73 citations · 235 across the 51 of their papers we have counts for
32 papers · 1 filter
Entangled Representations Amplify Collateral Damage in Unlearning
Evžen Wybitul, Tim G. J. Rudner, Christian Schroeder de Witt
A long-held intuition in interpretability research is that representational entanglement, the sharing of structure between knowledge domains in a neural network, makes unlearning h…
A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization
Xianghong Fang, Wenlong Mou, Yuan Yuan +2
Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lacks a unified conceptual framework for understanding quantization tradeoffs. In th…
A Continuous-Time Markov Chain Framework for Insertion Language Models
Dhruvesh Patel, Benjamin Rozonoyer, Soumitra Das +3
Insertion Language Models (ILMs) offer several advantages over left-to-right generation and mask-based generation. However, existing formulations of insertion-based generation have…
Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel +4
When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refi…
Open Problems in Frontier AI Risk Management
Marta Ziosi, Miro Plueckebaum, Stephen Casper +26
Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pa…
Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
Tom A. Lamb, Desi R. Ivanova, Philip H. S. Torr +1
Calibration is central to reliable semantic uncertainty quantification, yet prior work has largely focused on discrimination, neglecting calibration. As calibration and discriminat…
Data-Driven Priors for Uncertainty-Aware Risk Prediction of Clinical Deterioration using Multimodal Data
L. Julián Lechuga López, Tim G. J. Rudner, Farah E. Shamout
Safe predictions are a crucial requirement for integrating predictive models into clinical decision support systems. One approach to improving trustworthiness is to enable models t…
Temporal Straightening for Latent Planning
Ying Wang, Oumayma Bounou, Gaoyue Zhou +4
Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to…
An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification
L. Julián Lechuga López, Farah E. Shamout, Tim G. J. Rudner
As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decision-making tasks. One proposed saf…
Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization
Yilun Kuang, Yash Dagade, Deep Chakraborty +4
Self-supervised learning aims to learn maximally informative representations, but explicit information maximization is hindered by the curse of dimensionality. Existing methods lik…
Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
Yilun Kuang, Yash Dagade, Tim G. J. Rudner +2
Joint-Embedding Predictive Architectures (JEPA) learn view-invariant representations and admit projection-based distribution matching for collapse prevention. Existing approaches r…
Out-of-Distribution Detection Methods Answer the Wrong Questions
Yucen Lily Li, Daohan Lu, Polina Kirichenko +4
To detect distribution shifts and improve model safety, many out-of-distribution (OOD) detection methods rely on the predictive uncertainty or features of supervised models trained…
Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
Vlad Sobal, Wancong Zhang, Kyunghyun Cho +3
A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms…
Can Transformers Learn Full Bayesian Inference in Context?
Arik Reuter, Tim G. J. Rudner, Vincent Fortuin +1
Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. Whil…
Exploring the Manifold of Neural Networks Using Diffusion Geometry
Elliott Abel, Andrew J. Steindl, Selma Mazioud +12
Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we apply manifold learning to the space of…
Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
Deep Chakraborty, Yann LeCun, Tim G. J. Rudner +1
A number of different architectures and loss functions have been applied to the problem of self-supervised learning (SSL), with the goal of developing embeddings that provide the b…
A Monte Carlo Framework for Calibrated Uncertainty Estimation in Sequence Prediction
Qidong Yang, Weicheng Zhu, Joseph Keslin +3
Probabilistic prediction of sequences from images and other high-dimensional data is a key challenge, particularly in risk-sensitive applications. In these settings, it is often de…
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Xingzhi Sun, Danqi Liao, Kincaid MacDonald +7
Rapid growth of high-dimensional datasets in fields such as single-cell RNA sequencing and spatial genomics has led to unprecedented opportunities for scientific discovery, but it…
Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks
Yunzhen Feng, Tim G. J. Rudner, Nikolaos Tsilivis +1
Adversarial examples have been shown to cause neural networks to fail on a wide range of vision and language tasks, but recent work has claimed that Bayesian neural networks (BNNs)…
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language dat…
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?
Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister +2
Causal confusion is a phenomenon where an agent learns a policy that reflects imperfect spurious correlations in the data. Such a policy may falsely appear to be optimal during tra…
Should We Learn Most Likely Functions or Parameters?
Shikai Qiu, Tim G. J. Rudner, Sanyam Kapoor +1
Standard regularized training procedures correspond to maximizing a posterior distribution over parameters, known as maximum a posteriori (MAP) estimation. However, model parameter…
A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
Yucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson
Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process…
Protein Design with Guided Discrete Diffusion
Nate Gruver, Samuel Stanton, Nathan C. Frey +6
A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. The generative model samples plausible sequences while t…