5 citations · 6 across the 13 of their papers we have counts for
14 papers
Einstein World Models
Munachiso Samuel Nwadike, Zangir Iklassov, Ali Mekky +2
Does intelligence require the ability to reason about phenomena beyond direct experience? It is natural to suspect that some complex thought cannot be captured through language alo…
Measuring AI Reasoning: A Guide for Researchers
Munachiso Samuel Nwadike, Zangir Iklassov, Kareem Ali +2
In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-…
Sycophancy Hides Linearly in the Attention Heads
Rifo Genadi, Munachiso Nwadike, Nurdaulet Mukhituly +3
We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we trai…
MAFM^3: Modular Adaptation of Foundation Models for Multi-Modal Medical AI
Mohammad Areeb Qazi, Munachiso S Nwadike, Ibrahim Almakky +2
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every doma…
The AI Data Scientist
Farkhad Akimov, Munachiso Samuel Nwadike, Zangir Iklassov +1
Imagine decision-makers uploading data and, within minutes, receiving clear, actionable insights delivered straight to their fingertips. That is the promise of the AI Data Scientis…
UNICON: UNIfied CONtinual Learning for Medical Foundational Models
Mohammad Areeb Qazi, Munachiso S Nwadike, Ibrahim Almakky +2
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every doma…
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Toluwani Aremu, Noor Hussein, Munachiso Nwadike +5
Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a…
Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View
Muhammad Cendekia Airlangga, Hilal AlQuabeh, Munachiso S Nwadike +1
We study memory in state-space language models using primacy and recency effects as behavioral tools to uncover how information is retained and forgotten over time. Applying struct…
Mechanistic Insights into Grokking from the Embedding Layer
H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic +2
Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexpl…
Number Representations in LLMs: A Computational Parallel to Human Perception
H. V. AlquBoj, Hilal AlQuabeh, Velibor Bojkovic +4
Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones. This cognitive bias, sup…
RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
Munachiso Nwadike, Zangir Iklassov, Toluwani Aremu +6
We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirection…
Reducing Hyperparameter Tuning Costs in ML, Vision and Language Model Training Pipelines via Memoization-Awareness
Abdelmajid Essofi, Ridwan Salahuddeen, Munachiso Nwadike +5
The training or fine-tuning of machine learning, vision, and language models is often implemented as a pipeline: a sequence of stages encompassing data preparation, model training…
Improving Personalisation in Valence and Arousal Prediction using Data Augmentation
Munachiso Nwadike, Jialin Li, Hanan Salam
In the field of emotion recognition and Human-Machine Interaction (HMI), personalised approaches have exhibited their efficacy in capturing individual-specific characteristics and…
Explainability Matters: Backdoor Attacks on Medical Imaging
Munachiso Nwadike, Takumi Miyawaki, Esha Sarkar +2
Deep neural networks have been shown to be vulnerable to backdoor attacks, which could be easily introduced to the training set prior to model training. Recent work has focused on…