English
Related papers

Related papers: Towards Stable Symbol Grounding with Zero-Suppress…

200 papers

Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational…

Machine Learning · Computer Science 2025-10-03 Zachary Baker , Yuxiao Li

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…

Multimedia · Computer Science 2019-04-02 Chuanmin Jia , Zhaoyi Liu , Yao Wang , Siwei Ma , Wen Gao

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL loss vanishing), where the posterior collapses to the…

Computation and Language · Computer Science 2019-11-14 Ruizhe Li , Xiao Li , Chenghua Lin , Matthew Collinson , Rui Mao

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…

Machine Learning · Computer Science 2014-02-20 Yiyi Liao , Yue Wang , Yong Liu

Continuing advances in neural interfaces have enabled simultaneous monitoring of spiking activity from hundreds to thousands of neurons. To interpret these large-scale data, several methods have been proposed to infer latent dynamic…

Machine Learning · Computer Science 2019-08-23 Mohammad Reza Keshtkaran , Chethan Pandarinath

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

Computation and Language · Computer Science 2025-10-03 Jiaqing Xie

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

Machine Learning · Computer Science 2025-06-18 Siyu Chen , Heejune Sheen , Xuyuan Xiong , Tianhao Wang , Zhuoran Yang

Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized…

Machine Learning · Computer Science 2026-05-27 Xieting Chu , Sriram Vishwanath , Vijay Ganesh

Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabulary, which might hinder performance (polysemicity and synonymy) and pose a challenge for…

Information Retrieval · Computer Science 2026-04-24 Yuxuan Zong , Mathias Vast , Basile Van Cooten , Laure Soulier , Benjamin Piwowarski

Although the semantic communications have exhibited satisfactory performance in a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise is a particular kind of…

Signal Processing · Electrical Eng. & Systems 2022-05-24 Qiyu Hu , Guangyi Zhang , Zhijin Qin , Yunlong Cai , Guanding Yu , Geoffrey Ye Li

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson

A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…

Quantum Physics · Physics 2025-04-11 Gaoyuan Wang , Jonathan Warrell , Prashant S. Emani , Mark Gerstein

A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse autoencoders (SAEs) are a popular method for finding these…

Machine Learning · Computer Science 2025-02-10 Patrick Leask , Bart Bussmann , Michael Pearce , Joseph Bloom , Curt Tigges , Noura Al Moubayed , Lee Sharkey , Neel Nanda

Forecasting physical signals in long time range is among the most challenging tasks in Partial Differential Equations (PDEs) research. To circumvent limitations of traditional solvers, many different Deep Learning methods have been…

Machine Learning · Computer Science 2023-06-09 Leon Migus , Julien Salomon , Patrick Gallinari

Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference instability, producing contradictory preference assignments in response to subtle,…

Machine Learning · Computer Science 2026-05-19 Shunchang Liu , Xin Chen , Belen Martin Urcelay , Francesco Croce

Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer several shortcomings that diminish their utility and internal…

Computation and Language · Computer Science 2025-06-27 Ryosuke Takahashi , Tatsuro Inaba , Kentaro Inui , Benjamin Heinzerling

Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are…

Artificial Intelligence · Computer Science 2026-05-19 Yuyang Liu , Jingya Wang , Liuzhenghao Lv , Yonghong Tian

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon.…

Computation and Language · Computer Science 2024-02-02 Yingji Zhang , Danilo S. Carvalho , Marco Valentino , Ian Pratt-Hartmann , Andre Freitas

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

One of the main obstacles for developing flexible AI systems is the split between data-based learners and model-based solvers. Solvers such as classical planners are very flexible and can deal with a variety of problem instances and goals…

Artificial Intelligence · Computer Science 2020-02-21 Blai Bonet , Hector Geffner