papers

Publications (14)

cs.AI2026

VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection

James Petullo, Sonny George, Dylan Cashman +1

A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. Mo…

cs.HC2019

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures

Dylan Cashman, Adam Perer, Remco Chang +1

Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configu…

cs.DB2019

NeuralCubes: Deep Representations for Visual Data Exploration

Zhe Wang, Dylan Cashman, Mingwei Li +5

Visual exploration of large multidimensional datasets has seen tremendous progress in recent years, allowing users to express rich data queries that produce informative visual summ…

cs.HC2025

"They Aren't Built For Me": An Exploratory Study of Strategies for Measurement of Graphical Primitives in Tactile Graphics

Areen Khalaila, Lane Harrison, Nam Wook Kim +1

Advancements in accessibility technologies such as low-cost swell form printers or refreshable tactile displays promise to allow blind or low-vision (BLV) people to analyze data by…

cs.HC2025

Speculating a Tactile Grammar: Toward Task-Aligned Chart Design for Non-Visual Perception

Areen Khalaila, Dylan Cashman

Tactile graphics are often adapted from visual chart designs, yet many of these encodings do not translate effectively to non-visual exploration. Blind and low-vision (BLV) people…

cs.CL2024

Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction

Sonny George, Chris Sypherd, Dylan Cashman

Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience…