2 citations · 6 across the 15 of their papers we have counts for
16 papers
AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research
Bernie Boscoe, Srinath Saikrishnan, Vikram Seenivasan +6
Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language acce…
AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups
Jack Stark, Srinath Saikrishnan, Vikram Seenivasan +3
Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows. However, using proprietary co…
Combining datasets with different ground truths using Low-Rank Adaptation to generalize image-based CNN models for photometric redshift prediction
Vikram Seenivasan, Srinath Saikrishnan, Andrew Lizarraga +3
In this work, we demonstrate how Low-Rank Adaptation (LoRA) can be used to combine different galaxy imaging datasets to improve redshift estimation with CNN models for cosmology. L…
Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology
Morgan Himes, Samiksha Krishnamurthy, Andrew Lizarraga +5
Upcoming surveys will produce billions of galaxy images but comparatively few spectra, motivating models that learn cross-modal representations. We build a dataset of 134,533 galax…
Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models
Zhanhao Cao, Clement Truong, Andrew Lizarraga
Recent advances in large language models are driven by scale, while parameter-efficient fine-tuning (PEFT) enables updating only a small fraction of parameters. Low-Rank Adaptation…
Latent Adaptive Planner for Dynamic Manipulation
Donghun Noh, Deqian Kong, Minglu Zhao +4
We present the Latent Adaptive Planner (LAP), a trajectory-level latent-variable policy for dynamic nonprehensile manipulation (e.g., box catching) that formulates planning as infe…
Better Prompt Compression Without Multi-Layer Perceptrons
Edouardo Honig, Andrew Lizarraga, Zijun Frank Zhang +1
Prompt compression is a promising approach to speeding up language model inference without altering the generative model. Prior works compress prompts into smaller sequences of lea…
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory
Eric Hanchen Jiang, Yasi Zhang, Zhi Zhang +4
Text-to-image (T2I) diffusion models have revolutionized generative modeling by producing high-fidelity, diverse, and visually realistic images from textual prompts. Despite these…
Understanding Galaxy Morphology Evolution Through Cosmic Time via Redshift Conditioned Diffusion Models
Andrew Lizarraga, Eric Hanchen Jiang, Jacob Nowack +4
Redshift measures the distance to galaxies and underlies our understanding of the origin of the Universe and galaxy evolution. Spectroscopic redshift is the gold-standard method fo…
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting
Eric Hanchen Jiang, Zhi Zhang, Dinghuai Zhang +9
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world…
Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
Deqian Kong, Dehong Xu, Minglu Zhao +6
In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifica…
SDSRA: A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning
Eric H. Jiang, Andrew Lizarraga
In this paper, we introduce a novel algorithm - the Skill-Driven Skill Recombination Algorithm (SDSRA) - an innovative framework that significantly enhances the efficiency of achie…
Differentiable VQ-VAE's for Robust White Matter Streamline Encodings
Andrew Lizarraga, Brandon Taraku, Edouardo Honig +2
Given the complex geometry of white matter streamlines, Autoencoders have been proposed as a dimension-reduction tool to simplify the analysis streamlines in a low-dimensional late…
StreamNet: A WAE for White Matter Streamline Analysis
Andrew Lizarraga, Katherine L. Narr, Kirsten A. Donald +1
We present StreamNet, an autoencoder architecture for the analysis of the highly heterogeneous geometry of large collections of white matter streamlines. This proposed framework ta…
Alignment of Tractography Streamlines using Deformation Transfer via Parallel Transport
Andrew Lizarraga, David Lee, Antoni Kubicki +4
We present a geometric framework for aligning white matter fiber tracts. By registering fiber tracts between brains, one expects to see overlap of anatomical structures that often…
SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment
Elvis Nunez, Andrew Lizarraga, Shantanu H. Joshi
We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) t…