2 citations · 2 across the 7 of their papers we have counts for
9 papers
Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis
Nicholas Stiles, Gregory W. Wornell
Which pretraining objective yields the best representation for downstream tasks under an information budget? We formalize this problem as a multitask information bottleneck, using…
Decocted Experience Improves Test-Time Inference in LLM Agents
Maohao Shen, Kaiwen Zha, Zexue He +6
There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g.…
LegacyAvatars: Volumetric Face Avatars For Traditional Graphics Pipelines
Safa C. Medin, Gengyan Li, Ziqian Bai +8
We introduce a novel representation for efficient classical rendering of photorealistic 3D face avatars. Leveraging recent advances in radiance fields anchored to parametric face m…
Contrastive Predictive Coding Done Right for Mutual Information Estimation
J. Jon Ryu, Pavan Yeddanapudi, Xiangxiang Xu +1
The InfoNCE objective, originally introduced for contrastive representation learning, has become a popular choice for mutual information (MI) estimation, despite its indirect conne…
Revisiting Orbital Minimization Method for Neural Operator Decomposition
J. Jon Ryu, Samuel Zhou, Gregory W. Wornell
Spectral decomposition of linear operators plays a central role in many areas of machine learning and scientific computing. Recent work has explored training neural networks to app…
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
Yepeng Liu, Xuandong Zhao, Dawn Song +2
Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among L…
Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
Minchan Jeong, J. Jon Ryu, Se-Young Yun +1
The Koopman operator provides a principled framework for analyzing nonlinear dynamical systems through linear operator theory. Recent advances in dynamic mode decomposition (DMD) h…
Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions
Tejas Jayashankar, J. Jon Ryu, Gregory Wornell
We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the -skew Jensen--Shannon diver…
FaceFolds: Meshed Radiance Manifolds for Efficient Volumetric Rendering of Dynamic Faces
Safa C. Medin, Gengyan Li, Ruofei Du +5
3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, efficiency, compatibility, and configura…