3/24/2026
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
Research on spectral alignment in forward-backward representations for successor representation learning in continuous spaces.
3/24/2026
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
MARLIN: multi-agent reinforcement learning method for efficient incremental DAG discovery from observational data.
3/24/2026
Collaborative Adaptive Curriculum for Progressive Knowledge Distillation
Collaborative knowledge distillation with adaptive curriculum learning for heterogeneous client capacities in edge visual analytics.
3/24/2026
Transformer-Based Predictive Maintenance for Risk-Aware Instrument Calibration
Transformer-based predictive maintenance model estimating instrument time-to-drift for optimized calibration scheduling.
3/24/2026
Bounded Coupled AI Learning Dynamics in Tri-Hierarchical Drone Swarms
Analysis of coupled learning dynamics in tri-hierarchical drone swarms with Hebbian learning, policy gradients, and meta-learning.
3/24/2026
Graph-Aware Text-Only Backdoor Poisoning for Text-Attributed Graphs
Graph-aware backdoor poisoning attack on text-attributed graphs through node text manipulation without structural changes.
3/24/2026
The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
Archive of 30 multivariate time series classification datasets extending the 2018 UEA benchmark for TSML research.
3/24/2026
CAMA: Exploring Collusive Adversarial Attacks in c-MARL
Study of collusive adversarial attacks against cooperative multi-agent reinforcement learning systems in robotics and UAV swarms.
3/24/2026
SymCircuit: Bayesian Structure Inference for Tractable Probabilistic Circuits via Entropy-Regularized Reinforcement Learning
SymCircuit: entropy-regularized RL approach for learning probabilistic circuit structure, replacing greedy search with generative policy.
3/24/2026
KV Cache Optimization Strategies for Scalable and Efficient LLM Inference
Survey of KV cache optimization strategies for efficient LLM inference with extended context windows from thousands to millions of tokens.
3/24/2026
Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP
Claude Opus 4.6 with Rocq proof assistant MCP tools autonomously proved 10/12 Putnam problems using compile-first strategy.
3/24/2026
SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operators
SLE-FNO: continual learning framework for Fourier Neural Operators to adapt to new experimental conditions without retraining.
3/24/2026
Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret
Theoretical analysis of RLHF with multi-source imperfect preferences from diverse annotators and reward models, deriving regret bounds.
3/24/2026
From Data to Laws: Neural Discovery of Conservation Laws Without False Positives
Neural-symbolic pipeline (NGCG) for discovering conservation laws from dynamical system data, addressing false positives and non-polynomial invariants.
3/24/2026
AE-LLM: Adaptive Efficiency Optimization for Large Language Models
Adaptive efficiency optimization framework combining multiple efficiency techniques for LLM deployment.
3/24/2026
Delightful Distributed Policy Gradient
Addresses negative learning from high-surprisal samples in distributed reinforcement learning with stale/mismatched actors.
3/24/2026
Does This Gradient Spark Joy?
Delightful Policy Gradient introduces efficiency signal to skip low-value backward passes in policy gradient training.
3/24/2026
RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
Row-momentum normalized preconditioning method for efficient training of deep neural networks.
3/24/2026
Understanding Behavior Cloning with Action Quantization
Analyzes behavior cloning with action quantization for autoregressive models in robotics and control tasks.
3/24/2026
LJ-Bench: Ontology-Based Benchmark for U.S. Crime
Ontology-based benchmark for evaluating LLM safety regarding illegal crime-related queries.
3/24/2026
MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
Memory-Keyed Attention mechanism reducing KV cache overhead for long-context LLM training and inference.
3/24/2026
Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems
Studies discrete data generation using diffusions with insights from random constraint satisfaction problems.
3/24/2026
Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
MixedDimKV method for efficient KV cache compression in transformer inference using mixed-dimension budget allocation.
3/24/2026
Optimal low-rank stochastic gradient estimation for LLM training
Low-rank stochastic gradient estimator for LLM training reducing memory constraints and gradient noise in high-dimensional spaces.
3/24/2026
CFNN: Continued Fraction Neural Network
Introduces continued fraction neural networks to capture non-linear functions with singularities using rational inductive bias.
3/24/2026
Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
Theoretical analysis of diffusion models on manifold-structured data examining statistical complexity and geometric properties.
3/24/2026
Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
arXiv paper on neuronal self-adaptation in spiking neural networks inspired by biological potassium channels for improved energy efficiency and robustness.
3/24/2026
Adversarial Attacks on Locally Private Graph Neural Networks
arXiv paper investigating adversarial attacks on graph neural networks trained with local differential privacy protections.
3/24/2026
Evaluating Uplift Modeling under Structural Biases: Insights into Metric Stability and Model Robustness
arXiv paper evaluating uplift modeling robustness under structural biases including selection bias, spillover effects, and unobserved confounding.
3/24/2026
Neural Autoregressive Flows for Markov Boundary Learning
arXiv paper on neural autoregressive flows for efficient Markov boundary discovery with theoretical reliability guarantees.
3/24/2026
Large Neighborhood Search meets Iterative Neural Constraint Heuristics
arXiv paper connecting iterative neural constraint heuristics to large neighborhood search, adapting ConsFormer into neural LNS procedure for optimization.
3/24/2026
Achieving $\widetilde{O}(1/\epsilon)$ Sample Complexity for Bilinear Systems Identification under Bounded Noises
arXiv paper on finite-sample identification for bilinear systems with bounded symmetric log-concave noise and trajectory-dependent regressors.
3/24/2026
Cross-Granularity Representations for Biological Sequences: Insights from ESM and BiGCARP
arXiv paper investigating cross-granularity representations in biological sequence models integrating hierarchical knowledge from nucleotides to genes.
3/24/2026
Simple Projection-Free Algorithm for Contextual Recommendation with Logarithmic Regret and Robustness
arXiv paper on projection-free algorithm for contextual recommendation bandits achieving logarithmic regret with improved efficiency over ONS methods.
3/24/2026
Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering
arXiv survey bridging academic attributed graph clustering methods with industrial deployment requirements and real-world constraints.
3/24/2026
A Knowledge-Informed Pretrained Model for Causal Discovery
arXiv paper on knowledge-informed pretrained model for causal discovery using coarse domain knowledge without relying on interventional data or strong priors.
3/24/2026
Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
arXiv paper introducing semantic sections as atlas-native feature ontology for interpreting obstructed representation spaces in neural networks.
3/24/2026
Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation
arXiv paper on incentive-aware federated learning framework addressing strategic agent participation with performance guarantees in distributed collaborative training.
3/24/2026
Beyond the Birkhoff Polytope: Spectral-Sphere-Constrained Hyper-Connections
arXiv paper generalizing residual connections into multi-stream hyper-connections with spectral-sphere constraints to maintain identity mapping stability.
3/24/2026
Natural Gradient Descent for Online Continual Learning
arXiv paper on natural gradient descent for online continual learning in image classification addressing catastrophic forgetting in non-i.i.d. data streams.
3/24/2026
Bayesian Scattering: A Principled Baseline for Uncertainty on Image Data
arXiv paper proposing Bayesian scattering as interpretable baseline for uncertainty quantification on image data using wavelet transforms and probabilistic modeling.
3/24/2026
LLM-ODE: Data-driven Discovery of Dynamical Systems with Large Language Models
LLM-based approach for automated discovery of governing equations in dynamical systems, replacing genetic programming with language models for efficiency.
3/24/2026
Enhancing LIME using Neural Decision Trees
Interpretability method combining LIME with neural decision trees for more stable and faithful explanations of complex models on tabular data.
3/24/2026
Discriminative Representation Learning for Clinical Prediction
Clinical prediction framework using discriminative representation learning aligned to outcomes rather than reconstruction objectives.
3/24/2026
Causally-Guided Diffusion for Stable Feature Selection
Feature selection method using causal principles and diffusion models to improve stability under distribution shifts.
3/24/2026
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
Investigation of how contextual recall emerges in transformers during pretraining vs. finetuning, examining in-context learning mechanisms for fact retrieval.
3/24/2026
Detection of adversarial intent in Human-AI teams using LLMs
Detection framework using LLMs to identify adversarial attacks against human-AI teams, covering data poisoning, prompt injection, and prompt engineering threats.
3/24/2026
From Causal Discovery to Dynamic Causal Inference in Neural Time Series
Method for discovering time-varying causal networks in neural time series without assuming known causal structure a priori.
3/24/2026
Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers
Theoretical analysis of synchronization gaps in diffusion transformers using coupled Ornstein-Uhlenbeck systems to explain mode interaction hierarchies in the reverse process.
3/24/2026
Structural Sensitivity in Compressed Transformers: Error Propagation, Lyapunov Stability, and Formally Verified Bounds
Study of sensitivity in compressed transformers across architectures, identifying which components degrade catastrophically vs. compress well, with formal bounds on error propagation.