相关论文: More Edits, More Stable: Understanding the Lifelon…

Robots capable of learning from demonstration (LfD) must exhibit stability while executing learned motion skills. To be effective in the real world, they should also remember multiple skills over time -- a capability lacking in current…

Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and software libraries continue to evolve. Model editing offers a lightweight alternative to retraining…

Exponential generalization bounds with near-tight rates have recently been established for uniformly stable learning algorithms. The notion of uniform stability, however, is stringent in the sense that it is invariant to the data-generating…

Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…

Deep Neural Networks (DNNs) are becoming integral components of real world services relied upon by millions of users. Unfortunately, architects of these systems can find it difficult to ensure reliable performance as irrelevant details like…

Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…

Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is…

Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate. Since retraining is computationally expensive, knowledge editing offers an efficient alternative --…

Image editing has achieved impressive results with the development of large-scale generative models. However, existing models mainly focus on the editing effects of intended objects and regions, often leading to unwanted changes in…

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived…

Large language models (LLMs) have exhibited impressive performance and surprising emergent properties. However, their effectiveness remains limited by the fixed context window of the transformer architecture, posing challenges for…

Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to…

Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most existing methods focus…

Large language models (LLMs) require continual knowledge updates to stay abreast of the ever-changing world facts, prompting the formulation of lifelong model editing task. While recent years have witnessed the development of various…

To be effective in sequential data processing, Recurrent Neural Networks (RNNs) are required to keep track of past events by creating memories. While the relation between memories and the network's hidden state dynamics was established over…

Masked diffusion language models enable parallel token generation and offer improved decoding efficiency over autoregressive models. However, their performance degrades significantly when generating multiple tokens simultaneously, due to a…

Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited…

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improved performance in controlled, teacher-forced evaluations.…

Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context settings. While token pruning reduces sequence length, prior methods rely on heuristics that…