4/16/2026
Diffusion Language Models for Speech Recognition
Exploration of masked and uniform-state diffusion language models for speech recognition rescoring and ASR hypothesis improvement.
4/16/2026
Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation
Hierarchical RL with runtime safety shielding for automated power grid operations, addressing safety constraints and generalization to unseen topologies.
4/16/2026
A Comparative Study of Dynamic Programming and Reinforcement Learning in Finite Horizon Dynamic Pricing
Comparative analysis of Fitted Dynamic Programming vs Reinforcement Learning for dynamic pricing across varying complexity levels and demand structures.
4/16/2026
Rhetorical Questions in LLM Representations: A Linear Probing Study
Linear probe analysis of how LLMs internally represent rhetorical questions. Studies persuasive language understanding in neural representations.
4/16/2026
From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
Formalizes 'vibe-testing' methodology for LLM evaluation. Studies how practitioners informally assess models beyond benchmarks.
4/16/2026
Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data
Automated feature preprocessing pipeline search for tabular machine learning. Studies AutoML approaches for classical model data preparation.
4/16/2026
MDPs with a State Sensing Cost
Markov decision processes with state sensing costs, balancing optimal actions against sensing/communication/computation expenses in decision-making.
4/16/2026
Two-Stage Regularization-Based Structured Pruning for LLMs
Two-stage regularization-based structured pruning method for reducing LLM parameters while minimizing knowledge loss and retraining requirements.
4/16/2026
RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning
Randomized Policy Learning approach for quadruped locomotion control with drastically reduced trainable parameters in neural network policies.
4/16/2026
Scalable unsupervised feature selection via weight stability
Minkowski weighted k-means++ for unsupervised feature selection in high-dimensional clustering by probabilistic centroid selection.
4/16/2026
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Token significance scoring in reinforcement learning to improve LLM reasoning efficiency by identifying which tokens contribute to correctness.
4/16/2026
Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes
Biased Scan Attention Transformer Neural Processes for scalable spatiotemporal inference across geology, epidemiology, climate and robotics applications.
4/16/2026
mLaSDI: Multi-stage latent space dynamics identification
Multi-stage latent space dynamics identification framework for solving PDEs via data-driven reduced-order models using autoencoders and ODEs.
4/16/2026
Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
Class-conditional heavy-tailed priors in VAEs addressing latent space bias for long-tailed generative modeling.
4/16/2026
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Guidance framework for discrete flow matching with exact guidance in discrete state spaces.
4/16/2026
The Signal is in the Steps: Local Scoring for Reasoning Data Selection
Local scoring method for selecting reasoning data from diverse teachers for efficient distillation into student models.
4/16/2026
Power Transform Revisited: Numerically Stable, and Federated
Numerically stable implementation of power transforms for data preprocessing with federated learning support.
4/16/2026
Modeling Student Learning with 3.8 Million Program Traces
Student learning model from 3.8M program traces analyzing coding skill development through interaction patterns.
4/16/2026
A Function-Centric Perspective on Flat and Sharp Minima
Function-centric analysis of flat vs sharp minima in deep networks, showing sharpness is function-dependent.
4/16/2026
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
Open-weight LLMs achieving IOI gold medal through test-time compute scaling for competitive programming.
4/16/2026
Empowering Targeted Neighborhood Search via Hyper Tour for Large-Scale TSP
Neural method with hyper-tour for targeted neighborhood search solving large-scale TSP instances efficiently.
4/16/2026
A Practitioner's Guide to Kolmogorov-Arnold Networks
Comprehensive review of Kolmogorov-Arnold Networks covering theory, relationships to MLPs and kernel methods, and applications.
4/16/2026
Data-Efficient RLVR via Off-Policy Influence Guidance
Influence-guided data selection for RLVR with theoretical guarantees for improving LLM reasoning efficiency.
4/16/2026
Think Outside the Policy: In-Context Steered Policy Optimization
In-context policy optimization for large reasoning models using off-policy exploration to improve RLVR reasoning capabilities.
4/16/2026
Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes
Hamiltonian Gaussian Processes for learning physically consistent dynamics from input-output data without velocity information.
4/16/2026
Guided Transfer Learning for Discrete Diffusion Models
Transfer learning via classifier guidance for discrete diffusion models in small-data regimes, extending continuous diffusion techniques.
4/16/2026
SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
Vector quantization technique for optimizing Kolmogorov-Arnold Network inference on edge devices with memory constraints.
4/16/2026
A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios
Review of diffusion models for simulation-based inference with intractable likelihoods, covering theoretical foundations and applications.
4/16/2026
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation
LLM content moderation system with continuous risk scoring that adapts to changing strictness requirements across platforms, replacing fixed binary classification.
4/16/2026
Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction
Systematic comparison of in-context operator learning versus single-operator learning for spatiotemporal prediction using neural networks.
4/16/2026
ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attacks
Comprehensive analysis of model reprogramming techniques for membership inference attacks, evaluating privacy vulnerabilities in deep learning models.
4/16/2026
Restless Bandits with Individual Penalty Constraints: A New Near-Optimal Index Policy and How to Learn It
Near-optimal index policy for restless multi-armed bandits with individual penalty constraints for resource allocation in dynamic wireless networks.
4/16/2026
WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning
Framework for generating and leveraging prior data through world models for sample-efficient offline-to-online reinforcement learning in robotics.
4/16/2026
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
Characterizes necessary and sufficient conditions for reward poisoning attacks in linear MDPs, providing theoretical framework for attack feasibility.
4/16/2026
Robust Adversarial Policy Optimization Under Dynamics Uncertainty
Proposes dual formulation for robust reinforcement learning under dynamics uncertainty, addressing limitations of domain randomization and adversarial RL methods.
4/16/2026
A Faster Path to Continual Learning
C-Flat optimization for continual learning on task streams avoiding forgetting with reduced computational overhead compared to prior approaches.
4/16/2026
THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture
THEIA: modular neural architecture learning complete Kleene three-valued logic end-to-end across mathematical domains with compositional generalization.
4/16/2026
Fast and principled equation discovery from chaos to climate
Bayesian-ARGOS: principled method for discovering equations governing complex systems from noisy observations using sparse regression.
4/16/2026
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Systematic investigation of on-policy distillation dynamics in LLM post-training, identifying conditions for success and failure mechanisms.
4/16/2026
Deep Learning Based Amharic Chatbot for FAQs in Universities
Chatbot using NLP and deep learning to answer FAQs in Amharic language for university students, addressing common administrative questions.
4/16/2026
Nonparametric Sparse Online Learning of the Koopman Operator
Sparse online learning algorithm for Koopman operator with stochastic approximation and convergence guarantees for nonlinear dynamical systems.
4/16/2026
Fast training of accurate physics-informed neural networks without gradient descent
Fast training method for physics-informed neural networks solving PDEs without gradient descent, addressing optimization and temporal causality.
4/16/2026
AudioX: A Unified Framework for Anything-to-Audio Generation
AudioX: unified multimodal framework for anything-to-audio generation integrating text, video, and audio signals for flexible audio synthesis.
4/16/2026
Fast and Simple Densest Subgraph with Predictions
Learning-augmented algorithms for densest subgraph problem using ML classifier predictions to achieve linear-time approximation.
4/16/2026
Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
PO-Flow: continuous normalizing flow framework for causal inference modeling potential outcomes and counterfactuals from observational data.
4/16/2026
Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification using Sparsity-Guided Steering Vectors
VS2 method for unsupervised adaptation of vision foundation models using sparse autoencoders for steering vectors without weight updates or labels.
4/16/2026
Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies
Geminet: lightweight ML-based traffic engineering framework using duality-based iterative process that handles topology changes with scalability.
4/16/2026
Frozen Forecasting: A Unified Evaluation
Proposes unified evaluation framework for assessing forecasting capabilities of frozen vision models across diverse tasks and abstraction levels.
4/16/2026
Autonomous Multi-objective Alloy Design through Simulation-guided Optimization
AutoMAT framework combines simulation, ML, and experiments for autonomous alloy discovery across competing objectives with data-efficient workflow.
4/16/2026
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
RL-PLUS method addresses capability boundary collapse in LLMs using reinforcement learning with hybrid-policy optimization to improve reasoning abilities beyond base model limits.