3 citations · 5 across the 26 of their papers we have counts for
26 papers
Feature Superposition in Neural Networks: From Theory to Practice
Dai Shi, Xiaoyu Li, Andi Han +1
Superposition refers to neural networks representing more features than they have dimensions. It was proposed to explain polysemantic neurons, which respond to several features, an…
When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models
Dai Shi, Xiaoyu Li, José Miguel Hernández-Lobato
Whether large language models (LLMs) can perform the abductive leap from evidence to a new system of axioms, commonly referred to as a jump, has recently attracted considerable deb…
Recipes for Steering and Scaling LLMs via Sampling
Jiajun He, Zongyu Guo, José Miguel Hernández-Lobato +1
Large Language Models (LLMs) are probabilistic models, typically defined by an autoregressive factorization. While recent work has begun to study richer target distributions beyond…
Wiener Chaos Expansion based Neural Operator for Singular Stochastic Partial Differential Equations
Dai Shi, Luke Thompson, Andi Han +3
In this paper, we explore how our recently developed Wiener Chaos Expansion (WCE)-based neural operator (NO) can be applied to singular stochastic partial differential equations, e…
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
Zongyu Guo, Jiajun He, Zhaoyang Jia +6
Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external…
Activation-Space Uncertainty Quantification for Pretrained Networks
Richard Bergna, Stefan Depeweg, Sergio Calvo-Ordoñez +3
Reliable uncertainty estimates are crucial for deploying pretrained models; yet, many strong methods for quantifying uncertainty require retraining, Monte Carlo sampling, or expens…
Stochastic Interpolants in Hilbert Spaces
James Boran Yu, RuiKang OuYang, Julien Horwood +1
Although diffusion models have successfully extended to function-valued data, stochastic interpolants -- which offer a flexible way to bridge arbitrary distributions -- remain limi…
Richer Bayesian Last Layers with Subsampled NTK Features
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4
Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty bec…
Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations
Dai Shi, Lequan Lin, Andi Han +4
Stochastic differential equations (SDEs) and stochastic partial differential equations (SPDEs) are fundamental for modeling stochastic dynamics across the natural sciences and mode…
A Diffusive Classification Loss for Learning Energy-based Generative Models
RuiKang OuYang, Louis Grenioux, José Miguel Hernández-Lobato
Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent…
Warm-Starting Iterative Gaussian Processes for Faster Sequential Inference
Alan Yufei Dong, Jihao Andreas Lin, José Miguel Hernández-Lobato
Efficient Gaussian process (GP) inference is critical for sequential decision-making tasks such as active learning, online prediction, and Bayesian optimization. Iterative approach…
CREPE: Controlling Diffusion with Replica Exchange
Jiajun He, Paul Jeha, Peter Potaptchik +5
Inference-time control of diffusion models aims to steer model outputs to satisfy new constraints without retraining. Previous approaches have mostly relied on heuristic guidance o…
Aligning Multimodal Representations through an Information Bottleneck
Antonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana +2
Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn a…
Scalable Gaussian Processes with Latent Kronecker Structure
Jihao Andreas Lin, Sebastian Ament, Maximilian Balandat +3
Applying Gaussian processes (GPs) to very large datasets remains a challenge due to limited computational scalability. Matrix structures, such as the Kronecker product, can acceler…
RNE: plug-and-play diffusion inference-time control and energy-based training
Jiajun He, José Miguel Hernández-Lobato, Yuanqi Du +1
Diffusion models generate data by removing noise gradually, which corresponds to the time-reversal of a noising process. However, access to only the denoising kernels is often insu…
Progressive Tempering Sampler with Diffusion
Severi Rissanen, RuiKang OuYang, Jiajun He +4
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fa…
There Was Never a Bottleneck in Concept Bottleneck Models
Antonio Almudévar, José Miguel Hernández-Lobato, Alfonso Ortega
Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a prom…
Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models
Fengzhe Zhang, Laurence I. Midgley, José Miguel Hernández-Lobato
Score-based diffusion models (SBDMs) are powerful amortized samplers for Boltzmann distributions; however, imperfect score estimates bias downstream Monte Carlo estimates. Classica…
FEAT: Free energy Estimators with Adaptive Transport
Jiajun He, Yuanqi Du, Francisco Vargas +4
We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation -- a critical challenge across scientific domains. FEAT leverages lea…
Nonparametric Heterogeneous Long-term Causal Effect Estimation via Data Combination
Weilin Chen, Ruichu Cai, Junjie Wan +2
Long-term causal inference has drawn increasing attention in many scientific domains. Existing methods mainly focus on estimating average long-term causal effects by combining long…
Causal Effect Estimation under Networked Interference without Networked Unconfoundedness Assumption
Weilin Chen, Ruichu Cai, Jie Qiao +2
Estimating causal effects under networked interference from observational data is a crucial yet challenging problem. Most existing methods mainly rely on the networked unconfounded…
Long-term Causal Inference via Modeling Sequential Latent Confounding
Weilin Chen, Ruichu Cai, Yuguang Yan +2
Long-term causal inference is an important but challenging problem across various scientific domains. To solve the latent confounding problem in long-term observational studies, ex…
DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
Wenlin Chen, Mingtian Zhang, Jiajun He +4
Score-based distillation methods train one-step diffusion models in two stages: they first train a teacher score model, then distill it into a one-step student model. However, this…
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
Jiajun He, Yuanqi Du, Francisco Vargas +5
We consider the sampling problem, where the aim is to draw samples from a distribution whose density is known only up to a normalization constant. Recent breakthroughs in generativ…