English
Related papers

Related papers: Geometry Conflict: Explaining and Controlling Forg…

200 papers

The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting which…

Machine Learning · Computer Science 2020-09-15 Gehui Shen , Song Zhang , Xiang Chen , Zhi-Hong Deng

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

Computation and Language · Computer Science 2026-03-16 Hongyang Chen , Zhongwu Sun , Hongfei Ye , Kunchi Li , Xuemin Lin

Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expressed in textual reasoning or drawing code carries no guarantee that a constraint-satisfying…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Juncheng Hu , Jiawei Du , Xin Zhang , Joey Tianyi Zhou

The success of autoregressive models largely depends on the effectiveness of vector quantization, a technique that discretizes continuous features by mapping them to the nearest code vectors within a learnable codebook. Two critical issues…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Xianghong Fang , Litao Guo , Hengchao Chen , Yuxuan Zhang , XiaofanXia , Dingjie Song , Yexin Liu , Hao Wang , Harry Yang , Yuan Yuan , Qiang Sun

In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously…

Machine Learning · Computer Science 2019-08-20 Gabrielle K. Liu

Automatic scoring of student responses enhances efficiency in education, but deploying a separate neural network for each task increases storage demands, maintenance efforts, and redundant computations. To address these challenges, this…

Computation and Language · Computer Science 2025-03-14 Luyang Fang , Ehsan Latif , Haoran Lu , Yifan Zhou , Ping Ma , Xiaoming Zhai

Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting is equal: Forgetting one fact (e.g., a U.S. president or an…

Machine Learning · Computer Science 2025-10-21 Jackson Harmon , Andreas Hochlehnert , Matthias Bethge , Ameya Prabhu

Artificial intelligence systems in critical fields like autonomous driving and medical imaging analysis often continually learn new tasks using a shared stream of input data. For instance, after learning to detect traffic signs, a model may…

Machine Learning · Computer Science 2025-11-18 Hanchen David Wang , Siwoo Bae , Zirong Chen , Meiyi Ma

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine Learning · Computer Science 2026-05-12 Xi Wang , Cheng Deng

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often…

Machine Learning · Computer Science 2024-07-17 Anton Alexandrov , Veselin Raychev , Mark Niklas Müller , Ce Zhang , Martin Vechev , Kristina Toutanova

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance…

Artificial Intelligence · Computer Science 2025-10-28 Nannan Shi , Chuanyu Qin , Shipeng Song , Man Luo

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

This paper presents a generalization of the Wasserstein distance for both persistence diagrams and merge trees [20], [66] that takes advantage of the regions of their topological features in the input domain. Specifically, we redefine the…

Graphics · Computer Science 2025-10-21 Mathieu Pont , Christoph Garth

Recent advancements in large language models (LLMs) and multi-modal models (MMs) have demonstrated their remarkable capabilities in problem-solving. Yet, their proficiency in tackling geometry math problems, which necessitates an integrated…

Artificial Intelligence · Computer Science 2024-05-20 Jiaxin Zhang , Zhongzhi Li , Mingliang Zhang , Fei Yin , Chenglin Liu , Yashar Moshfeghi

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case…

Machine Learning · Computer Science 2026-05-25 Lukas Thede , Stefan Winzeck , Zeynep Akata , Jonathan Richard Schwarz

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

Despite the significant advancements in Large Language Models (LLMs), catastrophic forgetting remains a substantial challenge, where models lose previously acquired knowledge upon learning new information. Continual learning (CL) strategies…

Machine Learning · Computer Science 2025-08-14 Iing Muttakhiroh , Thomas Fevens

Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and…

Computation and Language · Computer Science 2026-03-11 Isabelle Augenstein

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Machine Learning · Computer Science 2026-03-30 Alireza Moayedikia , Alicia Troncoso