English
Related papers

Related papers: Domain Restriction via Multi SAE Layer Transitions

200 papers

The increasing prevalence of Large Language Models (LLMs) demands effective safeguards for their operation, particularly concerning their tendency to generate out-of-context responses. A key challenge is accurately detecting when LLMs stray…

Computation and Language · Computer Science 2026-01-21 Jonathan Pan

Large Language Models (LLMs) excel at tasks like language processing, strategy games, and reasoning but struggle to build generalizable internal representations essential for adaptive decision-making in agents. For agents to effectively…

Artificial Intelligence · Computer Science 2025-01-14 Jason Du , Kelly Hong , Alishba Imran , Erfan Jahanparast , Mehdi Khfifi , Kaichun Qiao

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

Computation and Language · Computer Science 2026-03-20 Xiaoyin Chen , Canwen Xu , Yite Wang , Boyi Liu , Zhewei Yao , Yuxiong He

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…

Computation and Language · Computer Science 2026-02-05 Qinglong Cao , Yuntian Chen , Chao Ma , Xiaokang Yang

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

Standard statistical learning theory predicts that Large Language Models (LLMs) should overfit because their parameter counts vastly exceed the number of training tokens. Yet, in practice, they generalize robustly. We propose that the…

Machine Learning · Computer Science 2026-02-13 Dibyanayan Bandyopadhyay , Asif Ekbal

Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains. In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Ronghang Hu , Shoubhik Debnath , Saining Xie , Xinlei Chen

Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…

Machine Learning · Computer Science 2025-12-17 Albert Miao , Chenliang Zhou , Jiawei Zhou , Cengiz Oztireli

With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more challenging and their alignment less stable, particularly…

Machine Learning · Computer Science 2025-06-18 Hantao Lou , Changye Li , Jiaming Ji , Yaodong Yang

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…

Machine Learning · Computer Science 2025-04-21 Dmitrii Kharlapenko , Stepan Shabalin , Fazl Barez , Arthur Conmy , Neel Nanda

Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We propose LoRA-BAM - a method that adds OoD detection monitors…

Machine Learning · Computer Science 2025-06-03 Changshun Wu , Tianyi Duan , Saddek Bensalem , Chih-Hong Cheng

Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjacent layers to understand how features evolve through a…

Machine Learning · Computer Science 2024-11-19 Daniel Balcells , Benjamin Lerner , Michael Oesterle , Ediz Ucar , Stefan Heimersheim

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Machine Learning · Computer Science 2026-05-28 Li Lei , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evolutionary algorithms (EAs), though effective, often rely on…

Neural and Evolutionary Computing · Computer Science 2024-07-29 Yuxiao Huang , Shenghao Wu , Wenjie Zhang , Jibin Wu , Liang Feng , Kay Chen Tan

End-to-end automatic speech recognition (E2E ASR) systems have significantly improved speech recognition through training on extensive datasets. Despite these advancements, they still struggle to accurately recognize domain specific words,…

Computation and Language · Computer Science 2024-07-26 Jiwon Suh , Injae Na , Woohwan Jung

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning.…

Machine Learning · Computer Science 2019-09-06 Sharath M. Shankaranarayana , Davor Runje

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…

Image and Video Processing · Electrical Eng. & Systems 2020-04-30 Evan M. Yu , Juan Eugenio Iglesias , Adrian V. Dalca , Mert R. Sabuncu

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language…

Computation and Language · Computer Science 2024-05-31 Kun Zhao , Bohao Yang , Chen Tang , Chenghua Lin , Liang Zhan
‹ Prev 1 4 5 6 7 8 10 Next ›