34 citations · 70 across the 23 of their papers we have counts for
28 papers
JevGPT: Thinking Fast and Slow in Autonomous Research
Yasheng Sun, Yanning Dai, Yimeng Chen +9
Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval cov…
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
Li Nanbo, Firas Laakom, Yilan Zhang +10
Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ongoing computation and preserve…
Creation begins with understanding: LLMs as strategy designers for privacy-preserving tabular data synthesis
Jinmeng Li, Quan Zhang, Hangting Ye +4
Sharing tabular data in high-stakes domains is constrained by privacy regulations. Synthetic data offer a promising alternative, but deep generative models are costly to train and…
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Yimeng Chen, Zhe Ren, Firas Laakom +3
Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that attacker-published pages are tra…
Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
Alfonso Amayuelas, Firas Laakom, Piotr Piękos +5
The use of LLMs for code generation has naturally extended to code testing and evaluation. As codebases grow in size and complexity, so does the need for automated test generation.…
Huxley-Gödel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
Wenyi Wang, Piotr Piękos, Li Nanbo +5
Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor h…
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
Yimeng Chen, Piotr Piȩkos, Mateusz Ostaszewski +2
Evaluating the scientific discovery capabilities of large language model based agents, particularly how they cope with varying environmental complexity and utilize prior knowledge,…
Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
Firas Laakom, Haobo Chen, Jürgen Schmidhuber +1
Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through reg…
FACTS: A Factored State-Space Framework For World Modelling
Li Nanbo, Firas Laakom, Yucheng Xu +2
World modelling is essential for understanding and predicting the dynamics of complex systems by learning both spatial and temporal dependencies. However, current frameworks, such…
Pixel-Wise Color Constancy via Smoothness Techniques in Multi-Illuminant Scenes
Umut Cem Entok, Firas Laakom, Farhad Pakdaman +1
Most scenes are illuminated by several light sources, where the traditional assumption of uniform illumination is invalid. This issue is ignored in most color constancy methods, pr…
Class-wise Generalization Error: an Information-Theoretic Analysis
Firas Laakom, Yuheng Bu, Moncef Gabbouj
Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, whic…
Convolutional autoencoder-based multimodal one-class classification
Firas Laakom, Fahad Sohrab, Jenni Raitoharju +2
One-class classification refers to approaches of learning using data from a single class only. In this paper, we propose a deep learning one-class classification method suitable fo…
Newton Method-based Subspace Support Vector Data Description
Fahad Sohrab, Firas Laakom, Moncef Gabbouj
In this paper, we present an adaptation of Newton's method for the optimization of Subspace Support Vector Data Description (S-SVDD). The objective of S-SVDD is to map the original…
On Feature Diversity in Energy-based Models
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-m…
WLD-Reg: A Data-dependent Within-layer Diversity Regularizer
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from t…
Efficient CNN with uncorrelated Bag of Features pooling
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Despite the superior performance of CNN, deploying them on low computational power devices is still limited as they are typically computationally expensive. One key cause of the hi…
Non-Linear Spectral Dimensionality Reduction Under Uncertainty
Firas Laakom, Jenni Raitoharju, Nikolaos Passalis +2
In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives. Since real-world data usually…
Reducing Redundancy in the Bottleneck Representation of the Autoencoders
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks, e.g., dimensionality reduction, image compression, and image denoising. An AE has…
Learning to ignore: rethinking attention in CNNs
Firas Laakom, Kateryna Chumachenko, Jenni Raitoharju +2
Recently, there has been an increasing interest in applying attention mechanisms in Convolutional Neural Networks (CNNs) to solve computer vision tasks. Most of these methods learn…
Robust channel-wise illumination estimation
Firas Laakom, Jenni Raitoharju, Jarno Nikkanen +2
Recently, Convolutional Neural Networks (CNNs) have been widely used to solve the illuminant estimation problem and have often led to state-of-the-art results. Standard approaches…
Learning distinct features helps, provably
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +1
We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average -distance between the…
Graph Embedding with Data Uncertainty
Firas Laakom, Jenni Raitoharju, Nikolaos Passalis +2
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data…
Monte Carlo Dropout Ensembles for Robust Illumination Estimation
Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis +2
Computational color constancy is a preprocessing step used in many camera systems. The main aim is to discount the effect of the illumination on the colors in the scene and restore…