Miniml’s leadership includes active academics — University of Edinburgh professors, an Alan Turing Institute Fellow, and an ELLIS Scholar. We work at the boundary of machine learning research and enterprise systems, then carry the methods that hold up under scrutiny into production. Research that ships.
Technical work from Miniml researchers and collaborators — new methods, evaluations, and findings from frontier model development. Each entry links to a short summary on this site, with the full paper one click away.
In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. ...
Read summary →Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as interactive aids in live ...
Read summary →Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or ...
Read summary →Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and ...
Read summary →Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate ...
Read summary →Knowledge Graphs (KGs) and heterogeneous graphs (HGs) offer a principled way to represent multi-entity, multi-relational systems, while also revealing a persistent tension ...
Read summary →Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, ...
Read summary →Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first ...
Read summary →Vision-language models (VLMs) achieve strong performance on standard, high-quality datasets, but we still do not fully understand how they perform under real-world ...
Read summary →Clinical decision-making requires nuanced reasoning over heterogeneous evidence and traceable justifications. While recent LLM multi-agent systems (MAS) show promise, they largely optimise ...
Read summary →Tensor factorization has long been a cornerstone of knowledge graph (KG) reasoning, achieving state-of-the-art performance on static link prediction tasks with models ...
Read summary →Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, ...
Read summary →The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. ...
Read summary →Steering vectors are a flexible mechanism for controlling large language models (LLMs) along interpretable behaviours. Multi-behaviour steering, however, remains challenging due to ...
Read summary →We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the ...
Read summary →Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves ...
Read summary →Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved ...
Read summary →We introduce Faithful Logic-Aided Reasoning and Exploration (FLARE), a novel interpretable approach for traversing the problem space using task decomp...
Read summary →Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ...
Read summary →Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context. We propos...
Read summary →Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level LLMs, which ...
Read summary →Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predict...
Read summary →We introduce MMLongBench, the first benchmark covering a diverse set of long-context vision-language tasks to evaluate long-context vision-language mo...
Read summary →Foundation models for computer vision built on Vision Transformer (ViT) architectures have become increasingly widespread. However, their fine-tuning process is resource-intensive, slowing ...
Read summary →The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification that speeds up probab...
Read summary →Activation sparsity is an intriguing property of deep neural networks that has been extensively studied in ReLU-based models, due to its advantages ...
Read summary →Foundation models have recently demonstrated strong performance in various knowledge graph reasoning tasks. However, their applicability to temporal knowledge graphs (TKGs), where ...
Read summary →Feature attribution (FA) methods are common post-hoc approaches that explain how Large Language Models (LLMs) make predictions. Generating faithful at...
Read summary →Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate on-screen coordinates ...
Read summary →Large Language Models (LLMs) frequently produce factually inaccurate outputs—a phenomenon known as hallucination—which limits their accuracy in knowle...
Read summary →Autoregressive language models rely on a Key-Value (KV) Cache to avoid re-computing past hidden states during generation. As model sizes and context l...
Read summary →Clinical decision-making is inherently complex, often influenced by cognitive biases, incomplete information, and case ambiguity. Large Language Models (LLMs) have shown promise ...
Read summary →