Yaoqing Yang

Orcid: 0000-0001-9908-5531

Affiliations:
  • Dartmouth College, Hanover, NH, USA
  • University of California, Berkeley, RISE Lab, Berkeley, CA, USA (former)
  • Carnegie Mellon University, Department of Electrical and Computer Engineering, Pittsburgh, PA, USA (former, PhD)


According to our database1, Yaoqing Yang authored at least 88 papers between 2012 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization.
CoRR, May, 2026

RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search.
CoRR, May, 2026

RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization.
CoRR, March, 2026

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction.
CoRR, March, 2026

Learning to Discover Iterative Spectral Algorithms.
CoRR, February, 2026

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis.
CoRR, February, 2026

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation.
CoRR, February, 2026

Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis.
CoRR, January, 2026

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators.
CoRR, October, 2025

KCES: Training-Free Defense for Robust Graph Neural Networks via Kernel Complexity.
CoRR, June, 2025

From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks.
Trans. Mach. Learn. Res., 2025

A Model Zoo on Phase Transitions in Neural Networks.
J. Data-centric Mach. Learn. Res., 2025

LossLens: Diagnostics for Machine Learning Through Loss Landscape Visual Analytics.
IEEE Computer Graphics and Applications, 2025

Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Mitigating Memorization in Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Spectral Insights into Data-Oblivious Critical Layers in Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024
Visualizing Loss Functions as Topological Landscape Profiles.
CoRR, 2024

Evaluating Loss Landscapes from a Topology Perspective.
CoRR, 2024

Crafting Heavy-Tails in Weight Matrix Spectrum without Gradient Noise.
CoRR, 2024

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

MD tree: a model-diagnostic tree grown on loss landscape.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Teach LLMs to Phish: Stealing Private Information from Language Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Model Balancing Helps Low-data Training and Fine-tuning.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

When are ensembles really effective?
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

A Three-regime Model of Network Pruning.
Proceedings of the International Conference on Machine Learning, 2023

2022
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data.
CoRR, 2022

Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices.
Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022

Neurotoxin: Durable Backdoors in Federated Learning.
Proceedings of the International Conference on Machine Learning, 2022

Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks.
Proceedings of the IEEE International Conference on Data Mining, 2022

Self-supervised Spatial Reasoning on Multi-View Line Drawings.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
The Effect of Model Size on Worst-Group Generalization.
CoRR, 2021

Contrastive Spatial Reasoning on Multi-View Line Drawings.
CoRR, 2021

Taxonomizing local versus global structure in neural network loss landscapes.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models.
Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks.
Proceedings of the International Conference on 3D Vision, 2021

2020
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering.
IEEE Trans. Image Process., 2020

Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing.
Proc. IEEE, 2020

Benchmarking Semi-supervised Federated Learning.
CoRR, 2020

Serverless Straggler Mitigation using Local Error-Correcting Codes.
CoRR, 2020

Boundary thickness and robustness in learning models.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Serverless Straggler Mitigation using Error-Correcting Codes.
Proceedings of the 40th IEEE International Conference on Distributed Computing Systems, 2020

3D Coded SUMMA: Communication-Efficient and Robust Parallel Matrix Multiplication.
Proceedings of the Euro-Par 2020: Parallel Processing, 2020

Robust Class Parallelism - Error Resilient Parallel Inference with Low Communication Cost.
Proceedings of the 54th Asilomar Conference on Signals, Systems, and Computers, 2020

2019
Proactive Caching for Vehicular Multi-View 3D Video Streaming via Deep Reinforcement Learning.
IEEE Trans. Wirel. Commun., 2019

Coded Elastic Computing.
Proceedings of the IEEE International Symposium on Information Theory, 2019

Systematic Matrix Multiplication Codes.
Proceedings of the IEEE International Symposium on Information Theory, 2019

2018
Fast Temporal Path Localization on Graphs via Multiscale Viterbi Decoding.
IEEE Trans. Signal Process., 2018

Straggler-Resilient and Communication-Efficient Distributed Iterative Linear Solver.
CoRR, 2018

Coded Iterative Computing using Substitute Decoding.
CoRR, 2018

Coding for a Single Sparse Inverse Problem.
Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation.
Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2018), 2018

Cross-Iteration Coded Computing.
Proceedings of the 56th Annual Allerton Conference on Communication, 2018

2017
Detecting Localized Categorical Attributes on Graphs.
IEEE Trans. Signal Process., 2017

Spectrum Reuse Ratio in 5G Cellular Networks: A Matrix Graph Approach.
IEEE Trans. Mob. Comput., 2017

Graph Codes for Distributed Instant Message Collection in an Arbitrary Noisy Broadcast Network.
IEEE Trans. Inf. Theory, 2017

Rate Distortion for Lossy In-Network Linear Function Computation and Consensus: Distortion Accumulation and Sequential Reverse Water-Filling.
IEEE Trans. Inf. Theory, 2017

Computing Linear Transformations With Unreliable Components.
IEEE Trans. Inf. Theory, 2017

FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds.
CoRR, 2017

Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds.
CoRR, 2017

Coding Method for Parallel Iterative Linear Solver.
CoRR, 2017

Coded Distributed Computing for Inverse Problems.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Fast path localization on graphs via multiscale Viterbi decoding.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016
Rate Distortion for Lossy In-network Function Computation: Information Dissipation and Sequential Reverse Water-Filling.
CoRR, 2016

Detecting Structure-correlated Attributes on Graphs.
CoRR, 2016

Signal Localization, Decomposition and Dictionary Learning on Graphs.
CoRR, 2016

Fault-tolerant parallel linear filtering using compressive sensing.
Proceedings of the 9th International Symposium on Turbo Codes and Iterative Information Processing, 2016

Energy efficient distributed coding for data collection in a noisy sparse network.
Proceedings of the IEEE International Symposium on Information Theory, 2016

Computing linear transforms with unreliable components.
Proceedings of the IEEE International Symposium on Information Theory, 2016

Coding for lossy function computation: Analyzing sequential function computation with distortion accumulation.
Proceedings of the IEEE International Symposium on Information Theory, 2016

Signal detection on graphs: Bernoulli noise model.
Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016

Monitoring Manhattan's traffic at 5 intersections?
Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016

Fault-tolerant distributed logistic regression using unreliable components.
Proceedings of the 54th Annual Allerton Conference on Communication, 2016

2015
Information dissipation in noiseless lossy in-network function computation.
Proceedings of the 53rd Annual Allerton Conference on Communication, 2015

2014
How Much Frequency Can Be Reused in 5G Cellular Networks - A Matrix Graph Model.
CoRR, 2014

Achieving high frequency reuse in dense cellular networks: A matrix graph approach.
Proceedings of the 2014 IEEE Global Conference on Signal and Information Processing, 2014

Can a noisy encoder be used to communicate reliably?
Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013
Distributed flow scheduling in an unknown environment.
Proceedings of the 11th International Symposium and Workshops on Modeling and Optimization in Mobile, 2013

2012
Doppler frequency offsets estimation and diversity reception scheme of high speed railway with multiple antennas on separated carriages.
Proceedings of the International Conference on Wireless Communications and Signal Processing, 2012


  Loading...