Fang , Xiang Wang

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine Learning · Computer Science 2025-10-02 Anushka Tiwari , Sayantan Pal , Rohini K. Srihari , Kaiyi Ji

In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…

Machine Learning · Computer Science 2023-12-22 Kamil Deja , Bartosz Cywiński , Jan Rybarczyk , Tomasz Trzciński

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

Computation and Language · Computer Science 2026-04-08 Zhaohan Zhang , Ziquan Liu , Ioannis Patras
‹ Prev 1 2 3 10 Next ›