Bin Yu

Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation ACL 2026 Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis ACL 2026 Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization (Extended Abstract) COLT 2026 T4NMTD: Transition-Centric Reinforcement Learning for Non-Markovian Task Decomposition AAAI 2026 Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression ICML 2025 Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition ICLR 2025 Instability, Computational Efficiency and Statistical Accuracy JMLR 2025 MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES ICML 2025 Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms JMLR 2025 SPEX: Scaling Feature Interaction Explanations for LLMs ICML 2025 The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning JMLR 2025 Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning COLING 2025 Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making ICLR 2024 ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance ICML 2024 Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining ICML 2024 Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency COLT 2024 LoRA+: Efficient Low Rank Adaptation of Large Models ICML 2024 Minimum-Norm Interpolation Under Covariate Shift ICML 2024 Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs ICLR 2024 The Impact of Initialization on LoRA Finetuning Dynamics NeurIPS 2024 Bridging Discrete and Backpropagation: Straight-Through and Beyond NeurIPS 2023 Revisiting minimum description length complexity in overparameterized models JMLR 2023 A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds AISTATS 2022 C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection CVPR 2022 Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. ICML 2022 Improve Speech Enhancement using Perception-High-Related Time-Frequency Loss Interspeech 2022 The Three Stages of Learning Dynamics in High-dimensional Kernel Methods ICLR 2022 Adaptive wavelet distillation from neural networks through interpretations NeurIPS 2021 Fast Kernelized Correlation Filter Without Boundary Effect WACV 2021 High-Performance Discriminative Tracking With Transformers ICCV 2021 Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients JMLR 2020 Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge ICML 2020 Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models AISTATS 2020 Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning JMLR 2020 A Debiased MDI Feature Importance Measure for Random Forests NeurIPS 2019 Hierarchical interpretations for neural network predictions ICLR 2019 Log-concave sampling: Metropolis-Hastings algorithms are fast JMLR 2019 Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs ICLR 2018 Fast MCMC Sampling Algorithms on Polytopes JMLR 2018 High-Speed Tracking With Multi-Kernel Correlation Filters CVPR 2018 Local Identifiability of ℓ_1-minimization Dictionary Learning: a Sufficient and Almost Necessary Condition JMLR 2018 Log-concave sampling: Metropolis-Hastings algorithms are fast! COLT 2018 Supervised Neighborhoods for Distributed Nonparametric Regression AISTATS 2016 A Statistical Perspective on Algorithmic Leveraging JMLR 2015 Counting and Exploring Sizes of Markov Equivalence Classes of Directed Acyclic Graphs JMLR 2015 A Statistical Perspective on Algorithmic Leveraging ICML 2014 Early Stopping and Non-parametric Regression: An Optimal Data-dependent Stopping Rule JMLR 2014 Supervised Feature Selection in Graphs with Path Coding Penalties and Network Flows JMLR 2013 Minimax-Optimal Rates For Sparse Additive Models Over Kernel Classes Via Convex Programming JMLR 2012 Predicting Execution Time of Computer Programs Using Sparse Polynomial Regression NeurIPS 2010 Restricted Eigenvalue Properties for Correlated Gaussian Designs JMLR 2010 A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers NeurIPS 2009 Lower bounds on minimax rates for nonparametric regression with additive sparsity and smoothness NeurIPS 2009 Model Selection in Gaussian Graphical Models: High-Dimensional Consistency of \boldmath$\ell_1$-regularized MLE NeurIPS 2008 Nonparametric sparse hierarchical models describe V1 fMRI responses to natural images NeurIPS 2008 Stagewise Lasso JMLR 2007 Approximation Lasso Methods for Language Modeling ACL 2006 On Model Selection Consistency of Lasso JMLR 2006 Sparse Boosting JMLR 2006