1 citations · 1 across the 7 of their papers we have counts for
5 papers · 1 filter
Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding
Themistoklis Haris, Henry Li, Maryam Karimzadehgan
Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this problem, but often drop necessary context, lead…
Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
Jonathan Patsenker, Henry Li, Myeongseob Ko +2
Diffusion models have been firmly established as principled zero-shot solvers for linear and nonlinear inverse problems, owing to their powerful image prior and iterative sampling…
Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps
Henry Li, Ronen Basri, Yuval Kluger
Cascaded models are multi-scale generative models with a marked capacity for producing perceptually impressive samples at high resolutions. In this work, we show that they can also…
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Myeongseob Ko, Henry Li, Zhun Wang +6
Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful o…
Exponential weight averaging as damped harmonic motion
Jonathan Patsenker, Henry Li, Yuval Kluger
The exponential moving average (EMA) is a commonly used statistic for providing stable estimates of stochastic quantities in deep learning optimization. Recently, EMA has seen cons…