相关论文: Energy-Regularized Sequential Model Editing on Hyp…

While locate-then-edit knowledge editing efficiently updates knowledge encoded within Large Language Models (LLMs), a critical generalization failure mode emerges in the practical same-subject knowledge editing scenario: models fail to…

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…

Sparse Transformer has recently attracted a lot of attention since the ability for reducing the quadratic dependency on the sequence length. We argue that two factors, information bottleneck sensitivity and inconsistency between different…

Neuromorphic vision systems based on spiking neural networks (SNNs) offer ultra-low-power perception for event-based and frame-based cameras, yet catastrophic forgetting remains a critical barrier to deployment in continually evolving…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlying semantic meaning, can significantly affect their…

Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a…

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners…

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling…

Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems…

Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling…

In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD). Most related works study SMD by focusing on "effective…

This paper presents three hyperspectral mixture models jointly with Bayesian algorithms for supervised hyperspectral unmixing. Based on the residual component analysis model, the proposed general formulation assumes the linear model to be…

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language…

Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they often fail to generalize these updates to multi-hop reasoning…

I investigate a stronger form of regularization by deactivating neurons for extended periods, a departure from the temporary changes of methods like Dropout. However, this long-term dynamism introduces a critical challenge: severe training…

Recent advancements in scaling up models have significantly improved performance in Automatic Speech Recognition (ASR) tasks. However, training large ASR models from scratch remains costly. To address this issue, we introduce UME, a novel…

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each…

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built…

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…

Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and…