3/25/2026
Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
Adversarial robustness technique for ASR systems using precision-varying inference to defend against attacks.
3/25/2026
Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions
Causal discovery method for chain-reaction systems using interventional data to identify cascade-like causal structures.
3/25/2026
Generalizing Dynamics Modeling More Easily from Representation Perspective
Neural dynamics modeling from latent space representations for complex systems like climate and fluid dynamics.
3/25/2026
Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection
Post-hoc out-of-distribution detection using bounding box anomaly scoring in neural network feature spaces.
3/25/2026
Coordinate Encoding on Linear Grids for Physics-Informed Neural Networks
Proposes coordinate encoding on linear grids to improve physics-informed neural networks for solving PDEs.
3/25/2026
Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman Constraints
Analyzes non-adversarial Q-based imitation learning with Bellman constraints, showing IQ-Learn doesn't outperform behavioral cloning as believed.
3/25/2026
Double Coupling Architecture and Training Method for Optimization Problems of Differential Algebraic Equations with Parameters
Dual physics-informed neural network architecture for multi-task optimization of differential algebraic equations with parameters.
3/25/2026
Spiking Personalized Federated Learning for Brain-Computer Interface-Enabled Immersive Communication
Personalized federated learning framework for analyzing brain signals in BCI-enabled immersive communication systems.
3/25/2026
Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction
Applies multitask-informed in-context learning to tabular data for predicting steel properties during hot rolling manufacturing.
3/25/2026
From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
Studies robustness of logic and lookup-based neural networks to hardware bit-flip errors, comparing to precision reduction approaches.
3/25/2026
Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models
Theoretical framework for optimal test-time computation strategies in LLMs, modeling sampling, chain-of-thought, and backtracking with computation budgets.
3/25/2026
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
Theoretical analysis proving transformers can learn a class of teacher models including convolutional and attention-based architectures via gradient descent.
3/25/2026
Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials
Graph neural network with dynamic attention for computing interatomic potentials efficiently in molecular dynamics simulations.
3/25/2026
Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints
Studies implicit bias of gradient-based algorithms on multiclass separable data using normalized steepest descent framework.
3/25/2026
The Coordinate System Problem in Persistent Structural Memory for Neural Architectures
Introduces dual-view pheromone pathway network architecture investigating requirements for persistent structural memory in neural networks.
3/25/2026
Confidence Calibration under Ambiguous Ground Truth
Addresses confidence calibration when annotators disagree, showing structural failures of standard calibration methods on majority-voted labels.
3/25/2026
TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
Automated red-teaming framework using hierarchical strategy exploration to discover vulnerabilities in vision-language models.
3/25/2026
Balancing Safety and Efficiency in Aircraft Health Diagnosis: A Task Decomposition Framework with Heterogeneous Long-Micro Scale Cascading and Knowledge Distillation-based Interpretability
Task decomposition framework for aircraft health diagnosis using hierarchical cascading and knowledge distillation for interpretability.
3/25/2026
Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamics
Proposes identifiable variational dynamic factor model for learning latent factors from time series with theoretical identifiability guarantees.
3/25/2026
VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents
Combines vision, language, and offline RL to train generalizable agents that understand environmental dynamics and task instructions.
3/25/2026
Weak-PDE-Net: Discovering Open-Form PDEs via Differentiable Symbolic Networks and Weak Formulation
Framework for discovering partial differential equations from sparse noisy data using differentiable symbolic networks and weak formulation.
3/25/2026
Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data
Theoretical analysis of denoising score matching for diffusion models on low-dimensional manifolds using random feature neural networks.
3/25/2026
Can Graph Foundation Models Generalize Over Architecture?
Studies whether graph foundation models can generalize across different GNN architectures and graph characteristics, revealing limitations in current approaches.
3/25/2026
A Sobering Look at Tabular Data Generation via Probabilistic Circuits
Critical analysis of tabular data generation via probabilistic circuits, questioning progress claims and evaluation protocols in current benchmarks.
3/25/2026
Assessing the Robustness of Climate Foundation Models under No-Analog Distribution Shifts
Evaluates robustness of climate foundation models under out-of-distribution shifts from unprecedented climate states.
3/25/2026
MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices
MsFormer transformer-based framework for predictive maintenance in industrial IoT environments with complex sensor data dependencies.
3/25/2026
Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
Reinforcement learning approach for training autoregressive image models with policy-based tuning optimizing quality and diversity simultaneously.
3/25/2026
SpecXMaster Technical Report
AI system for automated spectroscopy interpretation in scientific discovery, reducing human bias in spectral analysis.
3/25/2026
Polaris: A G\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
Polaris framework enabling self-improving agents for small language models through policy repair via experience abstraction and code modifications.
3/25/2026
DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
Adaptive prompt routing mechanism for selecting appropriate LLM or generative model based on input prompts, balancing fidelity and diversity.
3/25/2026
Sparser, Faster, Lighter Transformer Language Models
Sparse packing format and CUDA kernels leveraging unstructured sparsity in LLM feedforward layers to reduce computational costs and model size.
3/25/2026
A One-Inclusion Graph Approach to Multi-Group Learning
Tight upper bounds on sample complexity for multi-group learning using one-inclusion graph prediction strategy and bipartite matching.
3/25/2026
General Machine Learning: Theory for Learning Under Variable Regimes
Foundational theoretical framework for learning under regime variation where learner, memory state, and evaluation conditions evolve over time.
3/25/2026
GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL
Offline reinforcement learning method using guided expectation-maximization for action selection from multimodal action distributions in fixed datasets.
3/25/2026
Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
Model-based reinforcement learning using neural ODEs and SDEs to capture stochastic dynamics in fully and partially observed environments.
3/25/2026
A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling
End-to-end reinforcement learning framework for heterogeneous DAG scheduling with gap-aware generation enabling rapid schedule adaptation across environments.
3/25/2026
SafeSeek: Universal Attribution of Safety Circuits in Language Models
Mechanistic interpretability framework identifying and attributing safety circuits in LLMs responsible for alignment, jailbreak, and backdoor behaviors.
3/25/2026
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Off-policy value-based reinforcement learning framework for LLMs enabling improved data utilization and sample efficiency for long-horizon tasks.
3/25/2026
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
Length-aware scheduling method accelerating reinforcement learning training for LLMs by optimizing rollout phase efficiency during chain-of-thought generation.
3/25/2026
Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning
Continual learning framework using mixture-of-experts with similarity awareness for data-efficient adaptation to new tasks with limited samples.
3/25/2026
End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions
Computationally efficient reinforcement learning algorithm for linear function approximation in MDPs satisfying linear Bellman completeness.
3/25/2026
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions
Federated learning approach combining differential privacy and Byzantine robustness to protect against both data leakage and adversarial server attacks.
3/25/2026
Evaluating Prompting Strategies for Chart Question Answering with Large Language Models
Systematic evaluation of prompting strategies (zero-shot, few-shot, chain-of-thought) for chart question answering across GPT-3.5, GPT-4, and GPT-4o models on ChartQA dataset.
3/25/2026
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
TIPS framework improves RL training for search-augmented LLMs via turn-level reward shaping, addressing sparse rewards and credit assignment in reasoning tasks.
3/25/2026
The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
Multi-agent reinforcement learning agents develop efficient private communication protocol; performance drops with human-comprehensible language enforced.
3/25/2026
Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction
CHANRG benchmark reveals limited generalization of RNA secondary-structure prediction models. 170K structured RNA families dataset.
3/25/2026
Errors in AI-Assisted Retrieval of Medical Literature: A Comparative Study
Quantitative assessment of reference retrieval errors from 5 LLM platforms on 2,000 medical literature references. Evaluates Grok-2, ChatGPT, Gemini, Perplexity, DeepSeek.
3/25/2026
Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees
Theoretical analysis of low-rank knowledge distillation for LLMs with convergence and generalization guarantees. Covers compression techniques for efficient deployment.
3/25/2026
Computational Arbitrage in AI Model Markets
Framework for computational arbitrage in AI model markets where arbitrageurs allocate inference budget across competing providers to undercut pricing.
3/25/2026
mmFHE: mmWave Sensing with End-to-End Fully Homomorphic Encryption
First system enabling fully homomorphic encryption for end-to-end mmWave radar sensing with composable FHE kernels for signal processing and ML inference.