4/2/2026
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
S0 tuning zero-overhead adaptation of hybrid recurrent-attention models outperforming LoRA on code generation.
4/2/2026
Safe learning-based control via function-based uncertainty quantification
Function-based uncertainty quantification for safe learning-based control in safety-critical systems.
4/2/2026
Learning and Generating Mixed States Prepared by Shallow Channel Circuits
Learning to generate mixed quantum states prepared by shallow channel circuits in trivial phases.
4/2/2026
LLM REgression with a Latent Iterative State Head
RELISH lightweight architecture for text regression with LLMs using iterative latent state refinement.
4/2/2026
A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware
Survey on Graph Neural Network acceleration techniques across algorithms, systems, and customized hardware.
4/2/2026
Certifiably Robust RAG against Retrieval Corruption
RobustRAG defense framework with certifiable robustness against retrieval corruption attacks on RAG systems.
4/2/2026
Inductive Global and Local Manifold Approximation and Projection
Inductive manifold learning approach for nonlinear dimensional reduction with local and global structure.
4/2/2026
Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction
Domain adaptation with distribution shifts and unobserved confounding using linear structural causal models.
4/2/2026
Diagnosing Neural Convergence with Topological Alignment Spectra
Topological Alignment Spectra method for analyzing multi-scale structural relationships in neural network representations.
4/2/2026
A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
Gaussian Process interpretation of wide neural networks with observation noise and arbitrary prior means.
4/2/2026
Learning Hyperparameters via a Data-Emphasized Variational Objective
Gradient-based hyperparameter learning via evidence lower bound objective from Bayesian variational methods.
4/2/2026
VT-Former: Efffcient Transformer-based Decoder for Varshamov-Tenengolts Codes
Transformer-based decoder for Varshamov-Tenengolts codes correcting insertion, deletion, and substitution errors.
4/2/2026
Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference
Multi-armed bandit algorithm using local graph structure to minimize regret under network interference.
4/2/2026
A Detailed Account of Compositional Automata Learning through Alphabet Refinement
Compositional automata learning technique for inferring models of concurrent systems through alphabet refinement.
4/2/2026
SetONet: A Set-Based Operator Network for Solving PDEs with Variable-Input Sampling
SetONet neural operator for solving PDEs with variable sensor layouts by treating inputs as unordered sets.
4/2/2026
Neural Conditional Transport Maps
Neural framework for learning conditional optimal transport maps using hypernetworks to generate adaptive transport parameters.
4/2/2026
But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors
JUSSA framework uses steering vectors to improve LLM-as-a-judge reliability, detecting and mitigating sycophancy through honesty-promoting alternatives.
4/2/2026
Binned semiparametric Bayesian networks for efficient kernel density estimation
Binned semiparametric Bayesian networks for efficient kernel density estimation using data binning to reduce computational cost.
4/2/2026
Double-Diffusion: ODE-Prior Accelerated Diffusion Models for Spatio-Temporal Graph Forecasting
Double-Diffusion integrates ODE-prior with denoising diffusion models for spatio-temporal graph forecasting, balancing deterministic and stochastic components.
4/2/2026
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Klear-Reasoner model with long reasoning capabilities using gradient-preserving clipping policy optimization, with detailed training disclosures.
4/2/2026
Pattern-based Knowledge Component Extraction from Student Code Using Representation Learning
Knowledge component discovery in programming using representation learning on student code for personalized instruction systems.
4/2/2026
Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling
Thompson sampling analysis for Sharpe ratio optimization in multi-armed bandit setting, addressing fractional objective with dependent mean-variance.
4/2/2026
Machine Generalize Learning in Agent-Based Models: Going Beyond Surrogate Models for Calibration in ABMs
LSTM-based machine learning calibrator for agent-based epidemic models, learning inverse mapping from time series to SIR parameters.
4/2/2026
Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Classical Machine Learning and Deep Learning Optimization Techniques with Neurofeedback
EEG classification study comparing neural network architectures and optimizers across brain hemisphere frequency bands using TensorFlow/PyTorch.
4/2/2026
A Survey and Comparative Evaluation of Intrinsic Dimension Estimators under the Manifold Hypothesis
Comprehensive survey of intrinsic dimension estimators under manifold hypothesis, reviewing theoretical foundations and comparing eight methods.
4/2/2026
Regularizing Extrapolation in Causal Inference
Analysis of weight constraints in linear smoothers for causal inference, balancing feature imbalance against parametric modeling assumptions.
4/2/2026
Polychromic Objectives for Reinforcement Learning
Polychromic objectives approach to prevent mode collapse in reinforcement learning fine-tuning, preserving policy diversity during exploration.
4/2/2026
High-probability Convergence Guarantees of Decentralized SGD
Convergence analysis for decentralized SGD with high-probability guarantees, removing restrictive assumptions on gradient bounds and noise.
4/2/2026
Incoherence in Goal-Conditioned Autoregressive Models
Mathematical analysis of incoherence in goal-conditioned autoregressive models, studying policy improvement through fine-tuning with online RL.
4/2/2026
The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference
Empirical study examining the R-Learner framework limitations for network causal inference with graph-dependent heterogeneous treatment effects.
4/2/2026
Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics
Theoretical analysis of diffusion models on discrete state spaces, establishing convergence guarantees for masked and random walk dynamics.
4/2/2026
Multivariate Uncertainty Quantification with Tomographic Quantile Forests
Tomographic Quantile Forests (TQF) for nonparametric uncertainty quantification in multivariate regression tasks.
4/2/2026
Meta-probabilistic Modeling
Meta-probabilistic modeling framework for discovering latent structure across collections of related datasets using probabilistic graphical models.
4/2/2026
Lossy Common Information in a Learnable Gray-Wyner Network
Research on learnable Gray-Wyner networks for disentangling common and task-specific information in computer vision.
4/2/2026
SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution
SAU method for machine unlearning in sparse LLMs via gradient masking and importance redistribution for privacy.
4/2/2026
On the Non-Identifiability of Steering Vectors in Large Language Models
Research showing activation steering vectors in LLMs are fundamentally non-identifiable with large equivalence classes.
4/2/2026
FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
FIRE method for reinitialization in continual learning that balances stability and plasticity in neural networks.
4/2/2026
Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
Research on Natural Hypergradient Descent for bilevel optimization using Fisher information matrix as Hessian surrogate.
4/2/2026
How Well Do Large-Scale Chemical Language Models Transfer to Downstream Tasks?
Evaluation of scaling laws for Chemical Language Models on downstream molecular property prediction tasks.
4/2/2026
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
Introduces adaptive backbone scaling framework for class incremental learning to balance plasticity and stability while reducing memory overhead.
4/2/2026
Data-Driven Integration Kernels for Interpretable Nonlocal Operator Learning
Framework for learning interpretable nonlocal operator kernels from data for climate process modeling.
4/2/2026
CHIMERA-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design
Standardized benchmark dataset for epitope-specific antibody design with unified evaluation metrics for generative methods.
4/2/2026
RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
Preconditioned optimization method using row-momentum normalization for scalable matrix-based neural network training.
4/2/2026
Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
Projection-free algorithm for contextual bandits achieving logarithmic regret with improved efficiency over Online Newton Step.
4/2/2026
SkillRouter: Skill Routing for LLM Agents at Scale
Skill routing system for LLM agents that identifies relevant skills from large ecosystems before planning or execution.
4/2/2026
Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning
Framework using LLMs to automatically design reward programs for cooperative multi-agent RL systems with sparse task feedback.
4/2/2026
DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
DreamerAD uses latent world models for efficient RL in autonomous driving, compressing diffusion sampling 80x with visual interpretability.
4/2/2026
Experiential Reflective Learning for Self-Improving LLM Agents
ERL framework enabling LLM agents to self-improve through experiential learning from past interactions and reflective adaptation.
4/2/2026
Neuro-Symbolic Process Anomaly Detection
Neuro-symbolic method for process anomaly detection combining neural networks with domain knowledge from process mining.
4/2/2026
Neural Federated Learning for Livestock Growth Prediction
Federated learning approach for livestock growth prediction addressing privacy concerns and limited datasets in agricultural applications.