Miniml
Expertise Industries Research Company
+44 131 392 7838 Book a Consultation →
Expertise Industries Research Company +44 131 392 7838 Book a Consultation

Category: Research

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages

We present SynDARin, a methodology for synthesizing high-quality reasoning datasets in low-resource languages. Our approach combines template-based ge…

Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference

We introduce Adaptive Computation Modules (ACMs) that enable fine-grained conditional computation for more efficient neural network inference. Our app…

Enhancing neural link predictors for temporal knowledge graphs with temporal regularisers

The problem of link prediction in temporal knowledge graphs (TKGs) consists of finding missing links in the knowledge base under temporal constraints.Recently, …

Self-Training Large Language Models for Tool-Use Without Demonstrations

We propose a self-training approach that enables large language models to learn tool use without requiring human demonstrations. Our method uses self-…

When Can Proxies Improve the Sample Complexity of Preference Learning?

We provide theoretical and empirical analysis of when proxy rewards can improve sample efficiency in preference learning. Our work establishes conditi…

Is Complex Query Answering Really Complex?

We challenge conventional wisdom about complex query answering by demonstrating that many supposedly complex queries can be solved with surprisingly s…

With Great Backbones Comes Great Adversarial Transferability

Advances in self-supervised learning (SSL) for machine vision have improved representation robustness and model performance, giving rise to pre-trained backbones like ResNet …

An Auditing Test to Detect Behavioral Shift in Language Models

We develop a comprehensive auditing framework to detect behavioral shifts in language models across different contexts and time periods. Our approach …

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

We investigate the cross-lingual transferability of backdoor attacks in instruction-tuned large language models. Our findings reveal that backdoors ca…

← Previous
Next →
Miniml

Enterprise AI consulting. We help teams move past the pilot and operate AI systems in production — built to own, govern, and trust.

Book a Consultation →
Expertise
AI Agents Knowledge & Retrieval Document Intelligence AI Strategy MLOps AI Governance
Industries
Healthcare Finance Retail & E-commerce Manufacturing Logistics Insurance Fintech
Company
About Research Insights Contact
© 2026 Miniml. All rights reserved.
Privacy Policy Terms of Service Book a Consultation