19 citations · 69 across the 25 of their papers we have counts for
29 papers
From Plato to Aristotle: Toward a General Theory of Representation Hypotheses
Dai Shi, Andi Han, Xiaoyu Li +2
The Platonic Representation Hypothesis (PRH) holds that increasingly capable models converge toward a common representation. However, recent studies have shown different views on a…
Controlling Dependence in Implicit Generative Models via Spread Mutual Information
Jiahao Yu, Song Liu, José Miguel Hernández-Lobato +1
Mutual information (MI) provides an objective for suppressing or encouraging statistical dependence in implicit generative models. However, direct MI evaluation is challenging in i…
ENCORE: Exact Non-equilibrium COntrol with Replica Exchange for Diffusion Generation
Jiahao Yu, Saifuddin Syed, José Miguel Hernández-Lobato +1
Inference-time control steers a pretrained generative model towards a target distribution without retraining. We study tilted targets , where is the samp…
Self-Confirming Superposition Traps in Reinforcement Learning
Dai Shi, Andi Han, Feng Chen +3
Reinforcement learning (RL) trains representations on data selected by the agent's policy, which then uses the resulting returns to guide its next choices. We show that this loop c…
SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration
Linhan Luo, Lequan Lin, Dai Shi +3
Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretr…
Evaluating the Diversity of AI-Generated Content with Diversity Profiles
Xiuyuan Hu, Xuege Hou, Guoqing Liu +6
Diversity is a fundamental criterion for evaluating generative artificial intelligence (AI) systems, yet its measurement remains inherently ambiguous. Existing approaches typically…
Making Reconstruction FID Predictive of Diffusion Generation FID
Tongda Xu, Mingwei He, Shady Abu-Hussein +6
It is well known that the reconstruction FID (rFID) of a VAE is poorly correlated with the generation FID (gFID) of a latent diffusion model. We propose interpolated FID (iFID), a…
Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa, Frank Schneider, Philipp Hennig +1
Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, t…
Training-Free Vector Quantization via Gaussian VAEs
Tongda Xu, Wendi Zheng, Jiajun He +4
Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due to discretization.…
Weighted Conditional Flow Matching
Sergio Calvo-Ordonez, Matthieu Meunier, Alvaro Cartea +3
Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows due to its computational efficiency and effectiveness. However, standa…
A Machine Learning Benchmarking Framework for Lipid Nanoparticle Transfection Efficiency Prediction
Asal Mehradfar, Mohammad Shahab Sepehri, Jose Miguel Hernandez-Lobato +4
The discovery of new ionizable lipids for efficient lipid nanoparticle (LNP)-mediated RNA delivery remains a major bottleneck in RNA therapeutics development. Recent advances demon…
Post-Hoc Uncertainty Quantification in Pre-Trained Neural Networks via Activation-Level Gaussian Processes
Richard Bergna, Stefan Depeweg, Sergio Calvo Ordonez +3
Uncertainty quantification in neural networks through methods such as Dropout, Bayesian neural networks and Laplace approximations is either prone to underfitting or computationall…
A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4
Performing gradient descent in a wide neural network is equivalent to computing the posterior mean of a Gaussian Process with the Neural Tangent Kernel (NTK-GP), for a specific pri…
Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations
Richard Bergna, Sergio Calvo-Ordoñez, Felix L. Opolka +2
We propose a novel Stochastic Differential Equation (SDE) framework to address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neur…
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
Xuexin Chen, Ruichu Cai, Zhengting Huang +5
We investigate the problem of explainability for machine learning models, focusing on Feature Attribution Methods (FAMs) that evaluate feature importance through perturbation tests…
Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo
Szilvia Ujváry, Gergely Flamich, Vincent Fortuin +1
An important yet underexplored question in the PAC-Bayes literature is how much tightness we lose by restricting the posterior family to factorized Gaussian distributions when opti…
Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
Pablo Morales-Álvarez, Arne Schmidt, José Miguel Hernández-Lobato +1
In the last years, the weakly supervised paradigm of multiple instance learning (MIL) has become very popular in many different areas. A paradigmatic example is computational patho…
Faster Relative Entropy Coding with Greedy Rejection Coding
Gergely Flamich, Stratis Markou, Jose Miguel Hernandez Lobato
Relative entropy coding (REC) algorithms encode a sample from a target distribution using a proposal distribution using as few bits as possible. Unlike entropy coding, REC…
Graph Neural Stochastic Differential Equations
Richard Bergna, Felix Opolka, Pietro Liò +1
We present a novel model Graph Neural Stochastic Differential Equations (Graph Neural SDEs). This technique enhances the Graph Neural Ordinary Differential Equations (Graph Neural…
Sampling-based inference for large linear models, with application to linearised Laplace
Javier Antorán, Shreyas Padhy, Riccardo Barbano +3
Large-scale linear models are ubiquitous throughout machine learning, with contemporary application as surrogate models for neural network uncertainty quantification; that is, the…
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
Riccardo Barbano, Johannes Leuschner, Javier Antorán +2
We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach…
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antorán, David Janz, James Urquhart Allingham +4
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community. The method provides reliable error bars and a…
Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior
Javier Antorán, Riccardo Barbano, Johannes Leuschner +2
Existing deep-learning based tomographic image reconstruction methods do not provide accurate estimates of reconstruction uncertainty, hindering their real-world deployment. This p…
Fast Relative Entropy Coding with A* coding
Gergely Flamich, Stratis Markou, José Miguel Hernández-Lobato
Relative entropy coding (REC) algorithms encode a sample from a target distribution using a proposal distribution , such that the expected codelength is $\mathcal{O}(D_{KL}[…