Publications (27)
Reimagining Retrieval Augmented Language Models for Answering Queries
Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez +4
We present a reality check on large language models and inspect the promise of retrieval augmented language models in comparison. Such language models are semi-parametric, where mo…
RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Xi Victoria Lin, Xilun Chen, Mingda Chen +9
Retrieval-augmented language models (RALMs) improve performance by accessing long-tail and up-to-date knowledge from external data stores, but are challenging to build. Existing ap…
Spontaneous formation of vector vortex beams in vertical-cavity surface-emitting lasers with feedback
Jesus Jimenez-Garcia, Pedro Rodriguez, T. Guillet +1
The spontaneous emergence of vector vortex beams with non-uniform polarization distribution is reported in a vertical-cavity surface-emitting laser (VCSEL) with frequency-selective…
Subatomicity in Rank-2 Lattice Monoids
Caroline Liu, Pedro Rodriguez, Marcos Tirador
Let be a cancellative and commutative monoid (written additively). The monoid is atomic if every non-invertible element can be written as a sum of irreducible elements (oft…
Data-Driven Modelling of the Van Allen Belts: The 5DRBM Model for Trapped Electrons
Lionel Métrailler, Guillaume Bélanger, Peter Kretschmar +10
The magnetosphere sustained by the rotation of the Earth's liquid iron core traps charged particles, mostly electrons and protons, into structures referred to as the Van Allen belt…
Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
Eric Wallace, Pedro Rodriguez, Shi Feng +2
Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited i…
Characterizing and Efficiently Accelerating Multimodal Generation Model Inference
Yejin Lee, Anna Sun, Basil Hosmer +27
Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system…
Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks
Pedro Rodriguez, Mahmoud Azab, Becka Silvert +4
Searching troves of videos with textual descriptions is a core multimodal retrieval task. Owing to the lack of a purpose-built dataset for text-to-video retrieval, video captioning…
SafePowerGraph-HIL: Real-Time HIL Validation of Heterogeneous GNNs for Bridging Sim-to-Real Gap in Power Grids
Aoxiang Ma, Salah Ghamizi, Jun Cao +1
As machine learning (ML) techniques gain prominence in power system research, validating these methods' effectiveness under real-world conditions requires real-time hardware-in-the…
PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems
Salah Ghamizi, Jun Cao, Aoxiang Ma +1
Efficiently solving unbalanced three-phase power flow in distribution grids is pivotal for grid analysis and simulation. There is a pressing need for scalable algorithms capable of…
Mitigating Noisy Inputs for Question Answering
Denis Peskov, Joe Barrow, Pedro Rodriguez +2
Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assi…
Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks
Tristan Thrush, Kushal Tirumala, Anmol Gupta +7
We introduce Dynatask: an open source system for setting up custom NLP tasks that aims to greatly lower the technical knowledge and effort required for hosting and evaluating state…
Solar Control on Jupiter's Equatorial X-ray Emissions: 26-29 November 2003 XMM-Newton Observation
Anil Bhardwaj, Graziella Branduardi-Raymont, Ronald F. Elsner +6
During November 26-29, 2003 XMM-Newton observed soft (0.2-2 keV) X-ray emission from Jupiter for 69 hours. The low-latitude X-ray disk emission of Jupiter is observed to be almost…
Generative AI in Computer Science Education: Accelerating Python Learning with ChatGPT
Ian McCulloh, Pedro Rodriguez, Srivaths Kumar +4
The increasing demand for digital literacy and artificial intelligence (AI) fluency in the workforce has highlighted the need for scalable, efficient programming instruction. This…
MultiContrievers: Analysis of Dense Retrieval Representations
Seraphina Goldfarb-Tarrant, Pedro Rodriguez, Jane Dwivedi-Yu +1
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affec…
py-irt: A Scalable Item Response Theory Library for Python
John P. Lalor, Pedro Rodriguez
py-irt is a Python library for fitting Bayesian Item Response Theory (IRT) models. py-irt estimates latent traits of subjects and items, making it appropriate for use in IRT tasks…
Byte Latent Transformer: Patches Scale Better Than Tokens
Artidoro Pagnoni, Ram Pasunuru, Pedro Rodriguez +11
We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant imp…
Localization of unique factorization semidomains
Victor Gonzalez, Harold Polo, Pedro Rodriguez
A semidomain is a subsemiring of an integral domain. Within this class, a unique factorization semidomain (UFS) is characterized by the property that every nonzero, nonunit element…
Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity
Pedro Rodriguez, Paul Crook, Seungwhan Moon +1
Open-ended human learning and information-seeking are increasingly mediated by digital assistants. However, such systems often ignore the user's pre-existing knowledge. Assuming a…
Quizbowl: The Case for Incremental Question Answering
Pedro Rodriguez, Shi Feng, Mohit Iyyer +2
Scholastic trivia competitions test knowledge and intelligence through mastery of question answering. Modern question answering benchmarks are one variant of the Turing test. Speci…
Finding AGN in Deep X-ray Flux States with Swift
Dirk Grupe, S. Komossa, Mason Bush +7
We report on our ongoing project of finding Active Galactic Nuclei (AGN) that go into deep X-ray flux states detected by Swift. Swift is performing an extensive study on the flux a…
Pathologies of Neural Models Make Interpretations Difficult
Shi Feng, Eric Wallace, Alvin Grissom +3
One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In exist…
S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval
Xiaodong Wang, Xuanyi Zhao, Pedro Rodriguez +7
As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capability known as episodic memory.…
Mitigation of Active Power Oscillation in Multi-VSG Grids: An Impedance-Based Perspective
Junjie Xiao, Lu Wang, Xiong Du +2
Active power oscillations frequently arise in inverter-dominated power systems with multiple converters operating under Virtual Synchronous Generator control, posing risks to syste…
Instruction-tuned Language Models are Better Knowledge Learners
Zhengbao Jiang, Zhiqing Sun, Weijia Shi +6
In order for large language model (LLM)-based assistants to effectively adapt to evolving information needs, it must be possible to update their factual knowledge through continued…
Physics-Aware Heterogeneous GNN Architecture for Real-Time BESS Optimization in Unbalanced Distribution Systems
Aoxiang Ma, Salah Ghamizi, Jun Cao +1
Battery energy storage systems (BESS) have become increasingly vital in three-phase unbalanced distribution grids for maintaining voltage stability and enabling optimal dispatch. H…
On the atomicity of power monoids of Puiseux monoids
Victor Gonzalez, Eddy Li, Henrick Rabinovitz +2
A submonoid of the additive group is called a Puiseux monoid if it consists of nonnegative rationals. Given a monoid , the set consisting of all nonempty finite sub…