260 citations · 585 across the 32 of their papers we have counts for
35 papers
Decentralized LLM Workflows via Sequential Auctions
Ian Gemp, Shubhendu Trivedi, Adam Fisch +7
We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstrated that agents organized thr…
Your Transformer Is Secretly Elastic
Walter Simoncini, Dheeraj Varghese, Gertjan J. Burghouts +1
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed si…
Strong Lensing Cosmology with Population-level Calibrated Neural Ratio Estimation
Sreevani Jarugula, Brian D. Nord, Aleksandra Ćiprijanović +1
Strong gravitational lensing contains key information about cosmic acceleration. Modern and next-generation galaxy imaging surveys are expected to provide high-quality data on $\ma…
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
Adam Fisch, Shubhendu Trivedi, Fantine Huot +5
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist w…
Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model
Karla Tame-Narvaez, Aleksandra Ćiprijanović, Shubhendu Trivedi
Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However…
Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
Stefanos Pertigkiozoglou, Mircea Petrache, Shubhendu Trivedi +1
Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can…
On Universality of Deep Equivariant Networks
Marco Pacini, Mircea Petrache, Bruno Lepri +2
Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tenso…
Automating Sensor Characterization with Bayesian Optimization
J. Cuevas-Zepeda, C. Chavez, J. Estrada +6
The development of novel instrumentation requires an iterative cycle with three stages: design, prototyping, and testing. Recent advancements in simulation and nanofabrication tech…
On the Need to Align Intent and Implementation in Uncertainty Quantification for Machine Learning
Shubhendu Trivedi, Brian D. Nord
Quantifying uncertainties for machine learning (ML) models is a foundational challenge in modern data analysis. This challenge is compounded by at least two key aspects of the fiel…
Watermarking Degrades Alignment in Language Models: Analysis and Mitigation
Apurv Verma, NhatHai Phan, Shubhendu Trivedi
Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training…
On Universality Classes of Equivariant Networks
Marco Pacini, Gabriele Santin, Bruno Lepri +1
Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separ…
MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels
Xiaoou Liu, Zhen Lin, Longchao Da +3
Large Language Models (LLMs) require robust confidence estimation, particularly in critical domains like healthcare and law where unreliable outputs can lead to significant consequ…
Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks
Ashwin Samudre, Mircea Petrache, Brian D. Nord +1
There has been much recent interest in designing neural networks (NNs) with relaxed equivariance, which interpolate between exact equivariance and full flexibility for consistent p…
Improving Equivariant Model Training via Constraint Relaxation
Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Shubhendu Trivedi +1
Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Desp…
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
The advent of large language models (LLMs) has dramatically advanced the state-of-the-art in numerous natural language generation tasks. For LLMs to be applied reliably, it is esse…
Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Large language models (LLMs) specializing in natural language generation (NLG) have recently started exhibiting promising capabilities across a variety of domains. However, gauging…
Approximation-Generalization Trade-offs under (Approximate) Group Equivariance
Mircea Petrache, Shubhendu Trivedi
The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models…
Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control
Zhen Lin, Shubhendu Trivedi, Cao Xiao +1
Many real-world multi-label prediction problems involve set-valued predictions that must satisfy specific requirements dictated by downstream usage. We focus on a typical scenario…
Conformal Prediction with Temporal Quantile Adjustments
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
We develop Temporal Quantile Adjustment (TQA), a general method to construct efficient and valid prediction intervals (PIs) for regression on cross-sectional time series data. Such…
Conformal Prediction Intervals with Temporal Dependence
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Cross-sectional prediction is common in many domains such as healthcare, including forecasting tasks using electronic health records, where different patients form a cross-section.…
Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Deep neural network (DNN) classifiers are often overconfident, producing miscalibrated class probabilities. In high-risk applications like healthcare, practitioners require $\texti…
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
Matthew Farrell, Blake Bordelon, Shubhendu Trivedi +1
Equivariance has emerged as a desirable property of representations of objects subject to identity-preserving transformations that constitute a group, such as translations and rota…
Locally Valid and Discriminative Prediction Intervals for Deep Learning Models
Zhen Lin, Shubhendu Trivedi, Jimeng Sun
Crucial for building trust in deep learning models for critical real-world applications is efficient and theoretically sound uncertainty quantification, a task that continues to be…
DeepSZ: Identification of Sunyaev-Zel'dovich Galaxy Clusters using Deep Learning
Zhen Lin, Nicholas Huang, Camille Avestruz +4
Galaxy clusters identified from the Sunyaev Zel'dovich (SZ) effect are a key ingredient in multi-wavelength cluster-based cosmology. We present a comparison between two methods of…