Our researchers have been involved in some important research papers as part of their hub activities. Here is a selection of this research.

2026/2027

Title Authors Publication
Agentcoma: A compositional benchmark mixing commonsense and mathematical reasoning in real-world scenarios Marek Rei Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Amb3r: Accurate feed-forward metric-scale 3d reconstruction with backend Hengyi Wang, Lourdes Agapito Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
CellTypeAI: cell annotation for scRNA-seq using local generative-AI Magnus Rattray Bioinformatics
CG-Floor: Centroid-guided diffusion for large-scale floorplan generation Yukun Lai Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Rohit Saxena, Pasquale Minervini arXiv preprint
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models José Miguel Hernández-Lobato arXiv preprint
Concept-based Adversarial Attack: a Probabilistic Perspective Andi Zhang, Samuel Kaski International Conference on Learning Representations
Conditional Diffusion Sampling José Miguel Hernández-Lobato arXiv preprint
Contrastively Pre-trained Event Embeddings with Schema-free LLM Annotations Steven Schockaert Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)
DeepSynBa: actionable drug combination prediction with complete dose-response profiles Magnus Rattray Bioinformatics
Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes Miguel Rodrigues arXiv preprint
Do Composed Image Retrieval Benchmarks Require Multimodal Composition? Rohit Saxena, Pasquale Minervini arXiv preprint
Embodied Intelligence Security with Vision-language Models: A Survey Canhui Liu Machine Intelligence Research
Exact Posterior Score Estimation for Solving Linear Inverse Problems Yee Whye Teh arXiv preprint
FEAT: Free energy Estimators with Adaptive Transport José Miguel Hernández-Lobato Journal of Statistical Mechanics: Theory and Experiment
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps Jose Miguel Hernandez-Lobato arXiv preprint
FLASHand: Feed-forward reLightable and Animatable Single-view Hand Reconstruction Yukun Lai Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers
Free energy Estimation on Any State Space José Miguel Hernández-Lobato arXiv preprint
Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformers Mingfei Sun arXiv preprint
Hierarchical inference and closure learning via adaptive surrogates for odes and pdes Mark Girolami arXiv preprint
Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences Michael Gutmann arXiv preprint
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Pasquale Minervini arXiv preprint
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models Mark Plumbley International Conference on Learning Representations
Meta flow maps enable scalable reward alignment Yee Whye Teh arXiv preprint
Multimodal spatial omics: From data acquisition to computational integration Magnus Rattray Patterns
Randomized Advantage Transformation Mingfei Sun ICML Proceedings
Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning Samuel Kaski, Mingfei Sun arXiv preprint
Richer bayesian last layers with subsampled ntk features Yarin Gal, Jose Miguel Hernández-Lobato arXiv preprint
Same Answer, Different Representations Rohit Saxena, Pasquale Minervini Accepted in EMNLP 2026
SFM-Adapter: Style-aware Feature Manipulation Adapter for Speech Style Editing Arshdeep Singh, Mark Plumbley IEEE Transactions on Audio, Speech and Language Processing
Similarity-Aware Machine Unlearning Haripriya Harikumar arXiv preprint
The Sociology of AI as an Emerging Field: Mapping Tensions and Boundaries Canhui Liu Sociology Compass
Towards Diverse Scientific Hypothesis Search with Large Language Models José Miguel Hernández-Lobato arXiv preprint
Transformed Latent Variable Multi-Output Gaussian Processes Magnus Rattray arXiv preprint
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models Rohit Saxena, Pasquale Minervini ICML 2026

2025 / 2026

Title Hub researchers listed as authors View paper
A Diffusive Classification Loss for Learning Energy-based Generative Models José Miguel Hernández‑Lobato arXiv
CCDb+: Enhanced Annotations and Multi-Modal Benchmark for Natural Dyadic Conversations Yukun Lai ACM Multimedia
CREPE: Controlling Diffusion with Replica Exchange José Miguel Hernández‑Lobato arXiv
DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision Mingtian Zhang; José Miguel Hernández‑Lobato; David Barber arXiv
Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio Zixing Song; José Miguel Hernández‑Lobato OpenReview
Efficient Deconvolution in Populational Inverse Problems Mark Girolami arXiv
EnvSDD: Benchmarking Environmental Sound Deepfake Detection Mark D. Plumbley arXiv
FedEDM: Federated Equivariant Diffusion Model for 3D Molecule Generation with Enhanced Communication Efficiency Zixing Song; José Miguel Hernández‑Lobato ACM
LGA-Net: Learning Local and Global Affinities for Sparse Scribble-based Image Colorization Yukun Lai ICCV / CVF ICCV
Neural Mutual Information Estimation with Vector Copulas Michael U. Gutmann arXiv
RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters Yukun Lai ICCV / CVF ICCV
Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement Yukun Lai SIGGRAPH Asia
Softly Constrained Denoisers for Diffusion Models Samuel Kaski; Mingfei Sun OpenReview
Summary of The Inaugural Music Source Restoration Challenge Mark D. Plumbley arXiv
Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation Models Mark D. Plumbley IEEE Xplore
Track and Tweak: Monitoring and Improving Group Fairness for Temporal Graph Neural Networks in Real Time Zixing Song; José Miguel Hernández‑Lobato ACM KDD
BiBBDM: Bidirectional Image Translation With Brownian Bridge Diffusion Models Yukun Lai IEEE TPAMI

2024/25

Title Hub researchers listed as authors View paper
A Primer on Variational Inference for Physics-Informed Deep Generative Modelling Mark Girolami Royal Society
AudioSetCaps: An Enriched Audio-Caption Dataset Using Automated Generation Pipeline With Large Audio and Language Models Mark Plumbley IEEE Xplore
Efficient Prior Calibration from Indirect Data Mark Girolami SIAM Journal on Scientific Computing
Training Neural Samplers with Reverse Diffusive KL Divergence Mingtian Zhang, David Barber, José Miguel Hernández‑Lobato arXiv
Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector Andi Zhang arXiv
Efficient Deconvolution in Populational Inverse Problems Mark Girolami arXiv