相关论文: Rebuilding ROME : Resolving Model Collapse during …

Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We…

Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining.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…

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to…

Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when performing fine-grained visual editing. We introduce a…

Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing approaches typically apply parameter perturbations to a static…

Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains largely unexplored due to insufficient, isolated, and…

Recent works on object removal and insertion have enhanced their performance by handling object effects such as shadows and reflections, using diffusion models trained on counterfactual datasets. However, the performance impact of applying…

Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge,…

We aim to develop a fundamental understanding of modality collapse, a recently observed empirical phenomenon wherein models trained for multimodal fusion tend to rely only on a subset of the modalities, ignoring the rest. We show that…

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their…

Large language models (LLMs) often exhibit hallucinations due to incorrect or outdated knowledge. Hence, model editing methods have emerged to enable targeted knowledge updates. To achieve this, a prevailing paradigm is the…

Multiple model reduction techniques have been proposed to tackle linear and non linear problems. Intrusive model order reduction techniques exhibit high accuracy levels, however, they are rarely used as a standalone industrial tool, because…

The training of large language models (LLMs) necessitates substantial data and computational resources, and updating outdated LLMs entails significant efforts and resources. While numerous model editing techniques (METs) have emerged to…

Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecessary exploration that wastes computation and can even…

Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse…

This contribution presents a model order reduction strategy for fast parametric modelling of problems with cracks formulated on spline discretizations. In the context of damage detection, parametric reduced order models (ROMs) are well…

Collaborative learning of large language models (LLMs) has emerged as a new paradigm for utilizing private data from different parties to guarantee efficiency and privacy. Meanwhile, Knowledge Editing (KE) for LLMs has also garnered…

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

Time-dependent partial differential equations are ubiquitous in physics-based modeling, but they remain computationally intensive in many-query scenarios, such as real-time forecasting, optimal control, and uncertainty quantification.…

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness.…