Publications (28)
Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?
Jonathan Roberts, Kai Han, Samuel Albanie
As the context limits of Large Language Models (LLMs) increase, the range of possible applications and downstream functions broadens. In many real-world tasks, decisions depend on…
Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs
Jonathan Roberts, Timo Lüddecke, Rehan Sheikh +2
Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains…
Optical identification using imperfections in 2D materials
Yameng Cao, Alexander J. Robson, Abdullah Alharbi +8
The ability to uniquely identify an object or device is important for authentication. Imperfections, locked into structures during fabrication, can be used to provide a fingerprint…
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
Jonathan Roberts, Kai Han, Neil Houlsby +1
Large multimodal models (LMMs) have proven flexible and generalisable across many tasks and fields. Although they have strong potential to aid scientific research, their capabiliti…
Powderday: Dust Radiative Transfer for Galaxy Simulations
Desika Narayanan, Matthew J. Turk, Thomas Robitaille +18
We present Powderday, a flexible, fast, open-source dust radiative transfer package designed to interface with galaxy formation simulations. Powderday builds on FSPS population syn…
Real-time Joint Motion Analysis and Instrument Tracking for Robot-Assisted Orthopaedic Surgery
Mario Strydom, Artur Banach, Liao Wu +3
Robotic-assisted orthopaedic surgeries demand accurate, automated leg manipulation for improved spatial accuracy to reduce iatrogenic damage. In this study, we propose novel rigid…
Geometric interpretation of the general POE model for a serial-link robot via conversion into D-H parameterization
Liao Wu, Ross Crawford, Jonathan Roberts
While Product of Exponentials (POE) formula has been gaining increasing popularity in modeling the kinematics of a serial-link robot, the Denavit-Hartenberg (D-H) notation is still…
SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models
Jonathan Roberts, Kai Han, Samuel Albanie
Interpreting remote sensing imagery enables numerous downstream applications ranging from land-use planning to deforestation monitoring. Robustly classifying this data is challengi…
Photonic crystals to enhance light extraction from 2D materials
Yasir J. Noori, Yameng Cao, Jonathan Roberts +4
We propose a scheme for coupling 2D materials to an engineered cavity based on a defective rod type photonic crystal lattice. We show results from numerical modelling of the sugges…
GAMEBoT: Transparent Assessment of LLM Reasoning in Games
Wenye Lin, Jonathan Roberts, Yunhan Yang +3
Large Language Models (LLMs) are increasingly deployed in real-world applications that demand complex reasoning. To track progress, robust benchmarks are required to evaluate their…
3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training
Yaqub Jonmohamadi, Shahnewaz Ali, Fengbei Liu +4
Minimally invasive surgery (MIS) has many documented advantages, but the surgeon's limited visual contact with the scene can be problematic. Hence, systems that can help surgeons n…
How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers
Jonathan Roberts, Kai Han, Samuel Albanie
Frontier LLMs are increasingly utilised across academia, society and industry. A commonly used unit for comparing models, their inputs and outputs, and estimating inference pricing…
GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models
Jonathan Roberts, Kai Han, Samuel Albanie
Large multimodal models (LMMs) have exhibited proficiencies across many visual tasks. Although numerous well-known benchmarks exist to evaluate model performance, they increasingly…
New Orbital Constraints for YSES 1 b and HR 2562 B from High-Precision Astrometry and Planetary Radial Velocities
Jonathan Roberts, William Thompson, Jason J. Wang +20
We present new VLTI/GRAVITY astrometry and updated orbit fits for the directly imaged companions YSES 1 b and HR 2562 B, substellar objects straddling the planet-brown dwarf bounda…
Composition and Configuration Patterns in Multiple-View Visualizations
Xi Chen, Wei Zeng, Yanna Lin +3
Multiple-view visualization (MV) is a layout design technique often employed to help users see a large number of data attributes and values in a single cohesive representation. Bec…
Gravitino Dark Matter and general neutralino NLSP
Laura Covi, Jasper Hasenkamp, Stefan Pokorski +1
We study the scenario of gravitino DM with a general neutralino NLSP in a model independent way. We consider all neutralino decay channels and compare them with the most recent BBN…
Arthroscopic Multi-Spectral Scene Segmentation Using Deep Learning
Shahnewaz Ali, Yaqub Jonmohamadi, Yu Takeda +4
Knee arthroscopy is a minimally invasive surgical (MIS) procedure which is performed to treat knee-joint ailment. Lack of visual information of the surgical site obtained from mini…
Optimal Dexterity for a Snake-like Surgical Manipulator using Patient-specific Task-space Constraints in a Computational Design Algorithm
Andrew Razjigaev, Ajay K. Pandey, Jonathan Roberts +1
Tendon-driven snake-like arms have been used to create highly dexterous continuum robots so that they can bend around anatomical obstacles to access clinical targets. In this paper…
Light extraction from 2D materials using liquid formed micro-lenses
Christopher S. Woodhead, Jonathan Roberts, Yasir J. Noori +6
The recent discovery of semiconducting two-dimensional materials has led to the prediction of a revolution in the field of optoelectronics, driven by the introduction of a series o…
The Pierre Auger Observatory: Contributions to the 33rd International Cosmic Ray Conference (ICRC 2013)
The Pierre Auger Collaboration, Alexander Aab, Pedro Abreu +495
Contributions of the Pierre Auger Collaboration to the 33rd International Cosmic Ray Conference, Rio de Janeiro, Brazil, July 2013
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma +31
Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they a…
Extracting random numbers from quantum tunnelling through a single diode
Ramón Bernardo-Gavito, Ibrahim Ethem Bagci, Jonathan Roberts +9
Random number generation is crucial in many aspects of everyday life, as online security and privacy depend ultimately on the quality of random numbers. Many current implementation…
GPT4GEO: How a Language Model Sees the World's Geography
Jonathan Roberts, Timo Lüddecke, Sowmen Das +2
Large language models (LLMs) have shown remarkable capabilities across a broad range of tasks involving question answering and the generation of coherent text and code. Comprehensi…
Cosmological Solutions of Low-Energy Heterotic M-Theory
Edmund J. Copeland, James Ellison, Andre Lukas +1
We derive a set of exact cosmological solutions to the D=4, N=1 supergravity description of heterotic M-theory. Having identified a new and exact SU(3) Toda model solution, we then…
IRIS: A Low Duty Cycle Cross-Layer Protocol for Long-Range Wireless Sensor Networks with Low Power Budget
Yi Chu, Paul Mitchell, David Grace +3
This paper presents a cross-layer protocol (IRIS) designed for long-range pipeline Wireless Sensor Networks with extremely low power budget, typically seen in a range of monitoring…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Visual Storytelling: A Methodological Approach to Designing and Implementing a Visualisation Poster
Rhiannon Owen, Jonathan Roberts
We present a design study of developing a visualisation poster. Posters can be difficult to create, and the story on a poster is not always clear. Using a case-study approach we pr…
Learning-Based Procedural Content Generation
Jonathan Roberts, Ke Chen
Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches. Among a variety of PCG techniques, search-ba…