1 citations · 1 across the 9 of their papers we have counts for
9 papers
Constrained and Composite Sampling via Proximal Sampler
Thanh Dang, Jiaming Liang
We study two log-concave sampling problems: constrained sampling and composite sampling. First, we consider sampling from a target distribution with density proportional to $\exp(-…
SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
Zhaoxin Wang, Jiaming Liang, Fengbin Zhu +5
Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behavio…
Prune, Don't Rebuild: Efficiently Tuning -Reachable Graphs for Nearest Neighbor Search
Tian Zhang, Ashwin Padaki, Jiaming Liang +2
Vector similarity search is an essential primitive in modern AI and ML applications. Most vector databases adopt graph-based approximate nearest neighbor (ANN) search algorithms, s…
Log-Averaged Mirror Prox for Fast, Large-Scale Optimal Transport in Linear Space
Matthew X. Burns, Jiaming Liang
We propose Log-Averaged Mirror Prox (LAMP), a linear-space primal-dual method for large-scale optimal transport. LAMP implements primal mirror prox updates by tracking an averaged…
GPU-Accelerated First-Order Method with Randomized Sampling for Binary Integer Programs
Ningji Wei, Jiaming Liang
We present a scalable, GPU-accelerated algorithmic framework for large binary integer programs that operates end-to-end with minimal synchronization overhead. The proposed method c…
Oracle-based Uniform Sampling from Convex Bodies
Thanh Dang, Jiaming Liang
We propose new Markov chain Monte Carlo algorithms to sample a uniform distribution on a convex body . Our algorithms are based on the proximal sampler, which uses Gibbs samplin…
A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design
Haydn Thomas Jones, Natalie Maus, Josh Magnus Ludan +9
AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit cons…
Unifying restart accelerated gradient and proximal bundle methods
Jiaming Liang
This paper presents a novel restarted version of Nesterov's accelerated gradient method and establishes its optimal iteration-complexity for solving convex smooth composite optimiz…
GreatSplicing: A Semantically Rich Splicing Dataset
Jiaming Liang, Yuwan Xue, Haowei Liu +9
In existing splicing forgery datasets, the insufficient semantic variety of spliced regions causes trained detection models to overfit semantic features rather than learn genuine s…