Search Results for author:
Found 18 papers, 4 papers with code
Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer
Currently, over a thousand LLMs exist that are multi-purpose and are capable of performing real world tasks, including Q&A, text summarization, content generation, etc.
What's the Magic Word? A Control Theory of LLM Prompting
We investigate the reachable set of output token sequences $R_y(\mathbf x_0)$ for which there exists a control input sequence $\mathbf u$ for each $\mathbf y \in R_y(\mathbf x_0)$ that steers the LLM to output $\mathbf y$ from initial state sequence $\mathbf x_0$.
Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models
Here, we propose a context-aware routing system, Tryage, that leverages a language model router for optimal selection of expert models from a model library based on analysis of individual input prompts.
Therapeutic algebra of immunomodulatory drug responses at single-cell resolution
We develop a unified mathematical model that quantitatively describes the transcriptome scale response of myeloid and lymphoid cell types to individual drugs and drug combinations through a single inferred regulatory network.
Engineering flexible machine learning systems by traversing functionally-invariant paths
We conceptualize the weight space of a neural network as a curved Riemannian manifold equipped with a metric tensor whose spectrum defines low rank subspaces in weight space that accommodate network adaptation without loss of prior knowledge.
Linear Transformations in Autoencoder Latent Space Predict Time Translations in Active Matter System
ML approaches are relevant in active matter, a field that spans scales and studies dynamics of far-from-equilibrium systems where there are significant challenges in predicting macroscopic behavior from microscopic interactions of active particles.
Traversing Geodesics to Grow Biological Structures
Biological tissues reliably grow into precise, functional structures from simple starting states during development.
Cell density controls signal propagation waves in a multicellular synthetic gene circuit
Here, we exploit physical-chemical coupling observed in a synthetic patterning circuit in order to control the size and spatial distribution of patterned synthetic cell sheets.
Signaling receptor localization maximizes cellular information acquisition in spatially-structured, natural environments
By viewing cell surface receptors as a sensor network, we develop an information theoretic framework for computing the optimal spatial organization of a sensing system for a given spatial signaling environment.
Active feature selection discovers minimal gene sets for classifying cell types and disease states with single-cell mRNA-seq data
Here, we introduce an active learning method (ActiveSVM) that identifies minimal but highly-informative gene sets that enable the identification of cell-types, physiological states, and genetic perturbations in single-cell data using a small number of genes.
Solving hybrid machine learning tasks by traversing weight space geodesics
Broadly, we introduce a geometric framework that unifies a range of machine learning objectives and that can be applied to multiple classes of neural network architectures.
Reinforcement Learning reveals fundamental limits on the mixing of active particles
The control of far-from-equilibrium physical systems, including active materials, has emerged as an important area for the application of reinforcement learning (RL) strategies to derive control policies for physical systems.
Programming Boundary Deformation Patterns in Active Networks
Studying a large set of shapes, we observe that the active networks contract in a shape-preserving manner that persists over the course of contraction.
Soft Condensed Matter
Sparsifying networks by traversing Geodesics
The geometry of weight spaces and functional manifolds of neural networks play an important role towards 'understanding' the intricacies of ML.
Self-organization of multi-layer spiking neural networks
Inspired by this strategy, we attempt to efficiently self-organize large neural networks with an arbitrary number of layers into a wide variety of architectures.
Geometric algorithms for predicting resilience and recovering damage in neural networks
Biological neural networks have evolved to maintain performance despite significant circuit damage.
Neural networks grown and self-organized by noise
The algorithm is adaptable to a wide-range of input-layer geometries, robust to malfunctioning units in the first layer, and so can be used to successfully grow and self-organize pooling architectures of different pool-sizes and shapes.
Active Learning of Spin Network Models
We apply the framework to the inference of spin network models and find that designed perturbations can reduce the sampling complexity by $10^6$-fold across a variety of network architectures.
